Vertex AI API . projects . locations . endpoints

close()

Close httplib2 connections.

computeTokens(endpoint, body=None, x__xgafv=None)

Return a list of tokens based on the input text.

Args:
  endpoint: string, Required. The name of the Endpoint requested to get lists of tokens and token ids. (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for ComputeTokens RPC call.
  "contents": [ # Optional. Input content.
    { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
      "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
          "fileData": { # URI based data. # Optional. URI based data.
            "fileUri": "A String", # Required. URI.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              "a_key": "", # Properties of the object.
            },
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
              "a_key": "", # Properties of the object.
            },
          },
          "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
            "data": "A String", # Required. Raw bytes.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "text": "A String", # Optional. Text part (can be code).
          "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            "endOffset": "A String", # Optional. The end offset of the video.
            "startOffset": "A String", # Optional. The start offset of the video.
          },
        },
      ],
      "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  "instances": [ # Optional. The instances that are the input to token computing API call. Schema is identical to the prediction schema of the text model, even for the non-text models, like chat models, or Codey models.
    "",
  ],
  "model": "A String", # Optional. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for ComputeTokens RPC call.
  "tokensInfo": [ # Lists of tokens info from the input. A ComputeTokensRequest could have multiple instances with a prompt in each instance. We also need to return lists of tokens info for the request with multiple instances.
    { # Tokens info with a list of tokens and the corresponding list of token ids.
      "role": "A String", # Optional. Optional fields for the role from the corresponding Content.
      "tokenIds": [ # A list of token ids from the input.
        "A String",
      ],
      "tokens": [ # A list of tokens from the input.
        "A String",
      ],
    },
  ],
}

countTokens(endpoint, body=None, x__xgafv=None)

Perform a token counting.

Args:
  endpoint: string, Required. The name of the Endpoint requested to perform token counting. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.CountTokens.
  "contents": [ # Optional. Input content.
    { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
      "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
          "fileData": { # URI based data. # Optional. URI based data.
            "fileUri": "A String", # Required. URI.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              "a_key": "", # Properties of the object.
            },
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
              "a_key": "", # Properties of the object.
            },
          },
          "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
            "data": "A String", # Required. Raw bytes.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "text": "A String", # Optional. Text part (can be code).
          "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            "endOffset": "A String", # Optional. The end offset of the video.
            "startOffset": "A String", # Optional. The start offset of the video.
          },
        },
      ],
      "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  "generationConfig": { # Generation config. # Optional. Generation config that the model will use to generate the response.
    "audioTimestamp": True or False, # Optional. If enabled, audio timestamp will be included in the request to the model.
    "candidateCount": 42, # Optional. Number of candidates to generate.
    "frequencyPenalty": 3.14, # Optional. Frequency penalties.
    "logprobs": 42, # Optional. Logit probabilities.
    "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message.
    "presencePenalty": 3.14, # Optional. Positive penalties.
    "responseLogprobs": True or False, # Optional. If true, export the logprobs results in response.
    "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
    "responseSchema": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. The `Schema` object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response.
      "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
        # Object with schema name: GoogleCloudAiplatformV1Schema
      ],
      "default": "", # Optional. Default value of the data.
      "description": "A String", # Optional. The description of the data.
      "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
        "A String",
      ],
      "example": "", # Optional. Example of the object. Will only populated when the object is the root.
      "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
      "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
      "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
      "maxLength": "A String", # Optional. Maximum length of the Type.STRING
      "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
      "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
      "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
      "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
      "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
      "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
      "nullable": True or False, # Optional. Indicates if the value may be null.
      "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
      "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
        "A String",
      ],
      "required": [ # Optional. Required properties of Type.OBJECT.
        "A String",
      ],
      "title": "A String", # Optional. The title of the Schema.
      "type": "A String", # Optional. The type of the data.
    },
    "routingConfig": { # The configuration for routing the request to a specific model. # Optional. Routing configuration.
      "autoMode": { # When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. # Automated routing.
        "modelRoutingPreference": "A String", # The model routing preference.
      },
      "manualMode": { # When manual routing is set, the specified model will be used directly. # Manual routing.
        "modelName": "A String", # The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'.
      },
    },
    "seed": 42, # Optional. Seed.
    "stopSequences": [ # Optional. Stop sequences.
      "A String",
    ],
    "temperature": 3.14, # Optional. Controls the randomness of predictions.
    "topK": 3.14, # Optional. If specified, top-k sampling will be used.
    "topP": 3.14, # Optional. If specified, nucleus sampling will be used.
  },
  "instances": [ # Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.
    "",
  ],
  "model": "A String", # Optional. The name of the publisher model requested to serve the prediction. Format: `projects/{project}/locations/{location}/publishers/*/models/*`
  "systemInstruction": { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
    "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
      { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
        "fileData": { # URI based data. # Optional. URI based data.
          "fileUri": "A String", # Required. URI.
          "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
        },
        "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
          "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
            "a_key": "", # Properties of the object.
          },
          "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
        },
        "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
          "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
          "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
            "a_key": "", # Properties of the object.
          },
        },
        "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
          "data": "A String", # Required. Raw bytes.
          "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
        },
        "text": "A String", # Optional. Text part (can be code).
        "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
          "endOffset": "A String", # Optional. The end offset of the video.
          "startOffset": "A String", # Optional. The start offset of the video.
        },
      },
    ],
    "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
  },
  "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
    { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
      "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
        { # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client.
          "description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
          "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
          "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
            "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            "default": "", # Optional. Default value of the data.
            "description": "A String", # Optional. The description of the data.
            "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
              "A String",
            ],
            "example": "", # Optional. Example of the object. Will only populated when the object is the root.
            "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
            "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
            "maxLength": "A String", # Optional. Maximum length of the Type.STRING
            "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
            "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
            "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
            "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            "nullable": True or False, # Optional. Indicates if the value may be null.
            "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              "A String",
            ],
            "required": [ # Optional. Required properties of Type.OBJECT.
              "A String",
            ],
            "title": "A String", # Optional. The title of the Schema.
            "type": "A String", # Optional. The type of the data.
          },
          "response": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function.
            "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            "default": "", # Optional. Default value of the data.
            "description": "A String", # Optional. The description of the data.
            "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
              "A String",
            ],
            "example": "", # Optional. Example of the object. Will only populated when the object is the root.
            "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
            "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
            "maxLength": "A String", # Optional. Maximum length of the Type.STRING
            "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
            "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
            "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
            "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            "nullable": True or False, # Optional. Indicates if the value may be null.
            "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              "A String",
            ],
            "required": [ # Optional. Required properties of Type.OBJECT.
              "A String",
            ],
            "title": "A String", # Optional. The title of the Schema.
            "type": "A String", # Optional. The type of the data.
          },
        },
      ],
      "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
        "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
          "dynamicThreshold": 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
          "mode": "A String", # The mode of the predictor to be used in dynamic retrieval.
        },
      },
      "retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
        "disableAttribution": True or False, # Optional. Deprecated. This option is no longer supported.
        "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/products/agent-builder # Set to use data source powered by Vertex AI Search.
          "datastore": "A String", # Required. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
        },
        "vertexRagStore": { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
          "ragCorpora": [ # Optional. Deprecated. Please use rag_resources instead.
            "A String",
          ],
          "ragResources": [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
            { # The definition of the Rag resource.
              "ragCorpus": "A String", # Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
              "ragFileIds": [ # Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
                "A String",
              ],
            },
          ],
          "similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
          "vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
        },
      },
    },
  ],
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.CountTokens.
  "totalBillableCharacters": 42, # The total number of billable characters counted across all instances from the request.
  "totalTokens": 42, # The total number of tokens counted across all instances from the request.
}

create(parent, body=None, endpointId=None, x__xgafv=None)

Creates an Endpoint.

Args:
  parent: string, Required. The resource name of the Location to create the Endpoint in. Format: `projects/{project}/locations/{location}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
  "clientConnectionConfig": { # Configurations (e.g. inference timeout) that are applied on your endpoints. # Configurations that are applied to the endpoint for online prediction.
    "inferenceTimeout": "A String", # Customizable online prediction request timeout.
  },
  "createTime": "A String", # Output only. Timestamp when this Endpoint was created.
  "dedicatedEndpointDns": "A String", # Output only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: `https://{endpoint_id}.{region}-{project_number}.prediction.vertexai.goog`.
  "dedicatedEndpointEnabled": True or False, # If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
  "deployedModels": [ # Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    { # A deployment of a Model. Endpoints contain one or more DeployedModels.
      "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
        "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
      },
      "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
      "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
        "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
          { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
            "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
            "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
          },
        ],
        "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
          "acceleratorCount": 42, # The number of accelerators to attach to the machine.
          "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
          "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
          "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
            "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
            "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
            "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
              "A String",
            ],
          },
          "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
        },
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
        "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
        "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
      },
      "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
      "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
      "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
      "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
      "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
        "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
          "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
          "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
            "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
              "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
                "",
              ],
              "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
              "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
              "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
                "maxValue": 3.14, # The maximum permissible value for this feature.
                "minValue": 3.14, # The minimum permissible value for this feature.
                "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
                "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
              },
              "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
              "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
                "A String",
              ],
              "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
                "",
              ],
              "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
              "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
              "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
                "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
                "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
                "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
                "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
                "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
                "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
              },
            },
          },
          "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
          "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
            "a_key": { # Metadata of the prediction output to be explained.
              "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
              "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
              "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
            },
          },
        },
        "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
          "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
            "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
              "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
              "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
                "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                  "A String",
                ],
              },
            },
            "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
            "neighborCount": 42, # The number of neighbors to return when querying for examples.
            "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
              "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
              "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
            },
          },
          "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
          "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
            "",
          ],
          "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
            "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
          },
          "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
          "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
        },
      },
      "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
      "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
      "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
      "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
        "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
        "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
        "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
        "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
      },
      "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
      "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
      "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
        "a_key": "A String",
      },
    },
  ],
  "description": "A String", # The description of the Endpoint.
  "displayName": "A String", # Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  "enablePrivateServiceConnect": True or False, # Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
  "encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    "kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  "etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
  "labels": { # The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    "a_key": "A String",
  },
  "modelDeploymentMonitoringJob": "A String", # Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}`
  "name": "A String", # Output only. The resource name of the Endpoint.
  "network": "A String", # Optional. The full name of the Google Compute Engine [network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. [Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert): `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is network name.
  "predictRequestResponseLoggingConfig": { # Configuration for logging request-response to a BigQuery table. # Configures the request-response logging for online prediction.
    "bigqueryDestination": { # The BigQuery location for the output content. # BigQuery table for logging. If only given a project, a new dataset will be created with name `logging__` where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name `request_response_logging`
      "outputUri": "A String", # Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: `bq://projectId` or `bq://projectId.bqDatasetId` or `bq://projectId.bqDatasetId.bqTableId`.
    },
    "enabled": True or False, # If logging is enabled or not.
    "samplingRate": 3.14, # Percentage of requests to be logged, expressed as a fraction in range(0,1].
  },
  "privateServiceConnectConfig": { # Represents configuration for private service connect. # Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive.
    "enablePrivateServiceConnect": True or False, # Required. If true, expose the IndexEndpoint via private service connect.
    "projectAllowlist": [ # A list of Projects from which the forwarding rule will target the service attachment.
      "A String",
    ],
    "serviceAttachment": "A String", # Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect.
  },
  "satisfiesPzi": True or False, # Output only. Reserved for future use.
  "satisfiesPzs": True or False, # Output only. Reserved for future use.
  "trafficSplit": { # A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    "a_key": 42,
  },
  "updateTime": "A String", # Output only. Timestamp when this Endpoint was last updated.
}

  endpointId: string, Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are `[a-z0-9-]`. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are `[0-9]` with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as `?endpoint_id=12345`. This is the fallback for fields that are not included in either the URI or the body.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

delete(name, x__xgafv=None)

Deletes an Endpoint.

