Close httplib2 connections.
searchKnowledge(conversation, body=None, x__xgafv=None)
Get answers for the given query based on knowledge documents.
suggestConversationSummary(conversation, body=None, x__xgafv=None)
Suggests summary for a conversation based on specific historical messages. The range of the messages to be used for summary can be specified in the request.
close()
Close httplib2 connections.
searchKnowledge(conversation, body=None, x__xgafv=None)
Get answers for the given query based on knowledge documents.
Args:
conversation: string, Optional. The conversation (between human agent and end user) where the search request is triggered. Format: `projects//locations//conversations/`. (required)
body: object, The request body.
The object takes the form of:
{ # The request message for Conversations.SearchKnowledge.
"conversation": "A String", # Optional. The conversation (between human agent and end user) where the search request is triggered. Format: `projects//locations//conversations/`.
"conversationProfile": "A String", # Required. The conversation profile used to configure the search. Format: `projects//locations//conversationProfiles/`.
"endUserMetadata": { # Optional. Information about the end-user to improve the relevance and accuracy of generative answers. This will be interpreted and used by a language model, so, for good results, the data should be self-descriptive, and in a simple structure. Example: ```json { "subscription plan": "Business Premium Plus", "devices owned": [ {"model": "Google Pixel 7"}, {"model": "Google Pixel Tablet"} ] } ```
"a_key": "", # Properties of the object.
},
"exactSearch": True or False, # Optional. Whether to search the query exactly without query rewrite.
"latestMessage": "A String", # Optional. The name of the latest conversation message when the request is triggered. Format: `projects//locations//conversations//messages/`.
"parent": "A String", # Required. The parent resource contains the conversation profile Format: 'projects/' or `projects//locations/`.
"query": { # Auxiliary proto messages. Represents the natural language text to be processed. # Required. The natural language text query for knowledge search.
"languageCode": "A String", # Required. The language of this conversational query. See [Language Support](https://cloud.google.com/dialogflow/docs/reference/language) for a list of the currently supported language codes. Note that queries in the same session do not necessarily need to specify the same language.
"text": "A String", # Required. The UTF-8 encoded natural language text to be processed. Text length must not exceed 256 characters for virtual agent interactions.
},
"querySource": "A String", # Optional. The source of the query in the request.
"searchConfig": { # Configuration specific to search queries with data stores. # Optional. Configuration specific to search queries with data stores.
"boostSpecs": [ # Optional. Boost specifications for data stores.
{ # Boost specifications for data stores.
"dataStores": [ # Optional. Data Stores where the boosting configuration is applied. The full names of the referenced data stores. Formats: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}` `projects/{project}/locations/{location}/dataStores/{data_store}
"A String",
],
"spec": [ # Optional. A list of boosting specifications.
{ # Boost specification to boost certain documents. A copy of google.cloud.discoveryengine.v1main.BoostSpec, field documentation is available at https://cloud.google.com/generative-ai-app-builder/docs/reference/rest/v1alpha/BoostSpec
"conditionBoostSpecs": [ # Optional. Condition boost specifications. If a document matches multiple conditions in the specifictions, boost scores from these specifications are all applied and combined in a non-linear way. Maximum number of specifications is 20.
{ # Boost applies to documents which match a condition.
"boost": 3.14, # Optional. Strength of the condition boost, which should be in [-1, 1]. Negative boost means demotion. Default is 0.0. Setting to 1.0 gives the document a big promotion. However, it does not necessarily mean that the boosted document will be the top result at all times, nor that other documents will be excluded. Results could still be shown even when none of them matches the condition. And results that are significantly more relevant to the search query can still trump your heavily favored but irrelevant documents. Setting to -1.0 gives the document a big demotion. However, results that are deeply relevant might still be shown. The document will have an upstream battle to get a fairly high ranking, but it is not blocked out completely. Setting to 0.0 means no boost applied. The boosting condition is ignored.
"boostControlSpec": { # Specification for custom ranking based on customer specified attribute value. It provides more controls for customized ranking than the simple (condition, boost) combination above. # Optional. Complex specification for custom ranking based on customer defined attribute value.
"attributeType": "A String", # Optional. The attribute type to be used to determine the boost amount. The attribute value can be derived from the field value of the specified field_name. In the case of numerical it is straightforward i.e. attribute_value = numerical_field_value. In the case of freshness however, attribute_value = (time.now() - datetime_field_value).
"controlPoints": [ # Optional. The control points used to define the curve. The monotonic function (defined through the interpolation_type above) passes through the control points listed here.
{ # The control points used to define the curve. The curve defined through these control points can only be monotonically increasing or decreasing(constant values are acceptable).
