answer(servingConfig, body=None, x__xgafv=None)
Answer query method.
Close httplib2 connections.
recommend(servingConfig, body=None, x__xgafv=None)
Makes a recommendation, which requires a contextual user event.
search(servingConfig, body=None, x__xgafv=None)
Performs a search.
searchLite(servingConfig, body=None, x__xgafv=None)
Performs a search. Similar to the SearchService.Search method, but a lite version that allows API key for authentication, where OAuth and IAM checks are not required. Only public website search is supported by this method. If data stores and engines not associated with public website search are specified, a `FAILED_PRECONDITION` error is returned. This method can be used for easy onboarding without having to implement an authentication backend. However, it is strongly recommended to use SearchService.Search instead with required OAuth and IAM checks to provide better data security.
Retrieves the next page of results.
Retrieves the next page of results.
answer(servingConfig, body=None, x__xgafv=None)
Answer query method.
Args:
servingConfig: string, Required. The resource name of the Search serving config, such as `projects/*/locations/global/collections/default_collection/engines/*/servingConfigs/default_serving_config`, or `projects/*/locations/global/collections/default_collection/dataStores/*/servingConfigs/default_serving_config`. This field is used to identify the serving configuration name, set of models used to make the search. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ConversationalSearchService.AnswerQuery method.
"answerGenerationSpec": { # Answer generation specification. # Answer generation specification.
"answerLanguageCode": "A String", # Language code for Answer. Use language tags defined by [BCP47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt). Note: This is an experimental feature.
"ignoreAdversarialQuery": True or False, # Specifies whether to filter out adversarial queries. The default value is `false`. Google employs search-query classification to detect adversarial queries. No answer is returned if the search query is classified as an adversarial query. For example, a user might ask a question regarding negative comments about the company or submit a query designed to generate unsafe, policy-violating output. If this field is set to `true`, we skip generating answers for adversarial queries and return fallback messages instead.
"ignoreJailBreakingQuery": True or False, # Optional. Specifies whether to filter out jail-breaking queries. The default value is `false`. Google employs search-query classification to detect jail-breaking queries. No summary is returned if the search query is classified as a jail-breaking query. A user might add instructions to the query to change the tone, style, language, content of the answer, or ask the model to act as a different entity, e.g. "Reply in the tone of a competing company's CEO". If this field is set to `true`, we skip generating summaries for jail-breaking queries and return fallback messages instead.
"ignoreLowRelevantContent": True or False, # Specifies whether to filter out queries that have low relevance. If this field is set to `false`, all search results are used regardless of relevance to generate answers. If set to `true` or unset, the behavior will be determined automatically by the service.
"ignoreNonAnswerSeekingQuery": True or False, # Specifies whether to filter out queries that are not answer-seeking. The default value is `false`. Google employs search-query classification to detect answer-seeking queries. No answer is returned if the search query is classified as a non-answer seeking query. If this field is set to `true`, we skip generating answers for non-answer seeking queries and return fallback messages instead.
"includeCitations": True or False, # Specifies whether to include citation metadata in the answer. The default value is `false`.
"modelSpec": { # Answer Generation Model specification. # Answer generation model specification.
"modelVersion": "A String", # Model version. If not set, it will use the default stable model. Allowed values are: stable, preview.
},
"promptSpec": { # Answer generation prompt specification. # Answer generation prompt specification.
"preamble": "A String", # Customized preamble.
},
},
"asynchronousMode": True or False, # Deprecated: This field is deprecated. Streaming Answer API will be supported. Asynchronous mode control. If enabled, the response will be returned with answer/session resource name without final answer. The API users need to do the polling to get the latest status of answer/session by calling ConversationalSearchService.GetAnswer or ConversationalSearchService.GetSession method.
"groundingSpec": { # Grounding specification. # Optional. Grounding specification.
"includeGroundingSupports": True or False, # Optional. Specifies whether to include grounding_supports in the answer. The default value is `false`. When this field is set to `true`, returned answer will have `grounding_score` and will contain GroundingSupports for each claim.
},
"query": { # Defines a user inputed query. # Required. Current user query.
"queryId": "A String", # Unique Id for the query.
"text": "A String", # Plain text.
},
"queryUnderstandingSpec": { # Query understanding specification. # Query understanding specification.
"queryClassificationSpec": { # Query classification specification. # Query classification specification.
"types": [ # Enabled query classification types.
"A String",
],
},
"queryRephraserSpec": { # Query rephraser specification. # Query rephraser specification.
"disable": True or False, # Disable query rephraser.
"maxRephraseSteps": 42, # Max rephrase steps. The max number is 5 steps. If not set or set to < 1, it will be set to 1 by default.
},
},
"relatedQuestionsSpec": { # Related questions specification. # Related questions specification.
"enable": True or False, # Enable related questions feature if true.
},
"safetySpec": { # Safety specification. # Model specification.
"enable": True or False, # Enable the safety filtering on the answer response. It is false by default.
},
"searchSpec": { # Search specification. # Search specification.
"searchParams": { # Search parameters. # Search parameters.
"boostSpec": { # Boost specification to boost certain documents. # Boost specification to boost certain documents in search results which may affect the answer query response. For more information on boosting, see [Boosting](https://cloud.google.com/retail/docs/boosting#boost)
"conditionBoostSpecs": [ # 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, # 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. Only one of the (condition, boost) combination or the boost_control_spec below are set. If both are set then the global boost is ignored and the more fine-grained boost_control_spec is applied.
"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. # Complex specification for custom ranking based on customer defined attribute value.
"attributeType": "A String", # 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": [ # 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", # 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, # 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", # The name of the field whose value will be used to determine the boost amount.
"interpolationType": "A String", # The interpolation type to be applied to connect the control points listed below.
},
"condition": "A String", # An expression which specifies a boost condition. The syntax and supported fields are the same as a filter expression. See SearchRequest.filter for detail syntax and limitations. Examples: * To boost documents with document ID "doc_1" or "doc_2", and color "Red" or "Blue": `(document_id: ANY("doc_1", "doc_2")) AND (color: ANY("Red", "Blue"))`
},
],
},
"dataStoreSpecs": [ # Specs defining dataStores to filter on in a search call and configurations for those dataStores. This is only considered for engines with multiple dataStores use case. For single dataStore within an engine, they should use the specs at the top level.
{ # A struct to define data stores to filter on in a search call and configurations for those data stores. Otherwise, an `INVALID_ARGUMENT` error is returned.
"dataStore": "A String", # Required. Full resource name of DataStore, such as `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`.
"filter": "A String", # Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
},
],
"filter": "A String", # The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive. This will be used to filter search results which may affect the Answer response. If this field is unrecognizable, an `INVALID_ARGUMENT` is returned. Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customers might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")' For more information about filtering including syntax and filter operators, see [Filter](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
"maxReturnResults": 42, # Number of search results to return. The default value is 10.
"orderBy": "A String", # The order in which documents are returned. Documents can be ordered by a field in an Document object. Leave it unset if ordered by relevance. `order_by` expression is case-sensitive. For more information on ordering, see [Ordering](https://cloud.google.com/retail/docs/filter-and-order#order) If this field is unrecognizable, an `INVALID_ARGUMENT` is returned.
"searchResultMode": "A String", # Specifies the search result mode. If unspecified, the search result mode defaults to `DOCUMENTS`. See [parse and chunk documents](https://cloud.google.com/generative-ai-app-builder/docs/parse-chunk-documents)
},
"searchResultList": { # Search result list. # Search result list.
"searchResults": [ # Search results.
{ # Search result.
"chunkInfo": { # Chunk information. # Chunk information.
"chunk": "A String", # Chunk resource name.
"content": "A String", # Chunk textual content.
"documentMetadata": { # Document metadata contains the information of the document of the current chunk. # Metadata of the document from the current chunk.
"title": "A String", # Title of the document.
"uri": "A String", # Uri of the document.
},
},
"unstructuredDocumentInfo": { # Unstructured document information. # Unstructured document information.
"document": "A String", # Document resource name.
"documentContexts": [ # List of document contexts. The content will be used for Answer Generation. This is supposed to be the main content of the document that can be long and comprehensive.
{ # Document context.
"content": "A String", # Document content to be used for answer generation.
"pageIdentifier": "A String", # Page identifier.
},
],
"extractiveAnswers": [ # Deprecated: This field is deprecated and will have no effect on the Answer generation. Please use document_contexts and extractive_segments fields. List of extractive answers.
{ # Extractive answer. [Guide](https://cloud.google.com/generative-ai-app-builder/docs/snippets#get-answers)
"content": "A String", # Extractive answer content.
"pageIdentifier": "A String", # Page identifier.
},
],
"extractiveSegments": [ # List of extractive segments.
{ # Extractive segment. [Guide](https://cloud.google.com/generative-ai-app-builder/docs/snippets#extractive-segments) Answer generation will only use it if document_contexts is empty. This is supposed to be shorter snippets.
"content": "A String", # Extractive segment content.
"pageIdentifier": "A String", # Page identifier.
},
],
"title": "A String", # Title.
"uri": "A String", # URI for the document.
},
},
],
},
},
"session": "A String", # The session resource name. Not required. When session field is not set, the API is in sessionless mode. We support auto session mode: users can use the wildcard symbol `-` as session ID. A new ID will be automatically generated and assigned.
"userLabels": { # The user labels applied to a resource must meet the following requirements: * Each resource can have multiple labels, up to a maximum of 64. * Each label must be a key-value pair. * Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters. * Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed. * The key portion of a label must be unique. However, you can use the same key with multiple resources. * Keys must start with a lowercase letter or international character. See [Google Cloud Document](https://cloud.google.com/resource-manager/docs/creating-managing-labels#requirements) for more details.
"a_key": "A String",
},
"userPseudoId": "A String", # A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website. This field should NOT have a fixed value such as `unknown_visitor`. The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
}
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 ConversationalSearchService.AnswerQuery method.
"answer": { # Defines an answer. # Answer resource object. If AnswerQueryRequest.QueryUnderstandingSpec.QueryRephraserSpec.max_rephrase_steps is greater than 1, use Answer.name to fetch answer information using ConversationalSearchService.GetAnswer API.
"answerSkippedReasons": [ # Additional answer-skipped reasons. This provides the reason for ignored cases. If nothing is skipped, this field is not set.