Args:
  name: string, Required. The name of the Endpoint resource to be deleted. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

deployModel(endpoint, body=None, x__xgafv=None)

Deploys a Model into this Endpoint, creating a DeployedModel within it.

Args:
  endpoint: string, Required. The name of the Endpoint resource into which to deploy a Model. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for EndpointService.DeployModel.
  "deployedModel": { # A deployment of a Model. Endpoints contain one or more DeployedModels. # Required. The DeployedModel to be created within the Endpoint. Note that Endpoint.traffic_split must be updated for the DeployedModel to start receiving traffic, either as part of this call, or via EndpointService.UpdateEndpoint.
    "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
      "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
      "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    },
    "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
    "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
      "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
        { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
          "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
          "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
        },
      ],
      "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
        "acceleratorCount": 42, # The number of accelerators to attach to the machine.
        "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
        "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
        "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
          "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
          "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
          "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
            "A String",
          ],
        },
        "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
      },
      "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
      "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
      "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
    },
    "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
    "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
    "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
      "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
        "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
        "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
          "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
            "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
            "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
              "",
            ],
            "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
            "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
            "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
              "maxValue": 3.14, # The maximum permissible value for this feature.
              "minValue": 3.14, # The minimum permissible value for this feature.
              "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
              "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
            },
            "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
            "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
              "A String",
            ],
            "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
            "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
              "",
            ],
            "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
            "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
            "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
              "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
              "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
              "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
              "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
              "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
              "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
            },
          },
        },
        "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
        "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
          "a_key": { # Metadata of the prediction output to be explained.
            "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
            "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
            "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
          },
        },
      },
      "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
        "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
          "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
            "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
            "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
              "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                "A String",
              ],
            },
          },
          "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
          "neighborCount": 42, # The number of neighbors to return when querying for examples.
          "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
            "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
            "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
          },
        },
        "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
          "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
            "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
          },
          "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
            "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
              "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                { # Noise sigma for a single feature.
                  "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                  "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                },
              ],
            },
            "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
            "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
          },
          "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
        },
        "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
          "",
        ],
        "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
          "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
        },
        "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
        "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
          "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
            "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
          },
          "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
            "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
              "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                { # Noise sigma for a single feature.
                  "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                  "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                },
              ],
            },
            "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
            "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
          },
          "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
        },
      },
    },
    "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
    "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
    "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
    "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
      "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
      "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
      "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
      "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
    },
    "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
    "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
    "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
      "a_key": "A String",
    },
  },
  "trafficSplit": { # A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If this field is non-empty, then the Endpoint's traffic_split will be overwritten with it. To refer to the ID of the just being deployed Model, a "0" should be used, and the actual ID of the new DeployedModel will be filled in its place by this method. The traffic percentage values must add up to 100. If this field is empty, then the Endpoint's traffic_split is not updated.
    "a_key": 42,
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

directPredict(endpoint, body=None, x__xgafv=None)

Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.DirectPredict.
  "inputs": [ # The prediction input.
    { # A tensor value type.
      "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
        True or False,
      ],
      "bytesVal": [ # STRING
        "A String",
      ],
      "doubleVal": [ # DOUBLE
        3.14,
      ],
      "dtype": "A String", # The data type of tensor.
      "floatVal": [ # FLOAT
        3.14,
      ],
      "int64Val": [ # INT64
        "A String",
      ],
      "intVal": [ # INT_8 INT_16 INT_32
        42,
      ],
      "listVal": [ # A list of tensor values.
        # Object with schema name: GoogleCloudAiplatformV1Tensor
      ],
      "shape": [ # Shape of the tensor.
        "A String",
      ],
      "stringVal": [ # STRING
        "A String",
      ],
      "structVal": { # A map of string to tensor.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
      },
      "tensorVal": "A String", # Serialized raw tensor content.
      "uint64Val": [ # UINT64
        "A String",
      ],
      "uintVal": [ # UINT8 UINT16 UINT32
        42,
      ],
    },
  ],
  "parameters": { # A tensor value type. # The parameters that govern the prediction.
    "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
      True or False,
    ],
    "bytesVal": [ # STRING
      "A String",
    ],
    "doubleVal": [ # DOUBLE
      3.14,
    ],
    "dtype": "A String", # The data type of tensor.
    "floatVal": [ # FLOAT
      3.14,
    ],
    "int64Val": [ # INT64
      "A String",
    ],
    "intVal": [ # INT_8 INT_16 INT_32
      42,
    ],
    "listVal": [ # A list of tensor values.
      # Object with schema name: GoogleCloudAiplatformV1Tensor
    ],
    "shape": [ # Shape of the tensor.
      "A String",
    ],
    "stringVal": [ # STRING
      "A String",
    ],
    "structVal": { # A map of string to tensor.
      "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
    },
    "tensorVal": "A String", # Serialized raw tensor content.
    "uint64Val": [ # UINT64
      "A String",
    ],
    "uintVal": [ # UINT8 UINT16 UINT32
      42,
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.DirectPredict.
  "outputs": [ # The prediction output.
    { # A tensor value type.
      "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
        True or False,
      ],
      "bytesVal": [ # STRING
        "A String",
      ],
      "doubleVal": [ # DOUBLE
        3.14,
      ],
      "dtype": "A String", # The data type of tensor.
      "floatVal": [ # FLOAT
        3.14,
      ],
      "int64Val": [ # INT64
        "A String",
      ],
      "intVal": [ # INT_8 INT_16 INT_32
        42,
      ],
      "listVal": [ # A list of tensor values.
        # Object with schema name: GoogleCloudAiplatformV1Tensor
      ],
      "shape": [ # Shape of the tensor.
        "A String",
      ],
      "stringVal": [ # STRING
        "A String",
      ],
      "structVal": { # A map of string to tensor.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
      },
      "tensorVal": "A String", # Serialized raw tensor content.
      "uint64Val": [ # UINT64
        "A String",
      ],
      "uintVal": [ # UINT8 UINT16 UINT32
        42,
      ],
    },
  ],
  "parameters": { # A tensor value type. # The parameters that govern the prediction.
    "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
      True or False,
    ],
    "bytesVal": [ # STRING
      "A String",
    ],
    "doubleVal": [ # DOUBLE
      3.14,
    ],
    "dtype": "A String", # The data type of tensor.
    "floatVal": [ # FLOAT
      3.14,
    ],
    "int64Val": [ # INT64
      "A String",
    ],
    "intVal": [ # INT_8 INT_16 INT_32
      42,
    ],
    "listVal": [ # A list of tensor values.
      # Object with schema name: GoogleCloudAiplatformV1Tensor
    ],
    "shape": [ # Shape of the tensor.
      "A String",
    ],
    "stringVal": [ # STRING
      "A String",
    ],
    "structVal": { # A map of string to tensor.
      "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
    },
    "tensorVal": "A String", # Serialized raw tensor content.
    "uint64Val": [ # UINT64
      "A String",
    ],
    "uintVal": [ # UINT8 UINT16 UINT32
      42,
    ],
  },
}

directRawPredict(endpoint, body=None, x__xgafv=None)

Perform an unary online prediction request to a gRPC model server for custom containers.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.DirectRawPredict.
  "input": "A String", # The prediction input.
  "methodName": "A String", # Fully qualified name of the API method being invoked to perform predictions. Format: `/namespace.Service/Method/` Example: `/tensorflow.serving.PredictionService/Predict`
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.DirectRawPredict.
  "output": "A String", # The prediction output.
}

explain(endpoint, body=None, x__xgafv=None)