"attributeValue": "A String", # Optional. Can be one of: 1. The numerical field value. 2. The duration spec for freshness: The value must be formatted as an XSD `dayTimeDuration` value (a restricted subset of an ISO 8601 duration value). The pattern for this is: `nDnM]`.
"boostAmount": 3.14, # Optional. The value between -1 to 1 by which to boost the score if the attribute_value evaluates to the value specified above.
},
],
"fieldName": "A String", # Optional. The name of the field whose value will be used to determine the boost amount.
"interpolationType": "A String", # Optional. The interpolation type to be applied to connect the control points listed below.
},
"condition": "A String", # Optional. An expression which specifies a boost condition. The syntax and supported fields are the same as a filter expression. Examples: * To boost documents with document ID "doc_1" or "doc_2", and color "Red" or "Blue": * (id: ANY("doc_1", "doc_2")) AND (color: ANY("Red","Blue"))
},
],
},
],
},
],
"filterSpecs": [ # Optional. Filter specification for data store queries.
{ # Filter specification for data store queries.
"dataStores": [ # Optional. The data store where the filter configuration is applied. Full resource name of data store, such as projects/{project}/locations/{location}/collections/{collectionId}/ dataStores/{dataStoreId}.
"A String",
],
"filter": "A String", # Optional. The filter expression to be applied. Expression syntax is documented at https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata#filter-expression-syntax
},
],
},
"sessionId": "A String", # Required. The ID of the search session. The session_id can be combined with Dialogflow V3 Agent ID retrieved from conversation profile or on its own to identify a search session. The search history of the same session will impact the search result. It's up to the API caller to choose an appropriate `Session ID`. It can be a random number or some type of session identifiers (preferably hashed). The length must not exceed 36 characters.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # The response message for Conversations.SearchKnowledge.
"answers": [ # Most relevant snippets extracted from articles in the given knowledge base, ordered by confidence.
{ # Represents a SearchKnowledge answer.
"answer": "A String", # The piece of text from the knowledge base documents that answers the search query
"answerRecord": "A String", # The name of the answer record. Format: `projects//locations//answer Records/`
"answerSources": [ # All sources used to generate the answer.
{ # The sources of the answers.
"metadata": { # Metadata associated with the article.
"a_key": "", # Properties of the object.
},
"snippet": "A String", # The relevant snippet of the article.
"title": "A String", # The title of the article.
"uri": "A String", # The URI of the article.
},
],
"answerType": "A String", # The type of the answer.
},
],
"rewrittenQuery": "A String", # The rewritten query used to search knowledge.
}
suggestConversationSummary(conversation, body=None, x__xgafv=None)
Suggests summary for a conversation based on specific historical messages. The range of the messages to be used for summary can be specified in the request.
Args:
conversation: string, Required. The conversation to fetch suggestion for. Format: `projects//locations//conversations/`. (required)
body: object, The request body.
The object takes the form of:
{ # The request message for Conversations.SuggestConversationSummary.
"assistQueryParams": { # Represents the parameters of human assist query. # Optional. Parameters for a human assist query. Only used for POC/demo purpose.
"documentsMetadataFilters": { # Key-value filters on the metadata of documents returned by article suggestion. If specified, article suggestion only returns suggested documents that match all filters in their Document.metadata. Multiple values for a metadata key should be concatenated by comma. For example, filters to match all documents that have 'US' or 'CA' in their market metadata values and 'agent' in their user metadata values will be ``` documents_metadata_filters { key: "market" value: "US,CA" } documents_metadata_filters { key: "user" value: "agent" } ```
"a_key": "A String",
},
},
"contextSize": 42, # Optional. Max number of messages prior to and including [latest_message] to use as context when compiling the suggestion. By default 500 and at most 1000.
"latestMessage": "A String", # Optional. The name of the latest conversation message used as context for compiling suggestion. If empty, the latest message of the conversation will be used. Format: `projects//locations//conversations//messages/`.
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # The response message for Conversations.SuggestConversationSummary.
"contextSize": 42, # Number of messages prior to and including last_conversation_message used to compile the suggestion. It may be smaller than the SuggestSummaryRequest.context_size field in the request if there weren't that many messages in the conversation.
"latestMessage": "A String", # The name of the latest conversation message used as context for compiling suggestion. Format: `projects//locations//conversations//messages/`.
"summary": { # Generated summary for a conversation. # Generated summary.
"answerRecord": "A String", # The name of the answer record. Format: "projects//answerRecords/"
"baselineModelVersion": "A String", # The baseline model version used to generate this summary. It is empty if a baseline model was not used to generate this summary.
"text": "A String", # The summary content that is concatenated into one string.
"textSections": { # The summary content that is divided into sections. The key is the section's name and the value is the section's content. There is no specific format for the key or value.
"a_key": "A String",
},
},
}