"A String",
],
"answerText": "A String", # The textual answer.
"citations": [ # Citations.
{ # Citation info for a segment.
"endIndex": "A String", # End of the attributed segment, exclusive.
"sources": [ # Citation sources for the attributed segment.
{ # Citation source.
"referenceId": "A String", # ID of the citation source.
},
],
"startIndex": "A String", # Index indicates the start of the segment, measured in bytes (UTF-8 unicode).
},
],
"completeTime": "A String", # Output only. Answer completed timestamp.
"createTime": "A String", # Output only. Answer creation timestamp.
"name": "A String", # Immutable. Fully qualified name `projects/{project}/locations/global/collections/{collection}/engines/{engine}/sessions/*/answers/*`
"queryUnderstandingInfo": { # Query understanding information. # Query understanding information.
"queryClassificationInfo": [ # Query classification information.
{ # Query classification information.
"positive": True or False, # Classification output.
"type": "A String", # Query classification type.
},
],
},
"references": [ # References.
{ # Reference.
"chunkInfo": { # Chunk information. # Chunk information.
"chunk": "A String", # Chunk resource name.
"content": "A String", # Chunk textual content.
"documentMetadata": { # Document metadata. # Document metadata.
"document": "A String", # Document resource name.
"pageIdentifier": "A String", # Page identifier.
"structData": { # The structured JSON metadata for the document. It is populated from the struct data from the Chunk in search result.
"a_key": "", # Properties of the object.
},
"title": "A String", # Title.
"uri": "A String", # URI for the document.
},
"relevanceScore": 3.14, # The relevance of the chunk for a given query. Values range from 0.0 (completely irrelevant) to 1.0 (completely relevant). This value is for informational purpose only. It may change for the same query and chunk at any time due to a model retraining or change in implementation.
},
"structuredDocumentInfo": { # Structured search information. # Structured document information.
"document": "A String", # Document resource name.
"structData": { # Structured search data.
"a_key": "", # Properties of the object.
},
},
"unstructuredDocumentInfo": { # Unstructured document information. # Unstructured document information.
"chunkContents": [ # List of cited chunk contents derived from document content.
{ # Chunk content.
"content": "A String", # Chunk textual content.
"pageIdentifier": "A String", # Page identifier.
"relevanceScore": 3.14, # The relevance of the chunk for a given query. Values range from 0.0 (completely irrelevant) to 1.0 (completely relevant). This value is for informational purpose only. It may change for the same query and chunk at any time due to a model retraining or change in implementation.
},
],
"document": "A String", # Document resource name.
"structData": { # The structured JSON metadata for the document. It is populated from the struct data from the Chunk in search result.
"a_key": "", # Properties of the object.
},
"title": "A String", # Title.
"uri": "A String", # URI for the document.
},
},
],
"relatedQuestions": [ # Suggested related questions.
"A String",
],
"state": "A String", # The state of the answer generation.
"steps": [ # Answer generation steps.
{ # Step information.
"actions": [ # Actions.
{ # Action.
"observation": { # Observation. # Observation.
"searchResults": [ # Search results observed by the search action, it can be snippets info or chunk info, depending on the citation type set by the user.
{
"chunkInfo": [ # If citation_type is CHUNK_LEVEL_CITATION and chunk mode is on, populate chunk info.
{ # Chunk information.
"chunk": "A String", # Chunk resource name.
"content": "A String", # Chunk textual content.
"relevanceScore": 3.14, # The relevance of the chunk for a given query. Values range from 0.0 (completely irrelevant) to 1.0 (completely relevant). This value is for informational purpose only. It may change for the same query and chunk at any time due to a model retraining or change in implementation.
},
],
"document": "A String", # Document resource name.
"snippetInfo": [ # If citation_type is DOCUMENT_LEVEL_CITATION, populate document level snippets.
{ # Snippet information.
"snippet": "A String", # Snippet content.
"snippetStatus": "A String", # Status of the snippet defined by the search team.
},
],
"structData": { # Data representation. The structured JSON data for the document. It's populated from the struct data from the Document, or the Chunk in search result.
"a_key": "", # Properties of the object.
},
"title": "A String", # Title.
"uri": "A String", # URI for the document.
},
],
},
"searchAction": { # Search action. # Search action.
"query": "A String", # The query to search.
},
},
],
"description": "A String", # The description of the step.
"state": "A String", # The state of the step.
"thought": "A String", # The thought of the step.
},
],
},
"answerQueryToken": "A String", # A global unique ID used for logging.
"session": { # External session proto definition. # Session resource object. It will be only available when session field is set and valid in the AnswerQueryRequest request.
"endTime": "A String", # Output only. The time the session finished.
"name": "A String", # Immutable. Fully qualified name `projects/{project}/locations/global/collections/{collection}/engines/{engine}/sessions/*`
"startTime": "A String", # Output only. The time the session started.
"state": "A String", # The state of the session.
"turns": [ # Turns.
{ # Represents a turn, including a query from the user and a answer from service.
"answer": "A String", # The resource name of the answer to the user query. Only set if the answer generation (/answer API call) happened in this turn.
"query": { # Defines a user inputed query. # The user query.
"queryId": "A String", # Unique Id for the query.
"text": "A String", # Plain text.
},
},
],
"userPseudoId": "A String", # A unique identifier for tracking users.
},
}
close()
Close httplib2 connections.
recommend(servingConfig, body=None, x__xgafv=None)
Makes a recommendation, which requires a contextual user event.
Args:
servingConfig: string, Required. Full resource name of a ServingConfig: `projects/*/locations/global/collections/*/engines/*/servingConfigs/*`, or `projects/*/locations/global/collections/*/dataStores/*/servingConfigs/*` One default serving config is created along with your recommendation engine creation. The engine ID is used as the ID of the default serving config. For example, for Engine `projects/*/locations/global/collections/*/engines/my-engine`, you can use `projects/*/locations/global/collections/*/engines/my-engine/servingConfigs/my-engine` for your RecommendationService.Recommend requests. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for Recommend method.
"filter": "A String", # Filter for restricting recommendation results with a length limit of 5,000 characters. Currently, only filter expressions on the `filter_tags` attribute is supported. Examples: * `(filter_tags: ANY("Red", "Blue") OR filter_tags: ANY("Hot", "Cold"))` * `(filter_tags: ANY("Red", "Blue")) AND NOT (filter_tags: ANY("Green"))` If `attributeFilteringSyntax` is set to true under the `params` field, then attribute-based expressions are expected instead of the above described tag-based syntax. Examples: * (launguage: ANY("en", "es")) AND NOT (categories: ANY("Movie")) * (available: true) AND (launguage: ANY("en", "es")) OR (categories: ANY("Movie")) If your filter blocks all results, the API returns generic (unfiltered) popular Documents. If you only want results strictly matching the filters, set `strictFiltering` to `true` in RecommendRequest.params to receive empty results instead. Note that the API never returns Documents with `storageStatus` as `EXPIRED` or `DELETED` regardless of filter choices.
"pageSize": 42, # Maximum number of results to return. Set this property to the number of recommendation results needed. If zero, the service chooses a reasonable default. The maximum allowed value is 100. Values above 100 are set to 100.
"params": { # Additional domain specific parameters for the recommendations. Allowed values: * `returnDocument`: Boolean. If set to `true`, the associated Document object is returned in RecommendResponse.RecommendationResult.document. * `returnScore`: Boolean. If set to true, the recommendation score corresponding to each returned Document is set in RecommendResponse.RecommendationResult.metadata. The given score indicates the probability of a Document conversion given the user's context and history. * `strictFiltering`: Boolean. True by default. If set to `false`, the service returns generic (unfiltered) popular Documents instead of empty if your filter blocks all recommendation results. * `diversityLevel`: String. Default empty. If set to be non-empty, then it needs to be one of: * `no-diversity` * `low-diversity` * `medium-diversity` * `high-diversity` * `auto-diversity` This gives request-level control and adjusts recommendation results based on Document category. * `attributeFilteringSyntax`: Boolean. False by default. If set to true, the `filter` field is interpreted according to the new, attribute-based syntax.
"a_key": "",
},
"userEvent": { # UserEvent captures all metadata information Discovery Engine API needs to know about how end users interact with your website. # Required. Context about the user, what they are looking at and what action they took to trigger the Recommend request. Note that this user event detail won't be ingested to userEvent logs. Thus, a separate userEvent write request is required for event logging. Don't set UserEvent.user_pseudo_id or UserEvent.user_info.user_id to the same fixed ID for different users. If you are trying to receive non-personalized recommendations (not recommended; this can negatively impact model performance), instead set UserEvent.user_pseudo_id to a random unique ID and leave UserEvent.user_info.user_id unset.
"attributes": { # Extra user event features to include in the recommendation model. These attributes must NOT contain data that needs to be parsed or processed further, e.g. JSON or other encodings. If you provide custom attributes for ingested user events, also include them in the user events that you associate with prediction requests. Custom attribute formatting must be consistent between imported events and events provided with prediction requests. This lets the Discovery Engine API use those custom attributes when training models and serving predictions, which helps improve recommendation quality. This field needs to pass all below criteria, otherwise an `INVALID_ARGUMENT` error is returned: * The key must be a UTF-8 encoded string with a length limit of 5,000 characters. * For text attributes, at most 400 values are allowed. Empty values are not allowed. Each value must be a UTF-8 encoded string with a length limit of 256 characters. * For number attributes, at most 400 values are allowed. For product recommendations, an example of extra user information is `traffic_channel`, which is how a user arrives at the site. Users can arrive at the site by coming to the site directly, coming through Google search, or in other ways.
"a_key": { # A custom attribute that is not explicitly modeled in a resource, e.g. UserEvent.
"numbers": [ # The numerical values of this custom attribute. For example, `[2.3, 15.4]` when the key is "lengths_cm". Exactly one of CustomAttribute.text or CustomAttribute.numbers should be set. Otherwise, an `INVALID_ARGUMENT` error is returned.
3.14,
],
"text": [ # The textual values of this custom attribute. For example, `["yellow", "green"]` when the key is "color". Empty string is not allowed. Otherwise, an `INVALID_ARGUMENT` error is returned. Exactly one of CustomAttribute.text or CustomAttribute.numbers should be set. Otherwise, an `INVALID_ARGUMENT` error is returned.