Perform an online explanation. If deployed_model_id is specified, the corresponding DeployModel must have explanation_spec populated. If deployed_model_id is not specified, all DeployedModels must have explanation_spec populated.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the explanation. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.Explain.
  "deployedModelId": "A String", # If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.
  "explanationSpecOverride": { # The ExplanationSpec entries that can be overridden at online explanation time. # If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as: - Explaining top-5 predictions results as opposed to top-1; - Increasing path count or step count of the attribution methods to reduce approximate errors; - Using different baselines for explaining the prediction results.
    "examplesOverride": { # Overrides for example-based explanations. # The example-based explanations parameter overrides.
      "crowdingCount": 42, # The number of neighbors to return that have the same crowding tag.
      "dataFormat": "A String", # The format of the data being provided with each call.
      "neighborCount": 42, # The number of neighbors to return.
      "restrictions": [ # Restrict the resulting nearest neighbors to respect these constraints.
        { # Restrictions namespace for example-based explanations overrides.
          "allow": [ # The list of allowed tags.
            "A String",
          ],
          "deny": [ # The list of deny tags.
            "A String",
          ],
          "namespaceName": "A String", # The namespace name.
        },
      ],
      "returnEmbeddings": True or False, # If true, return the embeddings instead of neighbors.
    },
    "metadata": { # The ExplanationMetadata entries that can be overridden at online explanation time. # The metadata to be overridden. If not specified, no metadata is overridden.
      "inputs": { # Required. Overrides the input metadata of the features. The key is the name of the feature to be overridden. The keys specified here must exist in the input metadata to be overridden. If a feature is not specified here, the corresponding feature's input metadata is not overridden.
        "a_key": { # The input metadata entries to be overridden.
          "inputBaselines": [ # Baseline inputs for this feature. This overrides the `input_baseline` field of the ExplanationMetadata.InputMetadata object of the corresponding feature's input metadata. If it's not specified, the original baselines are not overridden.
            "",
          ],
        },
      },
    },
    "parameters": { # Parameters to configure explaining for Model's predictions. # The parameters to be overridden. Note that the attribution method cannot be changed. If not specified, no parameter is overridden.
      "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
        "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
          "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
          "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
            "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
              "A String",
            ],
          },
        },
        "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
        "neighborCount": 42, # The number of neighbors to return when querying for examples.
        "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
          "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
          "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
        },
      },
      "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
        "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
          "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
        },
        "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
          "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
            "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
              { # Noise sigma for a single feature.
                "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
              },
            ],
          },
          "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
          "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
        },
        "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
      },
      "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
        "",
      ],
      "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
        "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
      },
      "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
      "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
        "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
          "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
        },
        "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
          "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
            "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
              { # Noise sigma for a single feature.
                "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
              },
            ],
          },
          "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
          "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
        },
        "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
      },
    },
  },
  "instances": [ # Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
    "",
  ],
  "parameters": "", # The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.Explain.
  "deployedModelId": "A String", # ID of the Endpoint's DeployedModel that served this explanation.
  "explanations": [ # The explanations of the Model's PredictResponse.predictions. It has the same number of elements as instances to be explained.
    { # Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given instance.
      "attributions": [ # Output only. Feature attributions grouped by predicted outputs. For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining. By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of `0.4` for approving a loan application, the model's decision is to reject the application since `p(reject) = 0.6 > p(approve) = 0.4`, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class. If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.
        { # Attribution that explains a particular prediction output.
          "approximationError": 3.14, # Output only. Error of feature_attributions caused by approximation used in the explanation method. Lower value means more precise attributions. * For Sampled Shapley attribution, increasing path_count might reduce the error. * For Integrated Gradients attribution, increasing step_count might reduce the error. * For XRAI attribution, increasing step_count might reduce the error. See [this introduction](/vertex-ai/docs/explainable-ai/overview) for more information.
          "baselineOutputValue": 3.14, # Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in ExplanationMetadata.inputs. The field name of the output is determined by the key in ExplanationMetadata.outputs. If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by output_index. If there are multiple baselines, their output values are averaged.
          "featureAttributions": "", # Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs. The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result. The format of the value is determined by the feature's input format: * If the feature is a scalar value, the attribution value is a floating number. * If the feature is an array of scalar values, the attribution value is an array. * If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct. The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).
          "instanceOutputValue": 3.14, # Output only. Model predicted output on the corresponding explanation instance. The field name of the output is determined by the key in ExplanationMetadata.outputs. If the Model predicted output has multiple dimensions, this is the value in the output located by output_index.
          "outputDisplayName": "A String", # Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model. This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.
          "outputIndex": [ # Output only. The index that locates the explained prediction output. If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.
            42,
          ],
          "outputName": "A String", # Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.
        },
      ],
      "neighbors": [ # Output only. List of the nearest neighbors for example-based explanations. For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.
        { # Neighbors for example-based explanations.
          "neighborDistance": 3.14, # Output only. The neighbor distance.
          "neighborId": "A String", # Output only. The neighbor id.
        },
      ],
    },
  ],
  "predictions": [ # The predictions that are the output of the predictions call. Same as PredictResponse.predictions.
    "",
  ],
}

fetchPredictOperation(endpoint, body=None, x__xgafv=None)

Fetch an asynchronous online prediction operation.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` or `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.FetchPredictOperation.
  "operationName": "A String", # Required. The server-assigned name for the operation.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

generateContent(model, body=None, x__xgafv=None)

Generate content with multimodal inputs.

Args:
  model: string, Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for [PredictionService.GenerateContent].
  "contents": [ # Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
    { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
      "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
          "fileData": { # URI based data. # Optional. URI based data.
            "fileUri": "A String", # Required. URI.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              "a_key": "", # Properties of the object.
            },
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
              "a_key": "", # Properties of the object.
            },
          },
          "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
            "data": "A String", # Required. Raw bytes.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "text": "A String", # Optional. Text part (can be code).
          "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            "endOffset": "A String", # Optional. The end offset of the video.
            "startOffset": "A String", # Optional. The start offset of the video.
          },
        },
      ],
      "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  "generationConfig": { # Generation config. # Optional. Generation config.
    "audioTimestamp": True or False, # Optional. If enabled, audio timestamp will be included in the request to the model.
    "candidateCount": 42, # Optional. Number of candidates to generate.
    "frequencyPenalty": 3.14, # Optional. Frequency penalties.
    "logprobs": 42, # Optional. Logit probabilities.
    "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message.
    "presencePenalty": 3.14, # Optional. Positive penalties.
    "responseLogprobs": True or False, # Optional. If true, export the logprobs results in response.
    "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
    "responseSchema": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. The `Schema` object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response.
      "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
        # Object with schema name: GoogleCloudAiplatformV1Schema
      ],
      "default": "", # Optional. Default value of the data.
      "description": "A String", # Optional. The description of the data.
      "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
        "A String",
      ],
      "example": "", # Optional. Example of the object. Will only populated when the object is the root.
      "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
      "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
      "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
      "maxLength": "A String", # Optional. Maximum length of the Type.STRING
      "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
      "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
      "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
      "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
      "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
      "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
      "nullable": True or False, # Optional. Indicates if the value may be null.
      "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
      "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
        "A String",
      ],
      "required": [ # Optional. Required properties of Type.OBJECT.
        "A String",
      ],
      "title": "A String", # Optional. The title of the Schema.
      "type": "A String", # Optional. The type of the data.
    },
    "routingConfig": { # The configuration for routing the request to a specific model. # Optional. Routing configuration.
      "autoMode": { # When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. # Automated routing.
        "modelRoutingPreference": "A String", # The model routing preference.
      },
      "manualMode": { # When manual routing is set, the specified model will be used directly. # Manual routing.
        "modelName": "A String", # The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'.
      },
    },
    "seed": 42, # Optional. Seed.
    "stopSequences": [ # Optional. Stop sequences.
      "A String",
    ],
    "temperature": 3.14, # Optional. Controls the randomness of predictions.
    "topK": 3.14, # Optional. If specified, top-k sampling will be used.
    "topP": 3.14, # Optional. If specified, nucleus sampling will be used.
  },
  "labels": { # Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.
    "a_key": "A String",
  },
  "safetySettings": [ # Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
    { # Safety settings.
      "category": "A String", # Required. Harm category.
      "method": "A String", # Optional. Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score.
      "threshold": "A String", # Required. The harm block threshold.
    },
  ],
  "systemInstruction": { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
    "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
      { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
        "fileData": { # URI based data. # Optional. URI based data.
          "fileUri": "A String", # Required. URI.
          "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
        },
        "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
          "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
            "a_key": "", # Properties of the object.
          },
          "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
        },
        "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
          "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
          "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
            "a_key": "", # Properties of the object.
          },
        },
        "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
          "data": "A String", # Required. Raw bytes.
          "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
        },
        "text": "A String", # Optional. Text part (can be code).
        "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
          "endOffset": "A String", # Optional. The end offset of the video.
          "startOffset": "A String", # Optional. The start offset of the video.
        },
      },
    ],
    "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
  },
  "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request.
    "functionCallingConfig": { # Function calling config. # Optional. Function calling config.
      "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
        "A String",
      ],
      "mode": "A String", # Optional. Function calling mode.
    },
  },
  "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
    { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
      "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
        { # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client.
          "description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
          "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
          "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
            "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            "default": "", # Optional. Default value of the data.
            "description": "A String", # Optional. The description of the data.
            "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
              "A String",
            ],
            "example": "", # Optional. Example of the object. Will only populated when the object is the root.
            "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
            "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
            "maxLength": "A String", # Optional. Maximum length of the Type.STRING
            "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
            "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
            "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
            "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            "nullable": True or False, # Optional. Indicates if the value may be null.
            "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              "A String",
            ],
            "required": [ # Optional. Required properties of Type.OBJECT.
              "A String",
            ],
            "title": "A String", # Optional. The title of the Schema.
            "type": "A String", # Optional. The type of the data.
          },
          "response": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function.
            "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            "default": "", # Optional. Default value of the data.
            "description": "A String", # Optional. The description of the data.
            "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
              "A String",
            ],
            "example": "", # Optional. Example of the object. Will only populated when the object is the root.
            "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
            "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
            "maxLength": "A String", # Optional. Maximum length of the Type.STRING
            "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
            "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
            "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
            "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            "nullable": True or False, # Optional. Indicates if the value may be null.
            "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              "A String",
            ],
            "required": [ # Optional. Required properties of Type.OBJECT.
              "A String",
            ],
            "title": "A String", # Optional. The title of the Schema.
            "type": "A String", # Optional. The type of the data.
          },
        },
      ],
      "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
        "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
          "dynamicThreshold": 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
          "mode": "A String", # The mode of the predictor to be used in dynamic retrieval.
        },
      },
      "retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
        "disableAttribution": True or False, # Optional. Deprecated. This option is no longer supported.
        "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/products/agent-builder # Set to use data source powered by Vertex AI Search.
          "datastore": "A String", # Required. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
        },
        "vertexRagStore": { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
          "ragCorpora": [ # Optional. Deprecated. Please use rag_resources instead.
            "A String",
          ],
          "ragResources": [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
            { # The definition of the Rag resource.
              "ragCorpus": "A String", # Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
              "ragFileIds": [ # Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
                "A String",
              ],
            },
          ],
          "similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
          "vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
        },
      },
    },
  ],
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for [PredictionService.GenerateContent].
  "candidates": [ # Output only. Generated candidates.
    { # A response candidate generated from the model.
      "avgLogprobs": 3.14, # Output only. Average log probability score of the candidate.
      "citationMetadata": { # A collection of source attributions for a piece of content. # Output only. Source attribution of the generated content.
        "citations": [ # Output only. List of citations.
          { # Source attributions for content.
            "endIndex": 42, # Output only. End index into the content.
            "license": "A String", # Output only. License of the attribution.
            "publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date of the attribution.
              "day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
              "month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
              "year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
            },
            "startIndex": 42, # Output only. Start index into the content.
            "title": "A String", # Output only. Title of the attribution.
            "uri": "A String", # Output only. Url reference of the attribution.
          },
        ],
      },
      "content": { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. # Output only. Content parts of the candidate.
        "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
          { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
            "fileData": { # URI based data. # Optional. URI based data.
              "fileUri": "A String", # Required. URI.
              "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
            },
            "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
              "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
                "a_key": "", # Properties of the object.
              },
              "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
            },
            "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
              "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
              "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
                "a_key": "", # Properties of the object.
              },
            },
            "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
              "data": "A String", # Required. Raw bytes.
              "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
            },
            "text": "A String", # Optional. Text part (can be code).
            "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
              "endOffset": "A String", # Optional. The end offset of the video.
              "startOffset": "A String", # Optional. The start offset of the video.
            },
          },
        ],
        "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
      },
      "finishMessage": "A String", # Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when `finish_reason` is set.
      "finishReason": "A String", # Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
      "groundingMetadata": { # Metadata returned to client when grounding is enabled. # Output only. Metadata specifies sources used to ground generated content.
        "groundingChunks": [ # List of supporting references retrieved from specified grounding source.
          { # Grounding chunk.
            "retrievedContext": { # Chunk from context retrieved by the retrieval tools. # Grounding chunk from context retrieved by the retrieval tools.
              "text": "A String", # Text of the attribution.
              "title": "A String", # Title of the attribution.
              "uri": "A String", # URI reference of the attribution.
            },
            "web": { # Chunk from the web. # Grounding chunk from the web.
              "title": "A String", # Title of the chunk.
              "uri": "A String", # URI reference of the chunk.
            },
          },
        ],
        "groundingSupports": [ # Optional. List of grounding support.
          { # Grounding support.
            "confidenceScores": [ # Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the grounding_chunk_indices.
              3.14,
            ],
            "groundingChunkIndices": [ # A list of indices (into 'grounding_chunk') specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved content attributed to the claim.
              42,
            ],
            "segment": { # Segment of the content. # Segment of the content this support belongs to.
              "endIndex": 42, # Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero.
              "partIndex": 42, # Output only. The index of a Part object within its parent Content object.
              "startIndex": 42, # Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero.
              "text": "A String", # Output only. The text corresponding to the segment from the response.
            },
          },
        ],
        "retrievalMetadata": { # Metadata related to retrieval in the grounding flow. # Optional. Output only. Retrieval metadata.
          "googleSearchDynamicRetrievalScore": 3.14, # Optional. Score indicating how likely information from Google Search could help answer the prompt. The score is in the range `[0, 1]`, where 0 is the least likely and 1 is the most likely. This score is only populated when Google Search grounding and dynamic retrieval is enabled. It will be compared to the threshold to determine whether to trigger Google Search.
        },
        "searchEntryPoint": { # Google search entry point. # Optional. Google search entry for the following-up web searches.
          "renderedContent": "A String", # Optional. Web content snippet that can be embedded in a web page or an app webview.
          "sdkBlob": "A String", # Optional. Base64 encoded JSON representing array of tuple.
        },
        "webSearchQueries": [ # Optional. Web search queries for the following-up web search.
          "A String",
        ],
      },
      "index": 42, # Output only. Index of the candidate.
      "logprobsResult": { # Logprobs Result # Output only. Log-likelihood scores for the response tokens and top tokens
        "chosenCandidates": [ # Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.
          { # Candidate for the logprobs token and score.
            "logProbability": 3.14, # The candidate's log probability.
            "token": "A String", # The candidate's token string value.
            "tokenId": 42, # The candidate's token id value.
          },
        ],
        "topCandidates": [ # Length = total number of decoding steps.
          { # Candidates with top log probabilities at each decoding step.
            "candidates": [ # Sorted by log probability in descending order.
              { # Candidate for the logprobs token and score.
                "logProbability": 3.14, # The candidate's log probability.
                "token": "A String", # The candidate's token string value.
                "tokenId": 42, # The candidate's token id value.
              },
            ],
          },
        ],
      },
      "safetyRatings": [ # Output only. List of ratings for the safety of a response candidate. There is at most one rating per category.
        { # Safety rating corresponding to the generated content.
          "blocked": True or False, # Output only. Indicates whether the content was filtered out because of this rating.
          "category": "A String", # Output only. Harm category.
          "probability": "A String", # Output only. Harm probability levels in the content.
          "probabilityScore": 3.14, # Output only. Harm probability score.
          "severity": "A String", # Output only. Harm severity levels in the content.
          "severityScore": 3.14, # Output only. Harm severity score.
        },
      ],
    },
  ],
  "modelVersion": "A String", # Output only. The model version used to generate the response.
  "promptFeedback": { # Content filter results for a prompt sent in the request. # Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.
    "blockReason": "A String", # Output only. Blocked reason.
    "blockReasonMessage": "A String", # Output only. A readable block reason message.
    "safetyRatings": [ # Output only. Safety ratings.
      { # Safety rating corresponding to the generated content.
        "blocked": True or False, # Output only. Indicates whether the content was filtered out because of this rating.
        "category": "A String", # Output only. Harm category.
        "probability": "A String", # Output only. Harm probability levels in the content.
        "probabilityScore": 3.14, # Output only. Harm probability score.
        "severity": "A String", # Output only. Harm severity levels in the content.
        "severityScore": 3.14, # Output only. Harm severity score.
      },
    ],
  },
  "usageMetadata": { # Usage metadata about response(s). # Usage metadata about the response(s).
    "candidatesTokenCount": 42, # Number of tokens in the response(s).
    "promptTokenCount": 42, # Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
    "totalTokenCount": 42, # Total token count for prompt and response candidates.
  },
}