"A String",
],
},
},
"attributionToken": "A String", # Token to attribute an API response to user action(s) to trigger the event. Highly recommended for user events that are the result of RecommendationService.Recommend. This field enables accurate attribution of recommendation model performance. The value must be one of: * RecommendResponse.attribution_token for events that are the result of RecommendationService.Recommend. * SearchResponse.attribution_token for events that are the result of SearchService.Search. This token enables us to accurately attribute page view or conversion completion back to the event and the particular predict response containing this clicked/purchased product. If user clicks on product K in the recommendation results, pass RecommendResponse.attribution_token as a URL parameter to product K's page. When recording events on product K's page, log the RecommendResponse.attribution_token to this field.
"completionInfo": { # Detailed completion information including completion attribution token and clicked completion info. # CompletionService.CompleteQuery details related to the event. This field should be set for `search` event when autocomplete function is enabled and the user clicks a suggestion for search.
"selectedPosition": 42, # End user selected CompleteQueryResponse.QuerySuggestion.suggestion position, starting from 0.
"selectedSuggestion": "A String", # End user selected CompleteQueryResponse.QuerySuggestion.suggestion.
},
"dataStore": "A String", # The DataStore resource full name, of the form `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`. Optional. Only required for user events whose data store can't by determined by UserEvent.engine or UserEvent.documents. If data store is set in the parent of write/import/collect user event requests, this field can be omitted.
"directUserRequest": True or False, # Should set to true if the request is made directly from the end user, in which case the UserEvent.user_info.user_agent can be populated from the HTTP request. This flag should be set only if the API request is made directly from the end user such as a mobile app (and not if a gateway or a server is processing and pushing the user events). This should not be set when using the JavaScript tag in UserEventService.CollectUserEvent.
"documents": [ # List of Documents associated with this user event. This field is optional except for the following event types: * `view-item` * `add-to-cart` * `purchase` * `media-play` * `media-complete` In a `search` event, this field represents the documents returned to the end user on the current page (the end user may have not finished browsing the whole page yet). When a new page is returned to the end user, after pagination/filtering/ordering even for the same query, a new `search` event with different UserEvent.documents is desired.
{ # Detailed document information associated with a user event.
"id": "A String", # The Document resource ID.
"joined": True or False, # Output only. Whether the referenced Document can be found in the data store.
"name": "A String", # The Document resource full name, of the form: `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}/branches/{branch_id}/documents/{document_id}`
"promotionIds": [ # The promotion IDs associated with this Document. Currently, this field is restricted to at most one ID.
"A String",
],
"quantity": 42, # Quantity of the Document associated with the user event. Defaults to 1. For example, this field is 2 if two quantities of the same Document are involved in a `add-to-cart` event. Required for events of the following event types: * `add-to-cart` * `purchase`
"uri": "A String", # The Document URI - only allowed for website data stores.
},
],
"engine": "A String", # The Engine resource name, in the form of `projects/{project}/locations/{location}/collections/{collection_id}/engines/{engine_id}`. Optional. Only required for Engine produced user events. For example, user events from blended search.
"eventTime": "A String", # Only required for UserEventService.ImportUserEvents method. Timestamp of when the user event happened.
"eventType": "A String", # Required. User event type. Allowed values are: Generic values: * `search`: Search for Documents. * `view-item`: Detailed page view of a Document. * `view-item-list`: View of a panel or ordered list of Documents. * `view-home-page`: View of the home page. * `view-category-page`: View of a category page, e.g. Home > Men > Jeans * `add-feedback`: Add a user feedback. Retail-related values: * `add-to-cart`: Add an item(s) to cart, e.g. in Retail online shopping * `purchase`: Purchase an item(s) Media-related values: * `media-play`: Start/resume watching a video, playing a song, etc. * `media-complete`: Finished or stopped midway through a video, song, etc.
"filter": "A String", # The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. One example is for `search` events, the associated SearchRequest may contain a filter expression in SearchRequest.filter conforming to https://google.aip.dev/160#filtering. Similarly, for `view-item-list` events that are generated from a RecommendRequest, this field may be populated directly from RecommendRequest.filter conforming to https://google.aip.dev/160#filtering. The value must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
"mediaInfo": { # Media-specific user event information. # Media-specific info.
"mediaProgressDuration": "A String", # The media progress time in seconds, if applicable. For example, if the end user has finished 90 seconds of a playback video, then MediaInfo.media_progress_duration.seconds should be set to 90.
"mediaProgressPercentage": 3.14, # Media progress should be computed using only the media_progress_duration relative to the media total length. This value must be between `[0, 1.0]` inclusive. If this is not a playback or the progress cannot be computed (e.g. ongoing livestream), this field should be unset.
},
"pageInfo": { # Detailed page information. # Page metadata such as categories and other critical information for certain event types such as `view-category-page`.
"pageCategory": "A String", # The most specific category associated with a category page. To represent full path of category, use '>' sign to separate different hierarchies. If '>' is part of the category name, replace it with other character(s). Category pages include special pages such as sales or promotions. For instance, a special sale page may have the category hierarchy: `"pageCategory" : "Sales > 2017 Black Friday Deals"`. Required for `view-category-page` events. Other event types should not set this field. Otherwise, an `INVALID_ARGUMENT` error is returned.
"pageviewId": "A String", # A unique ID of a web page view. This should be kept the same for all user events triggered from the same pageview. For example, an item detail page view could trigger multiple events as the user is browsing the page. The `pageview_id` property should be kept the same for all these events so that they can be grouped together properly. When using the client side event reporting with JavaScript pixel and Google Tag Manager, this value is filled in automatically.
"referrerUri": "A String", # The referrer URL of the current page. When using the client side event reporting with JavaScript pixel and Google Tag Manager, this value is filled in automatically. However, some browser privacy restrictions may cause this field to be empty.
"uri": "A String", # Complete URL (window.location.href) of the user's current page. When using the client side event reporting with JavaScript pixel and Google Tag Manager, this value is filled in automatically. Maximum length 5,000 characters.
},
"panel": { # Detailed panel information associated with a user event. # Panel metadata associated with this user event.
"displayName": "A String", # The display name of the panel.
"panelId": "A String", # Required. The panel ID.
"panelPosition": 42, # The ordered position of the panel, if shown to the user with other panels. If set, then total_panels must also be set.
"totalPanels": 42, # The total number of panels, including this one, shown to the user. Must be set if panel_position is set.
},
"promotionIds": [ # The promotion IDs if this is an event associated with promotions. Currently, this field is restricted to at most one ID.
"A String",
],
"searchInfo": { # Detailed search information. # SearchService.Search details related to the event. This field should be set for `search` event.
"offset": 42, # An integer that specifies the current offset for pagination (the 0-indexed starting location, amongst the products deemed by the API as relevant). See SearchRequest.offset for definition. If this field is negative, an `INVALID_ARGUMENT` is returned. This can only be set for `search` events. Other event types should not set this field. Otherwise, an `INVALID_ARGUMENT` error is returned.
"orderBy": "A String", # The order in which products are returned, if applicable. See SearchRequest.order_by for definition and syntax. The value must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an `INVALID_ARGUMENT` error is returned. This can only be set for `search` events. Other event types should not set this field. Otherwise, an `INVALID_ARGUMENT` error is returned.
"searchQuery": "A String", # The user's search query. See SearchRequest.query for definition. The value must be a UTF-8 encoded string with a length limit of 5,000 characters. Otherwise, an `INVALID_ARGUMENT` error is returned. At least one of search_query or PageInfo.page_category is required for `search` events. Other event types should not set this field. Otherwise, an `INVALID_ARGUMENT` error is returned.
},
"sessionId": "A String", # A unique identifier for tracking a visitor session with a length limit of 128 bytes. A session is an aggregation of an end user behavior in a time span. A general guideline to populate the session_id: 1. If user has no activity for 30 min, a new session_id should be assigned. 2. The session_id should be unique across users, suggest use uuid or add UserEvent.user_pseudo_id as prefix.
"tagIds": [ # A list of identifiers for the independent experiment groups this user event belongs to. This is used to distinguish between user events associated with different experiment setups.
"A String",
],
"transactionInfo": { # A transaction represents the entire purchase transaction. # The transaction metadata (if any) associated with this user event.
"cost": 3.14, # All the costs associated with the products. These can be manufacturing costs, shipping expenses not borne by the end user, or any other costs, such that: * Profit = value - tax - cost
"currency": "A String", # Required. Currency code. Use three-character ISO-4217 code.
"discountValue": 3.14, # The total discount(s) value applied to this transaction. This figure should be excluded from TransactionInfo.value For example, if a user paid TransactionInfo.value amount, then nominal (pre-discount) value of the transaction is the sum of TransactionInfo.value and TransactionInfo.discount_value This means that profit is calculated the same way, regardless of the discount value, and that TransactionInfo.discount_value can be larger than TransactionInfo.value: * Profit = value - tax - cost
"tax": 3.14, # All the taxes associated with the transaction.
"transactionId": "A String", # The transaction ID with a length limit of 128 characters.
"value": 3.14, # Required. Total non-zero value associated with the transaction. This value may include shipping, tax, or other adjustments to the total value that you want to include.
},
"userInfo": { # Information of an end user. # Information about the end user.
"userAgent": "A String", # User agent as included in the HTTP header. The field must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an `INVALID_ARGUMENT` error is returned. This should not be set when using the client side event reporting with GTM or JavaScript tag in UserEventService.CollectUserEvent or if UserEvent.direct_user_request is set.
"userId": "A String", # Highly recommended for logged-in users. Unique identifier for logged-in user, such as a user name. Don't set for anonymous users. Always use a hashed value for this ID. Don't set the field to the same fixed ID for different users. This mixes the event history of those users together, which results in degraded model quality. The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
},
"userPseudoId": "A String", # Required. A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor log in/out of the website. Do not set the field to the same fixed ID for different users. This mixes the event history of those users together, which results in degraded model quality. The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned. The field should not contain PII or user-data. We recommend to use Google Analytics [Client ID](https://developers.google.com/analytics/devguides/collection/analyticsjs/field-reference#clientId) for this field.
},
"userLabels": { # The user labels applied to a resource must meet the following requirements: * Each resource can have multiple labels, up to a maximum of 64. * Each label must be a key-value pair. * Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters. * Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed. * The key portion of a label must be unique. However, you can use the same key with multiple resources. * Keys must start with a lowercase letter or international character. See [Requirements for labels](https://cloud.google.com/resource-manager/docs/creating-managing-labels#requirements) for more details.