get(name, x__xgafv=None)

Gets an Endpoint.

Args:
  name: string, Required. The name of the Endpoint resource. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
  "clientConnectionConfig": { # Configurations (e.g. inference timeout) that are applied on your endpoints. # Configurations that are applied to the endpoint for online prediction.
    "inferenceTimeout": "A String", # Customizable online prediction request timeout.
  },
  "createTime": "A String", # Output only. Timestamp when this Endpoint was created.
  "dedicatedEndpointDns": "A String", # Output only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: `https://{endpoint_id}.{region}-{project_number}.prediction.vertexai.goog`.
  "dedicatedEndpointEnabled": True or False, # If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
  "deployedModels": [ # Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    { # A deployment of a Model. Endpoints contain one or more DeployedModels.
      "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
        "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
      },
      "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
      "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
        "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
          { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
            "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
            "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
          },
        ],
        "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
          "acceleratorCount": 42, # The number of accelerators to attach to the machine.
          "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
          "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
          "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
            "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
            "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
            "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
              "A String",
            ],
          },
          "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
        },
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
        "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
        "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
      },
      "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
      "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
      "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
      "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
      "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
        "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
          "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
          "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
            "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
              "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
                "",
              ],
              "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
              "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
              "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
                "maxValue": 3.14, # The maximum permissible value for this feature.
                "minValue": 3.14, # The minimum permissible value for this feature.
                "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
                "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
              },
              "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
              "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
                "A String",
              ],
              "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
                "",
              ],
              "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
              "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
              "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
                "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
                "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
                "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
                "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
                "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
                "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
              },
            },
          },
          "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
          "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
            "a_key": { # Metadata of the prediction output to be explained.
              "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
              "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
              "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
            },
          },
        },
        "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
          "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
            "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
              "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
              "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
                "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                  "A String",
                ],
              },
            },
            "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
            "neighborCount": 42, # The number of neighbors to return when querying for examples.
            "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
              "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
              "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
            },
          },
          "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
          "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
            "",
          ],
          "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
            "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
          },
          "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
          "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
        },
      },
      "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
      "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
      "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
      "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
        "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
        "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
        "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
        "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
      },
      "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
      "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
      "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
        "a_key": "A String",
      },
    },
  ],
  "description": "A String", # The description of the Endpoint.
  "displayName": "A String", # Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  "enablePrivateServiceConnect": True or False, # Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
  "encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    "kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  "etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
  "labels": { # The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    "a_key": "A String",
  },
  "modelDeploymentMonitoringJob": "A String", # Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}`
  "name": "A String", # Output only. The resource name of the Endpoint.
  "network": "A String", # Optional. The full name of the Google Compute Engine [network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. [Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert): `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is network name.
  "predictRequestResponseLoggingConfig": { # Configuration for logging request-response to a BigQuery table. # Configures the request-response logging for online prediction.
    "bigqueryDestination": { # The BigQuery location for the output content. # BigQuery table for logging. If only given a project, a new dataset will be created with name `logging__` where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name `request_response_logging`
      "outputUri": "A String", # Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: `bq://projectId` or `bq://projectId.bqDatasetId` or `bq://projectId.bqDatasetId.bqTableId`.
    },
    "enabled": True or False, # If logging is enabled or not.
    "samplingRate": 3.14, # Percentage of requests to be logged, expressed as a fraction in range(0,1].
  },
  "privateServiceConnectConfig": { # Represents configuration for private service connect. # Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive.
    "enablePrivateServiceConnect": True or False, # Required. If true, expose the IndexEndpoint via private service connect.
    "projectAllowlist": [ # A list of Projects from which the forwarding rule will target the service attachment.
      "A String",
    ],
    "serviceAttachment": "A String", # Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect.
  },
  "satisfiesPzi": True or False, # Output only. Reserved for future use.
  "satisfiesPzs": True or False, # Output only. Reserved for future use.
  "trafficSplit": { # A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    "a_key": 42,
  },
  "updateTime": "A String", # Output only. Timestamp when this Endpoint was last updated.
}

list(parent, filter=None, orderBy=None, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)

Lists Endpoints in a Location.

Args:
  parent: string, Required. The resource name of the Location from which to list the Endpoints. Format: `projects/{project}/locations/{location}` (required)
  filter: string, Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports `=` and `!=`. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports `=` and `!=`. * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:*` or `labels:key` - key existence * A key including a space must be quoted. `labels."a key"`. * `base_model_name` only supports `=`. Some examples: * `endpoint=1` * `displayName="myDisplayName"` * `labels.myKey="myValue"` * `baseModelName="text-bison"`
  orderBy: string, A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * `display_name` * `create_time` * `update_time` Example: `display_name, create_time desc`.
  pageSize: integer, Optional. The standard list page size.
  pageToken: string, Optional. The standard list page token. Typically obtained via ListEndpointsResponse.next_page_token of the previous EndpointService.ListEndpoints call.
  readMask: string, Optional. Mask specifying which fields to read.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for EndpointService.ListEndpoints.
  "endpoints": [ # List of Endpoints in the requested page.
    { # Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
      "clientConnectionConfig": { # Configurations (e.g. inference timeout) that are applied on your endpoints. # Configurations that are applied to the endpoint for online prediction.
        "inferenceTimeout": "A String", # Customizable online prediction request timeout.
      },
      "createTime": "A String", # Output only. Timestamp when this Endpoint was created.
      "dedicatedEndpointDns": "A String", # Output only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: `https://{endpoint_id}.{region}-{project_number}.prediction.vertexai.goog`.
      "dedicatedEndpointEnabled": True or False, # If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
      "deployedModels": [ # Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
        { # A deployment of a Model. Endpoints contain one or more DeployedModels.
          "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
            "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
            "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
          },
          "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
          "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
            "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
              { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
                "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
                "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
              },
            ],
            "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
              "acceleratorCount": 42, # The number of accelerators to attach to the machine.
              "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
              "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
              "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
                "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
                "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
                "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
                  "A String",
                ],
              },
              "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
            },
            "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
            "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
            "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
          },
          "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
          "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
          "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
          "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
          "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
            "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
              "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
              "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
                "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
                  "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
                  "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
                    "",
                  ],
                  "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
                  "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
                  "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
                    "maxValue": 3.14, # The maximum permissible value for this feature.
                    "minValue": 3.14, # The minimum permissible value for this feature.
                    "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
                    "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
                  },
                  "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
                  "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
                    "A String",
                  ],
                  "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
                  "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
                    "",
                  ],
                  "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
                  "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
                  "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
                    "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
                    "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
                    "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
                    "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
                    "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
                    "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
                  },
                },
              },
              "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
              "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
                "a_key": { # Metadata of the prediction output to be explained.
                  "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
                  "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
                  "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
                },
              },
            },
            "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
              "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
                "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
                  "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
                  "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
                    "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                      "A String",
                    ],
                  },
                },
                "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
                "neighborCount": 42, # The number of neighbors to return when querying for examples.
                "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
                  "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
                  "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
                },
              },
              "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
                "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
                  "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
                },
                "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
                  "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                    "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                      { # Noise sigma for a single feature.
                        "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                        "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                      },
                    ],
                  },
                  "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
                  "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
                },
                "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
              },
              "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
                "",
              ],
              "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
                "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
              },
              "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
              "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
                "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
                  "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
                },
                "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
                  "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                    "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                      { # Noise sigma for a single feature.
                        "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                        "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                      },
                    ],
                  },
                  "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
                  "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
                },
                "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
              },
            },
          },
          "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
          "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
          "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
          "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
            "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
            "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
            "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
            "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
          },
          "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
          "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
          "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
            "a_key": "A String",
          },
        },
      ],
      "description": "A String", # The description of the Endpoint.
      "displayName": "A String", # Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
      "enablePrivateServiceConnect": True or False, # Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
      "encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
        "kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
      },
      "etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
      "labels": { # The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
        "a_key": "A String",
      },
      "modelDeploymentMonitoringJob": "A String", # Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}`
      "name": "A String", # Output only. The resource name of the Endpoint.
      "network": "A String", # Optional. The full name of the Google Compute Engine [network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. [Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert): `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is network name.
      "predictRequestResponseLoggingConfig": { # Configuration for logging request-response to a BigQuery table. # Configures the request-response logging for online prediction.
        "bigqueryDestination": { # The BigQuery location for the output content. # BigQuery table for logging. If only given a project, a new dataset will be created with name `logging__` where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name `request_response_logging`
          "outputUri": "A String", # Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: `bq://projectId` or `bq://projectId.bqDatasetId` or `bq://projectId.bqDatasetId.bqTableId`.
        },
        "enabled": True or False, # If logging is enabled or not.
        "samplingRate": 3.14, # Percentage of requests to be logged, expressed as a fraction in range(0,1].
      },
      "privateServiceConnectConfig": { # Represents configuration for private service connect. # Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive.
        "enablePrivateServiceConnect": True or False, # Required. If true, expose the IndexEndpoint via private service connect.
        "projectAllowlist": [ # A list of Projects from which the forwarding rule will target the service attachment.
          "A String",
        ],
        "serviceAttachment": "A String", # Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect.
      },
      "satisfiesPzi": True or False, # Output only. Reserved for future use.
      "satisfiesPzs": True or False, # Output only. Reserved for future use.
      "trafficSplit": { # A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
        "a_key": 42,
      },
      "updateTime": "A String", # Output only. Timestamp when this Endpoint was last updated.
    },
  ],
  "nextPageToken": "A String", # A token to retrieve the next page of results. Pass to ListEndpointsRequest.page_token to obtain that page.
}

list_next()

Retrieves the next page of results.

        Args:
          previous_request: The request for the previous page. (required)
          previous_response: The response from the request for the previous page. (required)

        Returns:
          A request object that you can call 'execute()' on to request the next
          page. Returns None if there are no more items in the collection.
        

mutateDeployedModel(endpoint, body=None, x__xgafv=None)

Updates an existing deployed model. Updatable fields include `min_replica_count`, `max_replica_count`, `autoscaling_metric_specs`, `disable_container_logging` (v1 only), and `enable_container_logging` (v1beta1 only).

Args:
  endpoint: string, Required. The name of the Endpoint resource into which to mutate a DeployedModel. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for EndpointService.MutateDeployedModel.
  "deployedModel": { # A deployment of a Model. Endpoints contain one or more DeployedModels. # Required. The DeployedModel to be mutated within the Endpoint. Only the following fields can be mutated: * `min_replica_count` in either DedicatedResources or AutomaticResources * `max_replica_count` in either DedicatedResources or AutomaticResources * autoscaling_metric_specs * `disable_container_logging` (v1 only) * `enable_container_logging` (v1beta1 only)
    "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
      "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
      "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    },
    "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
    "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
      "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
        { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
          "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
          "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
        },
      ],
      "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
        "acceleratorCount": 42, # The number of accelerators to attach to the machine.
        "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
        "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
        "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
          "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
          "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
          "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
            "A String",
          ],
        },
        "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
      },
      "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
      "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
      "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
    },
    "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
    "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
    "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
      "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
        "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
        "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
          "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
            "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
            "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
              "",
            ],
            "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
            "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
            "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
              "maxValue": 3.14, # The maximum permissible value for this feature.
              "minValue": 3.14, # The minimum permissible value for this feature.
              "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
              "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
            },
            "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
            "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
              "A String",
            ],
            "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
            "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
              "",
            ],
            "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
            "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
            "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
              "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
              "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
              "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
              "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
              "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
              "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
            },
          },
        },
        "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
        "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
          "a_key": { # Metadata of the prediction output to be explained.
            "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
            "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
            "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
          },
        },
      },
      "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
        "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
          "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
            "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
            "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
              "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                "A String",
              ],
            },
          },
          "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
          "neighborCount": 42, # The number of neighbors to return when querying for examples.
          "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
            "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
            "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
          },
        },
        "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
          "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
            "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
          },
          "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
            "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
              "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                { # Noise sigma for a single feature.
                  "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                  "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                },
              ],
            },
            "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
            "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
          },
          "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
        },
        "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
          "",
        ],
        "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
          "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
        },
        "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
        "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
          "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
            "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
          },
          "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
            "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
              "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                { # Noise sigma for a single feature.
                  "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                  "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                },
              ],
            },
            "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
            "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
          },
          "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
        },
      },
    },
    "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
    "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
    "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
    "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
      "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
      "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
      "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
      "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
    },
    "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
    "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
    "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
      "a_key": "A String",
    },
  },
  "updateMask": "A String", # Required. The update mask applies to the resource. See google.protobuf.FieldMask.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

patch(name, body=None, updateMask=None, x__xgafv=None)

Updates an Endpoint.

Args:
  name: string, Output only. The resource name of the Endpoint. (required)
  body: object, The request body.
    The object takes the form of:

{ # Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
  "clientConnectionConfig": { # Configurations (e.g. inference timeout) that are applied on your endpoints. # Configurations that are applied to the endpoint for online prediction.
    "inferenceTimeout": "A String", # Customizable online prediction request timeout.
  },
  "createTime": "A String", # Output only. Timestamp when this Endpoint was created.
  "dedicatedEndpointDns": "A String", # Output only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: `https://{endpoint_id}.{region}-{project_number}.prediction.vertexai.goog`.
  "dedicatedEndpointEnabled": True or False, # If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
  "deployedModels": [ # Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    { # A deployment of a Model. Endpoints contain one or more DeployedModels.
      "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
        "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
      },
      "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
      "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
        "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
          { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
            "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
            "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
          },
        ],
        "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
          "acceleratorCount": 42, # The number of accelerators to attach to the machine.
          "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
          "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
          "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
            "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
            "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
            "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
              "A String",
            ],
          },
          "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
        },
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
        "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
        "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
      },
      "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
      "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
      "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
      "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
      "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
        "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
          "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
          "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
            "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
              "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
                "",
              ],
              "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
              "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
              "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
                "maxValue": 3.14, # The maximum permissible value for this feature.
                "minValue": 3.14, # The minimum permissible value for this feature.
                "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
                "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
              },
              "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
              "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
                "A String",
              ],
              "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
                "",
              ],
              "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
              "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
              "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
                "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
                "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
                "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
                "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
                "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
                "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
              },
            },
          },
          "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
          "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
            "a_key": { # Metadata of the prediction output to be explained.
              "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
              "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
              "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
            },
          },
        },
        "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
          "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
            "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
              "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
              "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
                "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                  "A String",
                ],
              },
            },
            "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
            "neighborCount": 42, # The number of neighbors to return when querying for examples.
            "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
              "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
              "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
            },
          },
          "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
          "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
            "",
          ],
          "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
            "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
          },
          "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
          "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
        },
      },
      "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
      "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
      "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
      "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
        "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
        "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
        "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
        "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
      },
      "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
      "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
      "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
        "a_key": "A String",
      },
    },
  ],
  "description": "A String", # The description of the Endpoint.
  "displayName": "A String", # Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  "enablePrivateServiceConnect": True or False, # Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
  "encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    "kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  "etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
  "labels": { # The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    "a_key": "A String",
  },
  "modelDeploymentMonitoringJob": "A String", # Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}`
  "name": "A String", # Output only. The resource name of the Endpoint.
  "network": "A String", # Optional. The full name of the Google Compute Engine [network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. [Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert): `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is network name.
  "predictRequestResponseLoggingConfig": { # Configuration for logging request-response to a BigQuery table. # Configures the request-response logging for online prediction.
    "bigqueryDestination": { # The BigQuery location for the output content. # BigQuery table for logging. If only given a project, a new dataset will be created with name `logging__` where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name `request_response_logging`
      "outputUri": "A String", # Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: `bq://projectId` or `bq://projectId.bqDatasetId` or `bq://projectId.bqDatasetId.bqTableId`.
    },
    "enabled": True or False, # If logging is enabled or not.
    "samplingRate": 3.14, # Percentage of requests to be logged, expressed as a fraction in range(0,1].
  },
  "privateServiceConnectConfig": { # Represents configuration for private service connect. # Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive.
    "enablePrivateServiceConnect": True or False, # Required. If true, expose the IndexEndpoint via private service connect.
    "projectAllowlist": [ # A list of Projects from which the forwarding rule will target the service attachment.
      "A String",
    ],
    "serviceAttachment": "A String", # Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect.
  },
  "satisfiesPzi": True or False, # Output only. Reserved for future use.
  "satisfiesPzs": True or False, # Output only. Reserved for future use.
  "trafficSplit": { # A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    "a_key": 42,
  },
  "updateTime": "A String", # Output only. Timestamp when this Endpoint was last updated.
}