"a_key": "A String",
},
"validateOnly": True or False, # Use validate only mode for this recommendation query. If set to `true`, a fake model is used that returns arbitrary Document IDs. Note that the validate only mode should only be used for testing the API, or if the model is not ready.
}
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 Recommend method.
"attributionToken": "A String", # A unique attribution token. This should be included in the UserEvent logs resulting from this recommendation, which enables accurate attribution of recommendation model performance.
"missingIds": [ # IDs of documents in the request that were missing from the default Branch associated with the requested ServingConfig.
"A String",
],
"results": [ # A list of recommended Documents. The order represents the ranking (from the most relevant Document to the least).
{ # RecommendationResult represents a generic recommendation result with associated metadata.
"document": { # Document captures all raw metadata information of items to be recommended or searched. # Set if `returnDocument` is set to true in RecommendRequest.params.
"content": { # Unstructured data linked to this document. # The unstructured data linked to this document. Content must be set if this document is under a `CONTENT_REQUIRED` data store.
"mimeType": "A String", # The MIME type of the content. Supported types: * `application/pdf` (PDF, only native PDFs are supported for now) * `text/html` (HTML) * `application/vnd.openxmlformats-officedocument.wordprocessingml.document` (DOCX) * `application/vnd.openxmlformats-officedocument.presentationml.presentation` (PPTX) * `text/plain` (TXT) See https://www.iana.org/assignments/media-types/media-types.xhtml.
"rawBytes": "A String", # The content represented as a stream of bytes. The maximum length is 1,000,000 bytes (1 MB / ~0.95 MiB). Note: As with all `bytes` fields, this field is represented as pure binary in Protocol Buffers and base64-encoded string in JSON. For example, `abc123!?$*&()'-=@~` should be represented as `YWJjMTIzIT8kKiYoKSctPUB+` in JSON. See https://developers.google.com/protocol-buffers/docs/proto3#json.
"uri": "A String", # The URI of the content. Only Cloud Storage URIs (e.g. `gs://bucket-name/path/to/file`) are supported. The maximum file size is 2.5 MB for text-based formats, 200 MB for other formats.
},
"derivedStructData": { # Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.
"a_key": "", # Properties of the object.
},
"id": "A String", # Immutable. The identifier of the document. Id should conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters.
"indexStatus": { # Index status of the document. # Output only. The index status of the document. * If document is indexed successfully, the index_time field is populated. * Otherwise, if document is not indexed due to errors, the error_samples field is populated. * Otherwise, index_status is unset.
"errorSamples": [ # A sample of errors encountered while indexing the document. If this field is populated, the document is not indexed due to errors.
{ # 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).
"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.
},
],
"indexTime": "A String", # The time when the document was indexed. If this field is populated, it means the document has been indexed.
},
"indexTime": "A String", # Output only. The last time the document was indexed. If this field is set, the document could be returned in search results. This field is OUTPUT_ONLY. If this field is not populated, it means the document has never been indexed.
"jsonData": "A String", # The JSON string representation of the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"name": "A String", # Immutable. The full resource name of the document. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"parentDocumentId": "A String", # The identifier of the parent document. Currently supports at most two level document hierarchy. Id should conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters.
"schemaId": "A String", # The identifier of the schema located in the same data store.
"structData": { # The structured JSON data for the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"a_key": "", # Properties of the object.
},
},
"id": "A String", # Resource ID of the recommended Document.
"metadata": { # Additional Document metadata or annotations. Possible values: * `score`: Recommendation score in double value. Is set if `returnScore` is set to true in RecommendRequest.params.
"a_key": "",
},
},
],
"validateOnly": True or False, # True if RecommendRequest.validate_only was set.
}
search(servingConfig, body=None, x__xgafv=None)
Performs a search.
Args:
servingConfig: string, Required. The resource name of the Search serving config, such as `projects/*/locations/global/collections/default_collection/engines/*/servingConfigs/default_serving_config`, or `projects/*/locations/global/collections/default_collection/dataStores/default_data_store/servingConfigs/default_serving_config`. This field is used to identify the serving configuration name, set of models used to make the search. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for SearchService.Search method.
"boostSpec": { # Boost specification to boost certain documents. # Boost specification to boost certain documents. For more information on boosting, see [Boosting](https://cloud.google.com/generative-ai-app-builder/docs/boost-search-results)
"conditionBoostSpecs": [ # 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, # 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. Only one of the (condition, boost) combination or the boost_control_spec below are set. If both are set then the global boost is ignored and the more fine-grained boost_control_spec is applied.
"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. # Complex specification for custom ranking based on customer defined attribute value.
"attributeType": "A String", # 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": [ # 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", # 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, # 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", # The name of the field whose value will be used to determine the boost amount.
"interpolationType": "A String", # The interpolation type to be applied to connect the control points listed below.
},
"condition": "A String", # An expression which specifies a boost condition. The syntax and supported fields are the same as a filter expression. See SearchRequest.filter for detail syntax and limitations. Examples: * To boost documents with document ID "doc_1" or "doc_2", and color "Red" or "Blue": `(document_id: ANY("doc_1", "doc_2")) AND (color: ANY("Red", "Blue"))`
},
],
},
"branch": "A String", # The branch resource name, such as `projects/*/locations/global/collections/default_collection/dataStores/default_data_store/branches/0`. Use `default_branch` as the branch ID or leave this field empty, to search documents under the default branch.
"canonicalFilter": "A String", # The default filter that is applied when a user performs a search without checking any filters on the search page. The filter applied to every search request when quality improvement such as query expansion is needed. In the case a query does not have a sufficient amount of results this filter will be used to determine whether or not to enable the query expansion flow. The original filter will still be used for the query expanded search. This field is strongly recommended to achieve high search quality. For more information about filter syntax, see SearchRequest.filter.
"contentSearchSpec": { # A specification for configuring the behavior of content search. # A specification for configuring the behavior of content search.
"chunkSpec": { # Specifies the chunk spec to be returned from the search response. Only available if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS # Specifies the chunk spec to be returned from the search response. Only available if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS
"numNextChunks": 42, # The number of next chunks to be returned of the current chunk. The maximum allowed value is 3. If not specified, no next chunks will be returned.
"numPreviousChunks": 42, # The number of previous chunks to be returned of the current chunk. The maximum allowed value is 3. If not specified, no previous chunks will be returned.
},
"extractiveContentSpec": { # A specification for configuring the extractive content in a search response. # If there is no extractive_content_spec provided, there will be no extractive answer in the search response.
"maxExtractiveAnswerCount": 42, # The maximum number of extractive answers returned in each search result. An extractive answer is a verbatim answer extracted from the original document, which provides a precise and contextually relevant answer to the search query. If the number of matching answers is less than the `max_extractive_answer_count`, return all of the answers. Otherwise, return the `max_extractive_answer_count`. At most five answers are returned for each SearchResult.
"maxExtractiveSegmentCount": 42, # The max number of extractive segments returned in each search result. Only applied if the DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED or DataStore.solution_types is SOLUTION_TYPE_CHAT. An extractive segment is a text segment extracted from the original document that is relevant to the search query, and, in general, more verbose than an extractive answer. The segment could then be used as input for LLMs to generate summaries and answers. If the number of matching segments is less than `max_extractive_segment_count`, return all of the segments. Otherwise, return the `max_extractive_segment_count`.
"numNextSegments": 42, # Return at most `num_next_segments` segments after each selected segments.
"numPreviousSegments": 42, # Specifies whether to also include the adjacent from each selected segments. Return at most `num_previous_segments` segments before each selected segments.
"returnExtractiveSegmentScore": True or False, # Specifies whether to return the confidence score from the extractive segments in each search result. This feature is available only for new or allowlisted data stores. To allowlist your data store, contact your Customer Engineer. The default value is `false`.
},
"searchResultMode": "A String", # Specifies the search result mode. If unspecified, the search result mode defaults to `DOCUMENTS`.
"snippetSpec": { # A specification for configuring snippets in a search response. # If `snippetSpec` is not specified, snippets are not included in the search response.
"maxSnippetCount": 42, # [DEPRECATED] This field is deprecated. To control snippet return, use `return_snippet` field. For backwards compatibility, we will return snippet if max_snippet_count > 0.
"referenceOnly": True or False, # [DEPRECATED] This field is deprecated and will have no affect on the snippet.
"returnSnippet": True or False, # If `true`, then return snippet. If no snippet can be generated, we return "No snippet is available for this page." A `snippet_status` with `SUCCESS` or `NO_SNIPPET_AVAILABLE` will also be returned.
},
"summarySpec": { # A specification for configuring a summary returned in a search response. # If `summarySpec` is not specified, summaries are not included in the search response.
"ignoreAdversarialQuery": True or False, # Specifies whether to filter out adversarial queries. The default value is `false`. Google employs search-query classification to detect adversarial queries. No summary is returned if the search query is classified as an adversarial query. For example, a user might ask a question regarding negative comments about the company or submit a query designed to generate unsafe, policy-violating output. If this field is set to `true`, we skip generating summaries for adversarial queries and return fallback messages instead.
"ignoreJailBreakingQuery": True or False, # Optional. Specifies whether to filter out jail-breaking queries. The default value is `false`. Google employs search-query classification to detect jail-breaking queries. No summary is returned if the search query is classified as a jail-breaking query. A user might add instructions to the query to change the tone, style, language, content of the answer, or ask the model to act as a different entity, e.g. "Reply in the tone of a competing company's CEO". If this field is set to `true`, we skip generating summaries for jail-breaking queries and return fallback messages instead.
"ignoreLowRelevantContent": True or False, # Specifies whether to filter out queries that have low relevance. The default value is `false`. If this field is set to `false`, all search results are used regardless of relevance to generate answers. If set to `true`, only queries with high relevance search results will generate answers.
"ignoreNonSummarySeekingQuery": True or False, # Specifies whether to filter out queries that are not summary-seeking. The default value is `false`. Google employs search-query classification to detect summary-seeking queries. No summary is returned if the search query is classified as a non-summary seeking query. For example, `why is the sky blue` and `Who is the best soccer player in the world?` are summary-seeking queries, but `SFO airport` and `world cup 2026` are not. They are most likely navigational queries. If this field is set to `true`, we skip generating summaries for non-summary seeking queries and return fallback messages instead.
"includeCitations": True or False, # Specifies whether to include citations in the summary. The default value is `false`. When this field is set to `true`, summaries include in-line citation numbers. Example summary including citations: BigQuery is Google Cloud's fully managed and completely serverless enterprise data warehouse [1]. BigQuery supports all data types, works across clouds, and has built-in machine learning and business intelligence, all within a unified platform [2, 3]. The citation numbers refer to the returned search results and are 1-indexed. For example, [1] means that the sentence is attributed to the first search result. [2, 3] means that the sentence is attributed to both the second and third search results.
"languageCode": "A String", # Language code for Summary. Use language tags defined by [BCP47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt). Note: This is an experimental feature.
"modelPromptSpec": { # Specification of the prompt to use with the model. # If specified, the spec will be used to modify the prompt provided to the LLM.
"preamble": "A String", # Text at the beginning of the prompt that instructs the assistant. Examples are available in the user guide.
},
"modelSpec": { # Specification of the model. # If specified, the spec will be used to modify the model specification provided to the LLM.
"version": "A String", # The model version used to generate the summary. Supported values are: * `stable`: string. Default value when no value is specified. Uses a generally available, fine-tuned model. For more information, see [Answer generation model versions and lifecycle](https://cloud.google.com/generative-ai-app-builder/docs/answer-generation-models). * `preview`: string. (Public preview) Uses a preview model. For more information, see [Answer generation model versions and lifecycle](https://cloud.google.com/generative-ai-app-builder/docs/answer-generation-models).
},
"summaryResultCount": 42, # The number of top results to generate the summary from. If the number of results returned is less than `summaryResultCount`, the summary is generated from all of the results. At most 10 results for documents mode, or 50 for chunks mode, can be used to generate a summary. The chunks mode is used when SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.
"useSemanticChunks": True or False, # If true, answer will be generated from most relevant chunks from top search results. This feature will improve summary quality. Note that with this feature enabled, not all top search results will be referenced and included in the reference list, so the citation source index only points to the search results listed in the reference list.
},
},
"dataStoreSpecs": [ # Specs defining dataStores to filter on in a search call and configurations for those dataStores. This is only considered for engines with multiple dataStores use case. For single dataStore within an engine, they should use the specs at the top level.
{ # A struct to define data stores to filter on in a search call and configurations for those data stores. Otherwise, an `INVALID_ARGUMENT` error is returned.
"dataStore": "A String", # Required. Full resource name of DataStore, such as `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`.
"filter": "A String", # Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
},
],
"facetSpecs": [ # Facet specifications for faceted search. If empty, no facets are returned. A maximum of 100 values are allowed. Otherwise, an `INVALID_ARGUMENT` error is returned.
{ # A facet specification to perform faceted search.
"enableDynamicPosition": True or False, # Enables dynamic position for this facet. If set to true, the position of this facet among all facets in the response is determined automatically. If dynamic facets are enabled, it is ordered together. If set to false, the position of this facet in the response is the same as in the request, and it is ranked before the facets with dynamic position enable and all dynamic facets. For example, you may always want to have rating facet returned in the response, but it's not necessarily to always display the rating facet at the top. In that case, you can set enable_dynamic_position to true so that the position of rating facet in response is determined automatically. Another example, assuming you have the following facets in the request: * "rating", enable_dynamic_position = true * "price", enable_dynamic_position = false * "brands", enable_dynamic_position = false And also you have a dynamic facets enabled, which generates a facet `gender`. Then the final order of the facets in the response can be ("price", "brands", "rating", "gender") or ("price", "brands", "gender", "rating") depends on how API orders "gender" and "rating" facets. However, notice that "price" and "brands" are always ranked at first and second position because their enable_dynamic_position is false.
"excludedFilterKeys": [ # List of keys to exclude when faceting. By default, FacetKey.key is not excluded from the filter unless it is listed in this field. Listing a facet key in this field allows its values to appear as facet results, even when they are filtered out of search results. Using this field does not affect what search results are returned. For example, suppose there are 100 documents with the color facet "Red" and 200 documents with the color facet "Blue". A query containing the filter "color:ANY("Red")" and having "color" as FacetKey.key would by default return only "Red" documents in the search results, and also return "Red" with count 100 as the only color facet. Although there are also blue documents available, "Blue" would not be shown as an available facet value. If "color" is listed in "excludedFilterKeys", then the query returns the facet values "Red" with count 100 and "Blue" with count 200, because the "color" key is now excluded from the filter. Because this field doesn't affect search results, the search results are still correctly filtered to return only "Red" documents. A maximum of 100 values are allowed. Otherwise, an `INVALID_ARGUMENT` error is returned.
"A String",
],
"facetKey": { # Specifies how a facet is computed. # Required. The facet key specification.
"caseInsensitive": True or False, # True to make facet keys case insensitive when getting faceting values with prefixes or contains; false otherwise.
"contains": [ # Only get facet values that contain the given strings. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "contains" to "2022", the "category" facet only contains "Action > 2022" and "Sci-Fi > 2022". Only supported on textual fields. Maximum is 10.
"A String",
],
"intervals": [ # Set only if values should be bucketed into intervals. Must be set for facets with numerical values. Must not be set for facet with text values. Maximum number of intervals is 30.
{ # A floating point interval.
"exclusiveMaximum": 3.14, # Exclusive upper bound.
"exclusiveMinimum": 3.14, # Exclusive lower bound.
"maximum": 3.14, # Inclusive upper bound.
"minimum": 3.14, # Inclusive lower bound.
},
],
"key": "A String", # Required. Supported textual and numerical facet keys in Document object, over which the facet values are computed. Facet key is case-sensitive.
"orderBy": "A String", # The order in which documents are returned. Allowed values are: * "count desc", which means order by SearchResponse.Facet.values.count descending. * "value desc", which means order by SearchResponse.Facet.values.value descending. Only applies to textual facets. If not set, textual values are sorted in [natural order](https://en.wikipedia.org/wiki/Natural_sort_order); numerical intervals are sorted in the order given by FacetSpec.FacetKey.intervals.
"prefixes": [ # Only get facet values that start with the given string prefix. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "prefixes" to "Action", the "category" facet only contains "Action > 2022" and "Action > 2021". Only supported on textual fields. Maximum is 10.
"A String",
],
"restrictedValues": [ # Only get facet for the given restricted values. Only supported on textual fields. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "restricted_values" to "Action > 2022", the "category" facet only contains "Action > 2022". Only supported on textual fields. Maximum is 10.
"A String",
],
},
"limit": 42, # Maximum facet values that are returned for this facet. If unspecified, defaults to 20. The maximum allowed value is 300. Values above 300 are coerced to 300. For aggregation in healthcare search, when the [FacetKey.key] is "healthcare_aggregation_key", the limit will be overridden to 10,000 internally, regardless of the value set here. If this field is negative, an `INVALID_ARGUMENT` is returned.
},
],
"filter": "A String", # The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive. If this field is unrecognizable, an `INVALID_ARGUMENT` is returned. Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customer might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")' For more information about filtering including syntax and filter operators, see [Filter](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
"imageQuery": { # Specifies the image query input. # Raw image query.
"imageBytes": "A String", # Base64 encoded image bytes. Supported image formats: JPEG, PNG, and BMP.
},
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see [Standard fields](https://cloud.google.com/apis/design/standard_fields). This field helps to better interpret the query. If a value isn't specified, the query language code is automatically detected, which may not be accurate.
"offset": 42, # A 0-indexed integer that specifies the current offset (that is, starting result location, amongst the Documents deemed by the API as relevant) in search results. This field is only considered if page_token is unset. If this field is negative, an `INVALID_ARGUMENT` is returned.
"oneBoxPageSize": 42, # The maximum number of results to return for OneBox. This applies to each OneBox type individually. Default number is 10.
"orderBy": "A String", # The order in which documents are returned. Documents can be ordered by a field in an Document object. Leave it unset if ordered by relevance. `order_by` expression is case-sensitive. For more information on ordering the website search results, see [Order web search results](https://cloud.google.com/generative-ai-app-builder/docs/order-web-search-results). For more information on ordering the healthcare search results, see [Order healthcare search results](https://cloud.google.com/generative-ai-app-builder/docs/order-hc-results). If this field is unrecognizable, an `INVALID_ARGUMENT` is returned.
"pageSize": 42, # Maximum number of Documents to return. The maximum allowed value depends on the data type. Values above the maximum value are coerced to the maximum value. * Websites with basic indexing: Default `10`, Maximum `25`. * Websites with advanced indexing: Default `25`, Maximum `50`. * Other: Default `50`, Maximum `100`. If this field is negative, an `INVALID_ARGUMENT` is returned.
"pageToken": "A String", # A page token received from a previous SearchService.Search call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to SearchService.Search must match the call that provided the page token. Otherwise, an `INVALID_ARGUMENT` error is returned.
"params": { # Additional search parameters. For public website search only, supported values are: * `user_country_code`: string. Default empty. If set to non-empty, results are restricted or boosted based on the location provided. For example, `user_country_code: "au"` For available codes see [Country Codes](https://developers.google.com/custom-search/docs/json_api_reference#countryCodes) * `search_type`: double. Default empty. Enables non-webpage searching depending on the value. The only valid non-default value is 1, which enables image searching. For example, `search_type: 1`
"a_key": "",
},
"query": "A String", # Raw search query.
"queryExpansionSpec": { # Specification to determine under which conditions query expansion should occur. # The query expansion specification that specifies the conditions under which query expansion occurs.
"condition": "A String", # The condition under which query expansion should occur. Default to Condition.DISABLED.
"pinUnexpandedResults": True or False, # Whether to pin unexpanded results. If this field is set to true, unexpanded products are always at the top of the search results, followed by the expanded results.
},
"safeSearch": True or False, # Whether to turn on safe search. This is only supported for website search.
"searchAsYouTypeSpec": { # Specification for search as you type in search requests. # Search as you type configuration. Only supported for the IndustryVertical.MEDIA vertical.
"condition": "A String", # The condition under which search as you type should occur. Default to Condition.DISABLED.