  updateMask: string, Required. The update mask applies to the resource. See google.protobuf.FieldMask.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
  "clientConnectionConfig": { # Configurations (e.g. inference timeout) that are applied on your endpoints. # Configurations that are applied to the endpoint for online prediction.
    "inferenceTimeout": "A String", # Customizable online prediction request timeout.
  },
  "createTime": "A String", # Output only. Timestamp when this Endpoint was created.
  "dedicatedEndpointDns": "A String", # Output only. DNS of the dedicated endpoint. Will only be populated if dedicated_endpoint_enabled is true. Format: `https://{endpoint_id}.{region}-{project_number}.prediction.vertexai.goog`.
  "dedicatedEndpointEnabled": True or False, # If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
  "deployedModels": [ # Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    { # A deployment of a Model. Endpoints contain one or more DeployedModels.
      "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
        "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
      },
      "createTime": "A String", # Output only. Timestamp when the DeployedModel was created.
      "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
        "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`.
          { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
            "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization`
            "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
          },
        ],
        "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction.
          "acceleratorCount": 42, # The number of accelerators to attach to the machine.
          "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
          "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
          "reservationAffinity": { # A ReservationAffinity can be used to configure a Vertex AI resource (e.g., a DeployedModel) to draw its Compute Engine resources from a Shared Reservation, or exclusively from on-demand capacity. # Optional. Immutable. Configuration controlling how this resource pool consumes reservation.
            "key": "A String", # Optional. Corresponds to the label key of a reservation resource. To target a SPECIFIC_RESERVATION by name, use `compute.googleapis.com/reservation-name` as the key and specify the name of your reservation as its value.
            "reservationAffinityType": "A String", # Required. Specifies the reservation affinity type.
            "values": [ # Optional. Corresponds to the label values of a reservation resource. This must be the full resource name of the reservation.
              "A String",
            ],
          },
          "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
        },
        "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
        "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
        "spot": True or False, # Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
      },
      "disableContainerLogging": True or False, # For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send `stderr` and `stdout` streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to [Cloud Logging pricing](https://cloud.google.com/logging/pricing). User can disable container logging by setting this flag to true.
      "disableExplanations": True or False, # If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.
      "displayName": "A String", # The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
      "enableAccessLogging": True or False, # If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
      "explanationSpec": { # Specification of Model explanation. # Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
        "metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
          "featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
          "inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
            "a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
              "denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
                "",
              ],
              "encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
              "encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
              "featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
                "maxValue": 3.14, # The maximum permissible value for this feature.
                "minValue": 3.14, # The minimum permissible value for this feature.
                "originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
                "originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
              },
              "groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
              "indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
                "A String",
              ],
              "indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
              "inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
                "",
              ],
              "inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
              "modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
              "visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
                "clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
                "clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
                "colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
                "overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
                "polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
                "type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
              },
            },
          },
          "latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
          "outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
            "a_key": { # Metadata of the prediction output to be explained.
              "displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
              "indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
              "outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
            },
          },
        },
        "parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
          "examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
            "exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
              "dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
              "gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
                "uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
                  "A String",
                ],
              },
            },
            "nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
            "neighborCount": 42, # The number of neighbors to return when querying for examples.
            "presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
              "modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
              "query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
            },
          },
          "integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
          "outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
            "",
          ],
          "sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
            "pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
          },
          "topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
          "xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
            "blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
              "maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
            },
            "smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
              "featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
                "noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
                  { # Noise sigma for a single feature.
                    "name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
                    "sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
                  },
                ],
              },
              "noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
              "noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
            },
            "stepCount": 42, # Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range. Valid range of its value is [1, 100], inclusively.
          },
        },
      },
      "id": "A String", # Immutable. The ID of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this ID. This value should be 1-10 characters, and valid characters are `/[0-9]/`.
      "model": "A String", # Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` if no version is specified, the default version will be deployed.
      "modelVersionId": "A String", # Output only. The version ID of the model that is deployed.
      "privateEndpoints": { # PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predict_http_uri, explain_http_uri or health_http_uri. To send request via private service connect, use service_attachment. # Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
        "explainHttpUri": "A String", # Output only. Http(s) path to send explain requests.
        "healthHttpUri": "A String", # Output only. Http(s) path to send health check requests.
        "predictHttpUri": "A String", # Output only. Http(s) path to send prediction requests.
        "serviceAttachment": "A String", # Output only. The name of the service attachment resource. Populated if private service connect is enabled.
      },
      "serviceAccount": "A String", # The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the `iam.serviceAccounts.actAs` permission on this service account.
      "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`
      "systemLabels": { # System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.
        "a_key": "A String",
      },
    },
  ],
  "description": "A String", # The description of the Endpoint.
  "displayName": "A String", # Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
  "enablePrivateServiceConnect": True or False, # Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.
  "encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    "kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
  },
  "etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
  "labels": { # The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    "a_key": "A String",
  },
  "modelDeploymentMonitoringJob": "A String", # Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}`
  "name": "A String", # Output only. The resource name of the Endpoint.
  "network": "A String", # Optional. The full name of the Google Compute Engine [network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. [Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert): `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is network name.
  "predictRequestResponseLoggingConfig": { # Configuration for logging request-response to a BigQuery table. # Configures the request-response logging for online prediction.
    "bigqueryDestination": { # The BigQuery location for the output content. # BigQuery table for logging. If only given a project, a new dataset will be created with name `logging__` where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name `request_response_logging`
      "outputUri": "A String", # Required. BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: `bq://projectId` or `bq://projectId.bqDatasetId` or `bq://projectId.bqDatasetId.bqTableId`.
    },
    "enabled": True or False, # If logging is enabled or not.
    "samplingRate": 3.14, # Percentage of requests to be logged, expressed as a fraction in range(0,1].
  },
  "privateServiceConnectConfig": { # Represents configuration for private service connect. # Optional. Configuration for private service connect. network and private_service_connect_config are mutually exclusive.
    "enablePrivateServiceConnect": True or False, # Required. If true, expose the IndexEndpoint via private service connect.
    "projectAllowlist": [ # A list of Projects from which the forwarding rule will target the service attachment.
      "A String",
    ],
    "serviceAttachment": "A String", # Output only. The name of the generated service attachment resource. This is only populated if the endpoint is deployed with PrivateServiceConnect.
  },
  "satisfiesPzi": True or False, # Output only. Reserved for future use.
  "satisfiesPzs": True or False, # Output only. Reserved for future use.
  "trafficSplit": { # A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    "a_key": 42,
  },
  "updateTime": "A String", # Output only. Timestamp when this Endpoint was last updated.
}

predict(endpoint, body=None, x__xgafv=None)

Perform an online prediction.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.Predict.
  "instances": [ # Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
    "",
  ],
  "parameters": "", # The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.Predict.
  "deployedModelId": "A String", # ID of the Endpoint's DeployedModel that served this prediction.
  "metadata": "", # Output only. Request-level metadata returned by the model. The metadata type will be dependent upon the model implementation.
  "model": "A String", # Output only. The resource name of the Model which is deployed as the DeployedModel that this prediction hits.
  "modelDisplayName": "A String", # Output only. The display name of the Model which is deployed as the DeployedModel that this prediction hits.
  "modelVersionId": "A String", # Output only. The version ID of the Model which is deployed as the DeployedModel that this prediction hits.
  "predictions": [ # The predictions that are the output of the predictions call. The schema of any single prediction may be specified via Endpoint's DeployedModels' Model's PredictSchemata's prediction_schema_uri.
    "",
  ],
}

predictLongRunning(endpoint, body=None, x__xgafv=None)

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` or `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.PredictLongRunning.
  "instances": [ # Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the prediction call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
    "",
  ],
  "parameters": "", # Optional. The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

rawPredict(endpoint, body=None, x__xgafv=None)

Perform an online prediction with an arbitrary HTTP payload. The response includes the following HTTP headers: * `X-Vertex-AI-Endpoint-Id`: ID of the Endpoint that served this prediction. * `X-Vertex-AI-Deployed-Model-Id`: ID of the Endpoint's DeployedModel that served this prediction.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.RawPredict.
  "httpBody": { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged. # The prediction input. Supports HTTP headers and arbitrary data payload. A DeployedModel may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the RawPredict method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model. You can specify the schema for each instance in the predict_schemata.instance_schema_uri field when you create a Model. This schema applies when you deploy the `Model` as a `DeployedModel` to an Endpoint and use the `RawPredict` method.
    "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
    "data": "A String", # The HTTP request/response body as raw binary.
    "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
  "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
  "data": "A String", # The HTTP request/response body as raw binary.
  "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
    {
      "a_key": "", # Properties of the object. Contains field @type with type URL.
    },
  ],
}

serverStreamingPredict(endpoint, body=None, x__xgafv=None)