},
"session": "A String", # The session resource name. Optional. Session allows users to do multi-turn /search API calls or coordination between /search API calls and /answer API calls. Example #1 (multi-turn /search API calls): 1. Call /search API with the auto-session mode (see below). 2. Call /search API with the session ID generated in the first call. Here, the previous search query gets considered in query standing. I.e., if the first query is "How did Alphabet do in 2022?" and the current query is "How about 2023?", the current query will be interpreted as "How did Alphabet do in 2023?". Example #2 (coordination between /search API calls and /answer API calls): 1. Call /search API with the auto-session mode (see below). 2. Call /answer API with the session ID generated in the first call. Here, the answer generation happens in the context of the search results from the first search call. Auto-session mode: when `projects/.../sessions/-` is used, a new session gets automatically created. Otherwise, users can use the create-session API to create a session manually. Multi-turn Search feature is currently at private GA stage. Please use v1alpha or v1beta version instead before we launch this feature to public GA. Or ask for allowlisting through Google Support team.
"sessionSpec": { # Session specification. Multi-turn Search feature is currently at private GA stage. Please use v1alpha or v1beta version instead before we launch this feature to public GA. Or ask for allowlisting through Google Support team. # Session specification. Can be used only when `session` is set.
"queryId": "A String", # If set, the search result gets stored to the "turn" specified by this query ID. Example: Let's say the session looks like this: session { name: ".../sessions/xxx" turns { query { text: "What is foo?" query_id: ".../questions/yyy" } answer: "Foo is ..." } turns { query { text: "How about bar then?" query_id: ".../questions/zzz" } } } The user can call /search API with a request like this: session: ".../sessions/xxx" session_spec { query_id: ".../questions/zzz" } Then, the API stores the search result, associated with the last turn. The stored search result can be used by a subsequent /answer API call (with the session ID and the query ID specified). Also, it is possible to call /search and /answer in parallel with the same session ID & query ID.
"searchResultPersistenceCount": 42, # The number of top search results to persist. The persisted search results can be used for the subsequent /answer api call. This field is simliar to the `summary_result_count` field in SearchRequest.ContentSearchSpec.SummarySpec.summary_result_count. At most 10 results for documents mode, or 50 for chunks mode.
},
"spellCorrectionSpec": { # The specification for query spell correction. # The spell correction specification that specifies the mode under which spell correction takes effect.
"mode": "A String", # The mode under which spell correction replaces the original search query. Defaults to Mode.AUTO.
},
"userInfo": { # Information of an end user. # Information about the end user. Highly recommended for analytics. UserInfo.user_agent is used to deduce `device_type` for analytics.
"userAgent": "A String", # User agent as included in the HTTP header. The field must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an `INVALID_ARGUMENT` error is returned. This should not be set when using the client side event reporting with GTM or JavaScript tag in UserEventService.CollectUserEvent or if UserEvent.direct_user_request is set.
"userId": "A String", # Highly recommended for logged-in users. Unique identifier for logged-in user, such as a user name. Don't set for anonymous users. Always use a hashed value for this ID. Don't set the field to the same fixed ID for different users. This mixes the event history of those users together, which results in degraded model quality. The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
},
"userLabels": { # The user labels applied to a resource must meet the following requirements: * Each resource can have multiple labels, up to a maximum of 64. * Each label must be a key-value pair. * Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters. * Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed. * The key portion of a label must be unique. However, you can use the same key with multiple resources. * Keys must start with a lowercase letter or international character. See [Google Cloud Document](https://cloud.google.com/resource-manager/docs/creating-managing-labels#requirements) for more details.
"a_key": "A String",
},
"userPseudoId": "A String", # A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website. This field should NOT have a fixed value such as `unknown_visitor`. This should be the same identifier as UserEvent.user_pseudo_id and CompleteQueryRequest.user_pseudo_id The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
}
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 SearchService.Search method.
"attributionToken": "A String", # A unique search token. This should be included in the UserEvent logs resulting from this search, which enables accurate attribution of search model performance. This also helps to identify a request during the customer support scenarios.
"correctedQuery": "A String", # Contains the spell corrected query, if found. If the spell correction type is AUTOMATIC, then the search results are based on corrected_query. Otherwise the original query is used for search.
"facets": [ # Results of facets requested by user.
{ # A facet result.
"dynamicFacet": True or False, # Whether the facet is dynamically generated.
"key": "A String", # The key for this facet. For example, `"colors"` or `"price"`. It matches SearchRequest.FacetSpec.FacetKey.key.
"values": [ # The facet values for this field.
{ # A facet value which contains value names and their count.
"count": "A String", # Number of items that have this facet value.
"interval": { # A floating point interval. # Interval value for a facet, such as 10, 20) for facet "price". It matches [SearchRequest.FacetSpec.FacetKey.intervals.
"exclusiveMaximum": 3.14, # Exclusive upper bound.
"exclusiveMinimum": 3.14, # Exclusive lower bound.
"maximum": 3.14, # Inclusive upper bound.
"minimum": 3.14, # Inclusive lower bound.
},
"value": "A String", # Text value of a facet, such as "Black" for facet "colors".
},
],
},
],
"nextPageToken": "A String", # A token that can be sent as SearchRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.
"queryExpansionInfo": { # Information describing query expansion including whether expansion has occurred. # Query expansion information for the returned results.
"expandedQuery": True or False, # Bool describing whether query expansion has occurred.
"pinnedResultCount": "A String", # Number of pinned results. This field will only be set when expansion happens and SearchRequest.QueryExpansionSpec.pin_unexpanded_results is set to true.
},
"redirectUri": "A String", # The URI of a customer-defined redirect page. If redirect action is triggered, no search is performed, and only redirect_uri and attribution_token are set in the response.
"results": [ # A list of matched documents. The order represents the ranking.
{ # Represents the search results.
"chunk": { # Chunk captures all raw metadata information of items to be recommended or searched in the chunk mode. # The chunk data in the search response if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.
"chunkMetadata": { # Metadata of the current chunk. This field is only populated on SearchService.Search API. # Output only. Metadata of the current chunk.
"nextChunks": [ # The next chunks of the current chunk. The number is controlled by SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks. This field is only populated on SearchService.Search API.
# Object with schema name: GoogleCloudDiscoveryengineV1Chunk
],
"previousChunks": [ # The previous chunks of the current chunk. The number is controlled by SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks. This field is only populated on SearchService.Search API.
# Object with schema name: GoogleCloudDiscoveryengineV1Chunk
],
},
"content": "A String", # Content is a string from a document (parsed content).
"derivedStructData": { # Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.
"a_key": "", # Properties of the object.
},
"documentMetadata": { # Document metadata contains the information of the document of the current chunk. # Metadata of the document from the current chunk.
"structData": { # Data representation. The structured JSON data for the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"a_key": "", # Properties of the object.
},
"title": "A String", # Title of the document.
"uri": "A String", # Uri of the document.
},
"id": "A String", # Unique chunk ID of the current chunk.
"name": "A String", # The full resource name of the chunk. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}/chunks/{chunk_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"pageSpan": { # Page span of the chunk. # Page span of the chunk.
"pageEnd": 42, # The end page of the chunk.
"pageStart": 42, # The start page of the chunk.
},
"relevanceScore": 3.14, # Output only. Represents the relevance score based on similarity. Higher score indicates higher chunk relevance. The score is in range [-1.0, 1.0]. Only populated on SearchService.SearchResponse.
},
"document": { # Document captures all raw metadata information of items to be recommended or searched. # The document data snippet in the search response. Only fields that are marked as `retrievable` are populated.
"content": { # Unstructured data linked to this document. # The unstructured data linked to this document. Content must be set if this document is under a `CONTENT_REQUIRED` data store.
"mimeType": "A String", # The MIME type of the content. Supported types: * `application/pdf` (PDF, only native PDFs are supported for now) * `text/html` (HTML) * `application/vnd.openxmlformats-officedocument.wordprocessingml.document` (DOCX) * `application/vnd.openxmlformats-officedocument.presentationml.presentation` (PPTX) * `text/plain` (TXT) See https://www.iana.org/assignments/media-types/media-types.xhtml.
"rawBytes": "A String", # The content represented as a stream of bytes. The maximum length is 1,000,000 bytes (1 MB / ~0.95 MiB). Note: As with all `bytes` fields, this field is represented as pure binary in Protocol Buffers and base64-encoded string in JSON. For example, `abc123!?$*&()'-=@~` should be represented as `YWJjMTIzIT8kKiYoKSctPUB+` in JSON. See https://developers.google.com/protocol-buffers/docs/proto3#json.
"uri": "A String", # The URI of the content. Only Cloud Storage URIs (e.g. `gs://bucket-name/path/to/file`) are supported. The maximum file size is 2.5 MB for text-based formats, 200 MB for other formats.
},
"derivedStructData": { # Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.
"a_key": "", # Properties of the object.
},
"id": "A String", # Immutable. The identifier of the document. Id should conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters.
"indexStatus": { # Index status of the document. # Output only. The index status of the document. * If document is indexed successfully, the index_time field is populated. * Otherwise, if document is not indexed due to errors, the error_samples field is populated. * Otherwise, index_status is unset.
"errorSamples": [ # A sample of errors encountered while indexing the document. If this field is populated, the document is not indexed due to errors.
{ # 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).
"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.
},
],
"indexTime": "A String", # The time when the document was indexed. If this field is populated, it means the document has been indexed.
},
"indexTime": "A String", # Output only. The last time the document was indexed. If this field is set, the document could be returned in search results. This field is OUTPUT_ONLY. If this field is not populated, it means the document has never been indexed.
"jsonData": "A String", # The JSON string representation of the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"name": "A String", # Immutable. The full resource name of the document. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"parentDocumentId": "A String", # The identifier of the parent document. Currently supports at most two level document hierarchy. Id should conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters.
"schemaId": "A String", # The identifier of the schema located in the same data store.
"structData": { # The structured JSON data for the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"a_key": "", # Properties of the object.
},
},
"id": "A String", # Document.id of the searched Document.
},
],
"sessionInfo": { # Information about the session. # Session information. Only set if SearchRequest.session is provided. See its description for more details.
"name": "A String", # Name of the session. If the auto-session mode is used (when SearchRequest.session ends with "-"), this field holds the newly generated session name.
"queryId": "A String", # Query ID that corresponds to this search API call. One session can have multiple turns, each with a unique query ID. By specifying the session name and this query ID in the Answer API call, the answer generation happens in the context of the search results from this search call.
},
"summary": { # Summary of the top N search results specified by the summary spec. # A summary as part of the search results. This field is only returned if SearchRequest.ContentSearchSpec.summary_spec is set.
"safetyAttributes": { # Safety Attribute categories and their associated confidence scores. # A collection of Safety Attribute categories and their associated confidence scores.
"categories": [ # The display names of Safety Attribute categories associated with the generated content. Order matches the Scores.
"A String",
],
"scores": [ # The confidence scores of the each category, higher value means higher confidence. Order matches the Categories.
3.14,
],
},
"summarySkippedReasons": [ # Additional summary-skipped reasons. This provides the reason for ignored cases. If nothing is skipped, this field is not set.
"A String",
],
"summaryText": "A String", # The summary content.
"summaryWithMetadata": { # Summary with metadata information. # Summary with metadata information.
"citationMetadata": { # Citation metadata. # Citation metadata for given summary.
"citations": [ # Citations for segments.
{ # Citation info for a segment.
"endIndex": "A String", # End of the attributed segment, exclusive.
"sources": [ # Citation sources for the attributed segment.
{ # Citation source.
"referenceIndex": "A String", # Document reference index from SummaryWithMetadata.references. It is 0-indexed and the value will be zero if the reference_index is not set explicitly.
},
],
"startIndex": "A String", # Index indicates the start of the segment, measured in bytes/unicode.
},
],
},
"references": [ # Document References.
{ # Document reference.
"chunkContents": [ # List of cited chunk contents derived from document content.
{ # Chunk content.
"content": "A String", # Chunk textual content.
"pageIdentifier": "A String", # Page identifier.
},
],
"document": "A String", # Required. Document.name of the document. Full resource name of the referenced document, in the format `projects/*/locations/*/collections/*/dataStores/*/branches/*/documents/*`.
"title": "A String", # Title of the document.
"uri": "A String", # Cloud Storage or HTTP uri for the document.
},
],
"summary": "A String", # Summary text with no citation information.
},
},
"totalSize": 42, # The estimated total count of matched items irrespective of pagination. The count of results returned by pagination may be less than the total_size that matches.
}
searchLite(servingConfig, body=None, x__xgafv=None)
Performs a search. Similar to the SearchService.Search method, but a lite version that allows API key for authentication, where OAuth and IAM checks are not required. Only public website search is supported by this method. If data stores and engines not associated with public website search are specified, a `FAILED_PRECONDITION` error is returned. This method can be used for easy onboarding without having to implement an authentication backend. However, it is strongly recommended to use SearchService.Search instead with required OAuth and IAM checks to provide better data security.
Args:
servingConfig: string, Required. The resource name of the Search serving config, such as `projects/*/locations/global/collections/default_collection/engines/*/servingConfigs/default_serving_config`, or `projects/*/locations/global/collections/default_collection/dataStores/default_data_store/servingConfigs/default_serving_config`. This field is used to identify the serving configuration name, set of models used to make the search. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for SearchService.Search method.
"boostSpec": { # Boost specification to boost certain documents. # Boost specification to boost certain documents. For more information on boosting, see [Boosting](https://cloud.google.com/generative-ai-app-builder/docs/boost-search-results)
"conditionBoostSpecs": [ # 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, # 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. Only one of the (condition, boost) combination or the boost_control_spec below are set. If both are set then the global boost is ignored and the more fine-grained boost_control_spec is applied.
"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. # Complex specification for custom ranking based on customer defined attribute value.
"attributeType": "A String", # 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": [ # 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", # 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, # 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", # The name of the field whose value will be used to determine the boost amount.
"interpolationType": "A String", # The interpolation type to be applied to connect the control points listed below.
},
"condition": "A String", # An expression which specifies a boost condition. The syntax and supported fields are the same as a filter expression. See SearchRequest.filter for detail syntax and limitations. Examples: * To boost documents with document ID "doc_1" or "doc_2", and color "Red" or "Blue": `(document_id: ANY("doc_1", "doc_2")) AND (color: ANY("Red", "Blue"))`
},
],
},
"branch": "A String", # The branch resource name, such as `projects/*/locations/global/collections/default_collection/dataStores/default_data_store/branches/0`. Use `default_branch` as the branch ID or leave this field empty, to search documents under the default branch.
"canonicalFilter": "A String", # The default filter that is applied when a user performs a search without checking any filters on the search page. The filter applied to every search request when quality improvement such as query expansion is needed. In the case a query does not have a sufficient amount of results this filter will be used to determine whether or not to enable the query expansion flow. The original filter will still be used for the query expanded search. This field is strongly recommended to achieve high search quality. For more information about filter syntax, see SearchRequest.filter.
"contentSearchSpec": { # A specification for configuring the behavior of content search. # A specification for configuring the behavior of content search.
"chunkSpec": { # Specifies the chunk spec to be returned from the search response. Only available if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS # Specifies the chunk spec to be returned from the search response. Only available if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS
"numNextChunks": 42, # The number of next chunks to be returned of the current chunk. The maximum allowed value is 3. If not specified, no next chunks will be returned.
"numPreviousChunks": 42, # The number of previous chunks to be returned of the current chunk. The maximum allowed value is 3. If not specified, no previous chunks will be returned.
},
"extractiveContentSpec": { # A specification for configuring the extractive content in a search response. # If there is no extractive_content_spec provided, there will be no extractive answer in the search response.
"maxExtractiveAnswerCount": 42, # The maximum number of extractive answers returned in each search result. An extractive answer is a verbatim answer extracted from the original document, which provides a precise and contextually relevant answer to the search query. If the number of matching answers is less than the `max_extractive_answer_count`, return all of the answers. Otherwise, return the `max_extractive_answer_count`. At most five answers are returned for each SearchResult.
"maxExtractiveSegmentCount": 42, # The max number of extractive segments returned in each search result. Only applied if the DataStore is set to DataStore.ContentConfig.CONTENT_REQUIRED or DataStore.solution_types is SOLUTION_TYPE_CHAT. An extractive segment is a text segment extracted from the original document that is relevant to the search query, and, in general, more verbose than an extractive answer. The segment could then be used as input for LLMs to generate summaries and answers. If the number of matching segments is less than `max_extractive_segment_count`, return all of the segments. Otherwise, return the `max_extractive_segment_count`.
"numNextSegments": 42, # Return at most `num_next_segments` segments after each selected segments.
"numPreviousSegments": 42, # Specifies whether to also include the adjacent from each selected segments. Return at most `num_previous_segments` segments before each selected segments.
"returnExtractiveSegmentScore": True or False, # Specifies whether to return the confidence score from the extractive segments in each search result. This feature is available only for new or allowlisted data stores. To allowlist your data store, contact your Customer Engineer. The default value is `false`.
},
"searchResultMode": "A String", # Specifies the search result mode. If unspecified, the search result mode defaults to `DOCUMENTS`.
"snippetSpec": { # A specification for configuring snippets in a search response. # If `snippetSpec` is not specified, snippets are not included in the search response.
"maxSnippetCount": 42, # [DEPRECATED] This field is deprecated. To control snippet return, use `return_snippet` field. For backwards compatibility, we will return snippet if max_snippet_count > 0.
"referenceOnly": True or False, # [DEPRECATED] This field is deprecated and will have no affect on the snippet.
"returnSnippet": True or False, # If `true`, then return snippet. If no snippet can be generated, we return "No snippet is available for this page." A `snippet_status` with `SUCCESS` or `NO_SNIPPET_AVAILABLE` will also be returned.
},
"summarySpec": { # A specification for configuring a summary returned in a search response. # If `summarySpec` is not specified, summaries are not included in the search response.
"ignoreAdversarialQuery": True or False, # Specifies whether to filter out adversarial queries. The default value is `false`. Google employs search-query classification to detect adversarial queries. No summary is returned if the search query is classified as an adversarial query. For example, a user might ask a question regarding negative comments about the company or submit a query designed to generate unsafe, policy-violating output. If this field is set to `true`, we skip generating summaries for adversarial queries and return fallback messages instead.
"ignoreJailBreakingQuery": True or False, # Optional. Specifies whether to filter out jail-breaking queries. The default value is `false`. Google employs search-query classification to detect jail-breaking queries. No summary is returned if the search query is classified as a jail-breaking query. A user might add instructions to the query to change the tone, style, language, content of the answer, or ask the model to act as a different entity, e.g. "Reply in the tone of a competing company's CEO". If this field is set to `true`, we skip generating summaries for jail-breaking queries and return fallback messages instead.
"ignoreLowRelevantContent": True or False, # Specifies whether to filter out queries that have low relevance. The default value is `false`. If this field is set to `false`, all search results are used regardless of relevance to generate answers. If set to `true`, only queries with high relevance search results will generate answers.
"ignoreNonSummarySeekingQuery": True or False, # Specifies whether to filter out queries that are not summary-seeking. The default value is `false`. Google employs search-query classification to detect summary-seeking queries. No summary is returned if the search query is classified as a non-summary seeking query. For example, `why is the sky blue` and `Who is the best soccer player in the world?` are summary-seeking queries, but `SFO airport` and `world cup 2026` are not. They are most likely navigational queries. If this field is set to `true`, we skip generating summaries for non-summary seeking queries and return fallback messages instead.
"includeCitations": True or False, # Specifies whether to include citations in the summary. The default value is `false`. When this field is set to `true`, summaries include in-line citation numbers. Example summary including citations: BigQuery is Google Cloud's fully managed and completely serverless enterprise data warehouse [1]. BigQuery supports all data types, works across clouds, and has built-in machine learning and business intelligence, all within a unified platform [2, 3]. The citation numbers refer to the returned search results and are 1-indexed. For example, [1] means that the sentence is attributed to the first search result. [2, 3] means that the sentence is attributed to both the second and third search results.
"languageCode": "A String", # Language code for Summary. Use language tags defined by [BCP47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt). Note: This is an experimental feature.
"modelPromptSpec": { # Specification of the prompt to use with the model. # If specified, the spec will be used to modify the prompt provided to the LLM.
"preamble": "A String", # Text at the beginning of the prompt that instructs the assistant. Examples are available in the user guide.
},
"modelSpec": { # Specification of the model. # If specified, the spec will be used to modify the model specification provided to the LLM.