Perform a server-side streaming online prediction request for Vertex LLM streaming.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.StreamingPredict. The first message must contain endpoint field and optionally input. The subsequent messages must contain input.
  "inputs": [ # The prediction input.
    { # A tensor value type.
      "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
        True or False,
      ],
      "bytesVal": [ # STRING
        "A String",
      ],
      "doubleVal": [ # DOUBLE
        3.14,
      ],
      "dtype": "A String", # The data type of tensor.
      "floatVal": [ # FLOAT
        3.14,
      ],
      "int64Val": [ # INT64
        "A String",
      ],
      "intVal": [ # INT_8 INT_16 INT_32
        42,
      ],
      "listVal": [ # A list of tensor values.
        # Object with schema name: GoogleCloudAiplatformV1Tensor
      ],
      "shape": [ # Shape of the tensor.
        "A String",
      ],
      "stringVal": [ # STRING
        "A String",
      ],
      "structVal": { # A map of string to tensor.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
      },
      "tensorVal": "A String", # Serialized raw tensor content.
      "uint64Val": [ # UINT64
        "A String",
      ],
      "uintVal": [ # UINT8 UINT16 UINT32
        42,
      ],
    },
  ],
  "parameters": { # A tensor value type. # The parameters that govern the prediction.
    "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
      True or False,
    ],
    "bytesVal": [ # STRING
      "A String",
    ],
    "doubleVal": [ # DOUBLE
      3.14,
    ],
    "dtype": "A String", # The data type of tensor.
    "floatVal": [ # FLOAT
      3.14,
    ],
    "int64Val": [ # INT64
      "A String",
    ],
    "intVal": [ # INT_8 INT_16 INT_32
      42,
    ],
    "listVal": [ # A list of tensor values.
      # Object with schema name: GoogleCloudAiplatformV1Tensor
    ],
    "shape": [ # Shape of the tensor.
      "A String",
    ],
    "stringVal": [ # STRING
      "A String",
    ],
    "structVal": { # A map of string to tensor.
      "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
    },
    "tensorVal": "A String", # Serialized raw tensor content.
    "uint64Val": [ # UINT64
      "A String",
    ],
    "uintVal": [ # UINT8 UINT16 UINT32
      42,
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for PredictionService.StreamingPredict.
  "outputs": [ # The prediction output.
    { # A tensor value type.
      "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
        True or False,
      ],
      "bytesVal": [ # STRING
        "A String",
      ],
      "doubleVal": [ # DOUBLE
        3.14,
      ],
      "dtype": "A String", # The data type of tensor.
      "floatVal": [ # FLOAT
        3.14,
      ],
      "int64Val": [ # INT64
        "A String",
      ],
      "intVal": [ # INT_8 INT_16 INT_32
        42,
      ],
      "listVal": [ # A list of tensor values.
        # Object with schema name: GoogleCloudAiplatformV1Tensor
      ],
      "shape": [ # Shape of the tensor.
        "A String",
      ],
      "stringVal": [ # STRING
        "A String",
      ],
      "structVal": { # A map of string to tensor.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
      },
      "tensorVal": "A String", # Serialized raw tensor content.
      "uint64Val": [ # UINT64
        "A String",
      ],
      "uintVal": [ # UINT8 UINT16 UINT32
        42,
      ],
    },
  ],
  "parameters": { # A tensor value type. # The parameters that govern the prediction.
    "boolVal": [ # Type specific representations that make it easy to create tensor protos in all languages. Only the representation corresponding to "dtype" can be set. The values hold the flattened representation of the tensor in row major order. BOOL
      True or False,
    ],
    "bytesVal": [ # STRING
      "A String",
    ],
    "doubleVal": [ # DOUBLE
      3.14,
    ],
    "dtype": "A String", # The data type of tensor.
    "floatVal": [ # FLOAT
      3.14,
    ],
    "int64Val": [ # INT64
      "A String",
    ],
    "intVal": [ # INT_8 INT_16 INT_32
      42,
    ],
    "listVal": [ # A list of tensor values.
      # Object with schema name: GoogleCloudAiplatformV1Tensor
    ],
    "shape": [ # Shape of the tensor.
      "A String",
    ],
    "stringVal": [ # STRING
      "A String",
    ],
    "structVal": { # A map of string to tensor.
      "a_key": # Object with schema name: GoogleCloudAiplatformV1Tensor
    },
    "tensorVal": "A String", # Serialized raw tensor content.
    "uint64Val": [ # UINT64
      "A String",
    ],
    "uintVal": [ # UINT8 UINT16 UINT32
      42,
    ],
  },
}

streamGenerateContent(model, body=None, x__xgafv=None)

Generate content with multimodal inputs with streaming support.

Args:
  model: string, Required. The fully qualified name of the publisher model or tuned model endpoint to use. Publisher model format: `projects/{project}/locations/{location}/publishers/*/models/*` Tuned model endpoint format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for [PredictionService.GenerateContent].
  "contents": [ # Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
    { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
      "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
        { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
          "fileData": { # URI based data. # Optional. URI based data.
            "fileUri": "A String", # Required. URI.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
            "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
              "a_key": "", # Properties of the object.
            },
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
          },
          "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
            "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
            "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
              "a_key": "", # Properties of the object.
            },
          },
          "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
            "data": "A String", # Required. Raw bytes.
            "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
          },
          "text": "A String", # Optional. Text part (can be code).
          "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
            "endOffset": "A String", # Optional. The end offset of the video.
            "startOffset": "A String", # Optional. The start offset of the video.
          },
        },
      ],
      "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
    },
  ],
  "generationConfig": { # Generation config. # Optional. Generation config.
    "audioTimestamp": True or False, # Optional. If enabled, audio timestamp will be included in the request to the model.
    "candidateCount": 42, # Optional. Number of candidates to generate.
    "frequencyPenalty": 3.14, # Optional. Frequency penalties.
    "logprobs": 42, # Optional. Logit probabilities.
    "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message.
    "presencePenalty": 3.14, # Optional. Positive penalties.
    "responseLogprobs": True or False, # Optional. If true, export the logprobs results in response.
    "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: - `text/plain`: (default) Text output. - `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.
    "responseSchema": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. The `Schema` object allows the definition of input and output data types. These types can be objects, but also primitives and arrays. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). If set, a compatible response_mime_type must also be set. Compatible mimetypes: `application/json`: Schema for JSON response.
      "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
        # Object with schema name: GoogleCloudAiplatformV1Schema
      ],
      "default": "", # Optional. Default value of the data.
      "description": "A String", # Optional. The description of the data.
      "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
        "A String",
      ],
      "example": "", # Optional. Example of the object. Will only populated when the object is the root.
      "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
      "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
      "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
      "maxLength": "A String", # Optional. Maximum length of the Type.STRING
      "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
      "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
      "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
      "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
      "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
      "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
      "nullable": True or False, # Optional. Indicates if the value may be null.
      "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
      "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
        "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
      },
      "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
        "A String",
      ],
      "required": [ # Optional. Required properties of Type.OBJECT.
        "A String",
      ],
      "title": "A String", # Optional. The title of the Schema.
      "type": "A String", # Optional. The type of the data.
    },
    "routingConfig": { # The configuration for routing the request to a specific model. # Optional. Routing configuration.
      "autoMode": { # When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. # Automated routing.
        "modelRoutingPreference": "A String", # The model routing preference.
      },
      "manualMode": { # When manual routing is set, the specified model will be used directly. # Manual routing.
        "modelName": "A String", # The model name to use. Only the public LLM models are accepted. e.g. 'gemini-1.5-pro-001'.
      },
    },
    "seed": 42, # Optional. Seed.
    "stopSequences": [ # Optional. Stop sequences.
      "A String",
    ],
    "temperature": 3.14, # Optional. Controls the randomness of predictions.
    "topK": 3.14, # Optional. If specified, top-k sampling will be used.
    "topP": 3.14, # Optional. If specified, nucleus sampling will be used.
  },
  "labels": { # Optional. The labels with user-defined metadata for the request. It is used for billing and reporting only. Label keys and values can be no longer than 63 characters (Unicode codepoints) and can only contain lowercase letters, numeric characters, underscores, and dashes. International characters are allowed. Label values are optional. Label keys must start with a letter.
    "a_key": "A String",
  },
  "safetySettings": [ # Optional. Per request settings for blocking unsafe content. Enforced on GenerateContentResponse.candidates.
    { # Safety settings.
      "category": "A String", # Required. Harm category.
      "method": "A String", # Optional. Specify if the threshold is used for probability or severity score. If not specified, the threshold is used for probability score.
      "threshold": "A String", # Required. The harm block threshold.
    },
  ],
  "systemInstruction": { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. # Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
    "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
      { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
        "fileData": { # URI based data. # Optional. URI based data.
          "fileUri": "A String", # Required. URI.
          "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
        },
        "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
          "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
            "a_key": "", # Properties of the object.
          },
          "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
        },
        "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
          "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
          "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
            "a_key": "", # Properties of the object.
          },
        },
        "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
          "data": "A String", # Required. Raw bytes.
          "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
        },
        "text": "A String", # Optional. Text part (can be code).
        "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
          "endOffset": "A String", # Optional. The end offset of the video.
          "startOffset": "A String", # Optional. The start offset of the video.
        },
      },
    ],
    "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
  },
  "toolConfig": { # Tool config. This config is shared for all tools provided in the request. # Optional. Tool config. This config is shared for all tools provided in the request.
    "functionCallingConfig": { # Function calling config. # Optional. Function calling config.
      "allowedFunctionNames": [ # Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
        "A String",
      ],
      "mode": "A String", # Optional. Function calling mode.
    },
  },
  "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.
    { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).
      "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.
        { # Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client.
          "description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
          "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
          "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
            "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            "default": "", # Optional. Default value of the data.
            "description": "A String", # Optional. The description of the data.
            "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
              "A String",
            ],
            "example": "", # Optional. Example of the object. Will only populated when the object is the root.
            "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
            "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
            "maxLength": "A String", # Optional. Maximum length of the Type.STRING
            "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
            "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
            "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
            "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            "nullable": True or False, # Optional. Indicates if the value may be null.
            "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              "A String",
            ],
            "required": [ # Optional. Required properties of Type.OBJECT.
              "A String",
            ],
            "title": "A String", # Optional. The title of the Schema.
            "type": "A String", # Optional. The type of the data.
          },
          "response": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. # Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function.
            "anyOf": [ # Optional. The value should be validated against any (one or more) of the subschemas in the list.
              # Object with schema name: GoogleCloudAiplatformV1Schema
            ],
            "default": "", # Optional. Default value of the data.
            "description": "A String", # Optional. The description of the data.
            "enum": [ # Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
              "A String",
            ],
            "example": "", # Optional. Example of the object. Will only populated when the object is the root.
            "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
            "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY.
            "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY.
            "maxLength": "A String", # Optional. Maximum length of the Type.STRING
            "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT.
            "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER
            "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY.
            "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
            "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT.
            "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
            "nullable": True or False, # Optional. Indicates if the value may be null.
            "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
            "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.
              "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema
            },
            "propertyOrdering": [ # Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
              "A String",
            ],
            "required": [ # Optional. Required properties of Type.OBJECT.
              "A String",
            ],
            "title": "A String", # Optional. The title of the Schema.
            "type": "A String", # Optional. The type of the data.
          },
        },
      ],
      "googleSearchRetrieval": { # Tool to retrieve public web data for grounding, powered by Google. # Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.
        "dynamicRetrievalConfig": { # Describes the options to customize dynamic retrieval. # Specifies the dynamic retrieval configuration for the given source.
          "dynamicThreshold": 3.14, # Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
          "mode": "A String", # The mode of the predictor to be used in dynamic retrieval.
        },
      },
      "retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.
        "disableAttribution": True or False, # Optional. Deprecated. This option is no longer supported.
        "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/products/agent-builder # Set to use data source powered by Vertex AI Search.
          "datastore": "A String", # Required. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
        },
        "vertexRagStore": { # Retrieve from Vertex RAG Store for grounding. # Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
          "ragCorpora": [ # Optional. Deprecated. Please use rag_resources instead.
            "A String",
          ],
          "ragResources": [ # Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
            { # The definition of the Rag resource.
              "ragCorpus": "A String", # Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
              "ragFileIds": [ # Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
                "A String",
              ],
            },
          ],
          "similarityTopK": 42, # Optional. Number of top k results to return from the selected corpora.
          "vectorDistanceThreshold": 3.14, # Optional. Only return results with vector distance smaller than the threshold.
        },
      },
    },
  ],
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for [PredictionService.GenerateContent].
  "candidates": [ # Output only. Generated candidates.
    { # A response candidate generated from the model.
      "avgLogprobs": 3.14, # Output only. Average log probability score of the candidate.
      "citationMetadata": { # A collection of source attributions for a piece of content. # Output only. Source attribution of the generated content.
        "citations": [ # Output only. List of citations.
          { # Source attributions for content.
            "endIndex": 42, # Output only. End index into the content.
            "license": "A String", # Output only. License of the attribution.
            "publicationDate": { # Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp # Output only. Publication date of the attribution.
              "day": 42, # Day of a month. Must be from 1 to 31 and valid for the year and month, or 0 to specify a year by itself or a year and month where the day isn't significant.
              "month": 42, # Month of a year. Must be from 1 to 12, or 0 to specify a year without a month and day.
              "year": 42, # Year of the date. Must be from 1 to 9999, or 0 to specify a date without a year.
            },
            "startIndex": 42, # Output only. Start index into the content.
            "title": "A String", # Output only. Title of the attribution.
            "uri": "A String", # Output only. Url reference of the attribution.
          },
        ],
      },
      "content": { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn. # Output only. Content parts of the candidate.
        "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
          { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
            "fileData": { # URI based data. # Optional. URI based data.
              "fileUri": "A String", # Required. URI.
              "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
            },
            "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
              "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
                "a_key": "", # Properties of the object.
              },
              "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
            },
            "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
              "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
              "response": { # Required. The function response in JSON object format. Use "output" key to specify function output and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as function output.
                "a_key": "", # Properties of the object.
              },
            },
            "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
              "data": "A String", # Required. Raw bytes.
              "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
            },
            "text": "A String", # Optional. Text part (can be code).
            "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
              "endOffset": "A String", # Optional. The end offset of the video.
              "startOffset": "A String", # Optional. The start offset of the video.
            },
          },
        ],
        "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
      },
      "finishMessage": "A String", # Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when `finish_reason` is set.
      "finishReason": "A String", # Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
      "groundingMetadata": { # Metadata returned to client when grounding is enabled. # Output only. Metadata specifies sources used to ground generated content.
        "groundingChunks": [ # List of supporting references retrieved from specified grounding source.
          { # Grounding chunk.
            "retrievedContext": { # Chunk from context retrieved by the retrieval tools. # Grounding chunk from context retrieved by the retrieval tools.
              "text": "A String", # Text of the attribution.
              "title": "A String", # Title of the attribution.
              "uri": "A String", # URI reference of the attribution.
            },
            "web": { # Chunk from the web. # Grounding chunk from the web.
              "title": "A String", # Title of the chunk.
              "uri": "A String", # URI reference of the chunk.
            },
          },
        ],
        "groundingSupports": [ # Optional. List of grounding support.
          { # Grounding support.
            "confidenceScores": [ # Confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the grounding_chunk_indices.
              3.14,
            ],
            "groundingChunkIndices": [ # A list of indices (into 'grounding_chunk') specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved content attributed to the claim.
              42,
            ],
            "segment": { # Segment of the content. # Segment of the content this support belongs to.
              "endIndex": 42, # Output only. End index in the given Part, measured in bytes. Offset from the start of the Part, exclusive, starting at zero.
              "partIndex": 42, # Output only. The index of a Part object within its parent Content object.
              "startIndex": 42, # Output only. Start index in the given Part, measured in bytes. Offset from the start of the Part, inclusive, starting at zero.
              "text": "A String", # Output only. The text corresponding to the segment from the response.
            },
          },
        ],
        "retrievalMetadata": { # Metadata related to retrieval in the grounding flow. # Optional. Output only. Retrieval metadata.
          "googleSearchDynamicRetrievalScore": 3.14, # Optional. Score indicating how likely information from Google Search could help answer the prompt. The score is in the range `[0, 1]`, where 0 is the least likely and 1 is the most likely. This score is only populated when Google Search grounding and dynamic retrieval is enabled. It will be compared to the threshold to determine whether to trigger Google Search.
        },
        "searchEntryPoint": { # Google search entry point. # Optional. Google search entry for the following-up web searches.
          "renderedContent": "A String", # Optional. Web content snippet that can be embedded in a web page or an app webview.
          "sdkBlob": "A String", # Optional. Base64 encoded JSON representing array of tuple.
        },
        "webSearchQueries": [ # Optional. Web search queries for the following-up web search.
          "A String",
        ],
      },
      "index": 42, # Output only. Index of the candidate.
      "logprobsResult": { # Logprobs Result # Output only. Log-likelihood scores for the response tokens and top tokens
        "chosenCandidates": [ # Length = total number of decoding steps. The chosen candidates may or may not be in top_candidates.
          { # Candidate for the logprobs token and score.
            "logProbability": 3.14, # The candidate's log probability.
            "token": "A String", # The candidate's token string value.
            "tokenId": 42, # The candidate's token id value.
          },
        ],
        "topCandidates": [ # Length = total number of decoding steps.
          { # Candidates with top log probabilities at each decoding step.
            "candidates": [ # Sorted by log probability in descending order.
              { # Candidate for the logprobs token and score.
                "logProbability": 3.14, # The candidate's log probability.
                "token": "A String", # The candidate's token string value.
                "tokenId": 42, # The candidate's token id value.
              },
            ],
          },
        ],
      },
      "safetyRatings": [ # Output only. List of ratings for the safety of a response candidate. There is at most one rating per category.
        { # Safety rating corresponding to the generated content.
          "blocked": True or False, # Output only. Indicates whether the content was filtered out because of this rating.
          "category": "A String", # Output only. Harm category.
          "probability": "A String", # Output only. Harm probability levels in the content.
          "probabilityScore": 3.14, # Output only. Harm probability score.
          "severity": "A String", # Output only. Harm severity levels in the content.
          "severityScore": 3.14, # Output only. Harm severity score.
        },
      ],
    },
  ],
  "modelVersion": "A String", # Output only. The model version used to generate the response.
  "promptFeedback": { # Content filter results for a prompt sent in the request. # Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.
    "blockReason": "A String", # Output only. Blocked reason.
    "blockReasonMessage": "A String", # Output only. A readable block reason message.
    "safetyRatings": [ # Output only. Safety ratings.
      { # Safety rating corresponding to the generated content.
        "blocked": True or False, # Output only. Indicates whether the content was filtered out because of this rating.
        "category": "A String", # Output only. Harm category.
        "probability": "A String", # Output only. Harm probability levels in the content.
        "probabilityScore": 3.14, # Output only. Harm probability score.
        "severity": "A String", # Output only. Harm severity levels in the content.
        "severityScore": 3.14, # Output only. Harm severity score.
      },
    ],
  },
  "usageMetadata": { # Usage metadata about response(s). # Usage metadata about the response(s).
    "candidatesTokenCount": 42, # Number of tokens in the response(s).
    "promptTokenCount": 42, # Number of tokens in the request. When `cached_content` is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
    "totalTokenCount": 42, # Total token count for prompt and response candidates.
  },
}

streamRawPredict(endpoint, body=None, x__xgafv=None)

Perform a streaming online prediction with an arbitrary HTTP payload.

Args:
  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for PredictionService.StreamRawPredict.
  "httpBody": { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged. # The prediction input. Supports HTTP headers and arbitrary data payload.
    "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
    "data": "A String", # The HTTP request/response body as raw binary.
    "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
  "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
  "data": "A String", # The HTTP request/response body as raw binary.
  "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
    {
      "a_key": "", # Properties of the object. Contains field @type with type URL.
    },
  ],
}

undeployModel(endpoint, body=None, x__xgafv=None)

Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.

Args:
  endpoint: string, Required. The name of the Endpoint resource from which to undeploy a Model. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` (required)
  body: object, The request body.
    The object takes the form of:

{ # Request message for EndpointService.UndeployModel.
  "deployedModelId": "A String", # Required. The ID of the DeployedModel to be undeployed from the Endpoint.
  "trafficSplit": { # If this field is provided, then the Endpoint's traffic_split will be overwritten with it. If last DeployedModel is being undeployed from the Endpoint, the [Endpoint.traffic_split] will always end up empty when this call returns. A DeployedModel will be successfully undeployed only if it doesn't have any traffic assigned to it when this method executes, or if this field unassigns any traffic to it.
    "a_key": 42,
  },
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}