"version": "A String", # The model version used to generate the summary. Supported values are: * `stable`: string. Default value when no value is specified. Uses a generally available, fine-tuned model. For more information, see [Answer generation model versions and lifecycle](https://cloud.google.com/generative-ai-app-builder/docs/answer-generation-models). * `preview`: string. (Public preview) Uses a preview model. For more information, see [Answer generation model versions and lifecycle](https://cloud.google.com/generative-ai-app-builder/docs/answer-generation-models).
},
"summaryResultCount": 42, # The number of top results to generate the summary from. If the number of results returned is less than `summaryResultCount`, the summary is generated from all of the results. At most 10 results for documents mode, or 50 for chunks mode, can be used to generate a summary. The chunks mode is used when SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.
"useSemanticChunks": True or False, # If true, answer will be generated from most relevant chunks from top search results. This feature will improve summary quality. Note that with this feature enabled, not all top search results will be referenced and included in the reference list, so the citation source index only points to the search results listed in the reference list.
},
},
"dataStoreSpecs": [ # Specs defining dataStores to filter on in a search call and configurations for those dataStores. This is only considered for engines with multiple dataStores use case. For single dataStore within an engine, they should use the specs at the top level.
{ # A struct to define data stores to filter on in a search call and configurations for those data stores. Otherwise, an `INVALID_ARGUMENT` error is returned.
"dataStore": "A String", # Required. Full resource name of DataStore, such as `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`.
"filter": "A String", # Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
},
],
"facetSpecs": [ # Facet specifications for faceted search. If empty, no facets are returned. A maximum of 100 values are allowed. Otherwise, an `INVALID_ARGUMENT` error is returned.
{ # A facet specification to perform faceted search.
"enableDynamicPosition": True or False, # Enables dynamic position for this facet. If set to true, the position of this facet among all facets in the response is determined automatically. If dynamic facets are enabled, it is ordered together. If set to false, the position of this facet in the response is the same as in the request, and it is ranked before the facets with dynamic position enable and all dynamic facets. For example, you may always want to have rating facet returned in the response, but it's not necessarily to always display the rating facet at the top. In that case, you can set enable_dynamic_position to true so that the position of rating facet in response is determined automatically. Another example, assuming you have the following facets in the request: * "rating", enable_dynamic_position = true * "price", enable_dynamic_position = false * "brands", enable_dynamic_position = false And also you have a dynamic facets enabled, which generates a facet `gender`. Then the final order of the facets in the response can be ("price", "brands", "rating", "gender") or ("price", "brands", "gender", "rating") depends on how API orders "gender" and "rating" facets. However, notice that "price" and "brands" are always ranked at first and second position because their enable_dynamic_position is false.
"excludedFilterKeys": [ # List of keys to exclude when faceting. By default, FacetKey.key is not excluded from the filter unless it is listed in this field. Listing a facet key in this field allows its values to appear as facet results, even when they are filtered out of search results. Using this field does not affect what search results are returned. For example, suppose there are 100 documents with the color facet "Red" and 200 documents with the color facet "Blue". A query containing the filter "color:ANY("Red")" and having "color" as FacetKey.key would by default return only "Red" documents in the search results, and also return "Red" with count 100 as the only color facet. Although there are also blue documents available, "Blue" would not be shown as an available facet value. If "color" is listed in "excludedFilterKeys", then the query returns the facet values "Red" with count 100 and "Blue" with count 200, because the "color" key is now excluded from the filter. Because this field doesn't affect search results, the search results are still correctly filtered to return only "Red" documents. A maximum of 100 values are allowed. Otherwise, an `INVALID_ARGUMENT` error is returned.
"A String",
],
"facetKey": { # Specifies how a facet is computed. # Required. The facet key specification.
"caseInsensitive": True or False, # True to make facet keys case insensitive when getting faceting values with prefixes or contains; false otherwise.
"contains": [ # Only get facet values that contain the given strings. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "contains" to "2022", the "category" facet only contains "Action > 2022" and "Sci-Fi > 2022". Only supported on textual fields. Maximum is 10.
"A String",
],
"intervals": [ # Set only if values should be bucketed into intervals. Must be set for facets with numerical values. Must not be set for facet with text values. Maximum number of intervals is 30.
{ # A floating point interval.
"exclusiveMaximum": 3.14, # Exclusive upper bound.
"exclusiveMinimum": 3.14, # Exclusive lower bound.
"maximum": 3.14, # Inclusive upper bound.
"minimum": 3.14, # Inclusive lower bound.
},
],
"key": "A String", # Required. Supported textual and numerical facet keys in Document object, over which the facet values are computed. Facet key is case-sensitive.
"orderBy": "A String", # The order in which documents are returned. Allowed values are: * "count desc", which means order by SearchResponse.Facet.values.count descending. * "value desc", which means order by SearchResponse.Facet.values.value descending. Only applies to textual facets. If not set, textual values are sorted in [natural order](https://en.wikipedia.org/wiki/Natural_sort_order); numerical intervals are sorted in the order given by FacetSpec.FacetKey.intervals.
"prefixes": [ # Only get facet values that start with the given string prefix. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "prefixes" to "Action", the "category" facet only contains "Action > 2022" and "Action > 2021". Only supported on textual fields. Maximum is 10.
"A String",
],
"restrictedValues": [ # Only get facet for the given restricted values. Only supported on textual fields. For example, suppose "category" has three values "Action > 2022", "Action > 2021" and "Sci-Fi > 2022". If set "restricted_values" to "Action > 2022", the "category" facet only contains "Action > 2022". Only supported on textual fields. Maximum is 10.
"A String",
],
},
"limit": 42, # Maximum facet values that are returned for this facet. If unspecified, defaults to 20. The maximum allowed value is 300. Values above 300 are coerced to 300. For aggregation in healthcare search, when the [FacetKey.key] is "healthcare_aggregation_key", the limit will be overridden to 10,000 internally, regardless of the value set here. If this field is negative, an `INVALID_ARGUMENT` is returned.
},
],
"filter": "A String", # The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive. If this field is unrecognizable, an `INVALID_ARGUMENT` is returned. Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customer might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")' For more information about filtering including syntax and filter operators, see [Filter](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata)
"imageQuery": { # Specifies the image query input. # Raw image query.
"imageBytes": "A String", # Base64 encoded image bytes. Supported image formats: JPEG, PNG, and BMP.
},
"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see [Standard fields](https://cloud.google.com/apis/design/standard_fields). This field helps to better interpret the query. If a value isn't specified, the query language code is automatically detected, which may not be accurate.
"offset": 42, # A 0-indexed integer that specifies the current offset (that is, starting result location, amongst the Documents deemed by the API as relevant) in search results. This field is only considered if page_token is unset. If this field is negative, an `INVALID_ARGUMENT` is returned.
"oneBoxPageSize": 42, # The maximum number of results to return for OneBox. This applies to each OneBox type individually. Default number is 10.
"orderBy": "A String", # The order in which documents are returned. Documents can be ordered by a field in an Document object. Leave it unset if ordered by relevance. `order_by` expression is case-sensitive. For more information on ordering the website search results, see [Order web search results](https://cloud.google.com/generative-ai-app-builder/docs/order-web-search-results). For more information on ordering the healthcare search results, see [Order healthcare search results](https://cloud.google.com/generative-ai-app-builder/docs/order-hc-results). If this field is unrecognizable, an `INVALID_ARGUMENT` is returned.
"pageSize": 42, # Maximum number of Documents to return. The maximum allowed value depends on the data type. Values above the maximum value are coerced to the maximum value. * Websites with basic indexing: Default `10`, Maximum `25`. * Websites with advanced indexing: Default `25`, Maximum `50`. * Other: Default `50`, Maximum `100`. If this field is negative, an `INVALID_ARGUMENT` is returned.
"pageToken": "A String", # A page token received from a previous SearchService.Search call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to SearchService.Search must match the call that provided the page token. Otherwise, an `INVALID_ARGUMENT` error is returned.
"params": { # Additional search parameters. For public website search only, supported values are: * `user_country_code`: string. Default empty. If set to non-empty, results are restricted or boosted based on the location provided. For example, `user_country_code: "au"` For available codes see [Country Codes](https://developers.google.com/custom-search/docs/json_api_reference#countryCodes) * `search_type`: double. Default empty. Enables non-webpage searching depending on the value. The only valid non-default value is 1, which enables image searching. For example, `search_type: 1`
"a_key": "",
},
"query": "A String", # Raw search query.
"queryExpansionSpec": { # Specification to determine under which conditions query expansion should occur. # The query expansion specification that specifies the conditions under which query expansion occurs.
"condition": "A String", # The condition under which query expansion should occur. Default to Condition.DISABLED.
"pinUnexpandedResults": True or False, # Whether to pin unexpanded results. If this field is set to true, unexpanded products are always at the top of the search results, followed by the expanded results.
},
"safeSearch": True or False, # Whether to turn on safe search. This is only supported for website search.
"searchAsYouTypeSpec": { # Specification for search as you type in search requests. # Search as you type configuration. Only supported for the IndustryVertical.MEDIA vertical.
"condition": "A String", # The condition under which search as you type should occur. Default to Condition.DISABLED.
},
"session": "A String", # The session resource name. Optional. Session allows users to do multi-turn /search API calls or coordination between /search API calls and /answer API calls. Example #1 (multi-turn /search API calls): 1. Call /search API with the auto-session mode (see below). 2. Call /search API with the session ID generated in the first call. Here, the previous search query gets considered in query standing. I.e., if the first query is "How did Alphabet do in 2022?" and the current query is "How about 2023?", the current query will be interpreted as "How did Alphabet do in 2023?". Example #2 (coordination between /search API calls and /answer API calls): 1. Call /search API with the auto-session mode (see below). 2. Call /answer API with the session ID generated in the first call. Here, the answer generation happens in the context of the search results from the first search call. Auto-session mode: when `projects/.../sessions/-` is used, a new session gets automatically created. Otherwise, users can use the create-session API to create a session manually. Multi-turn Search feature is currently at private GA stage. Please use v1alpha or v1beta version instead before we launch this feature to public GA. Or ask for allowlisting through Google Support team.
"sessionSpec": { # Session specification. Multi-turn Search feature is currently at private GA stage. Please use v1alpha or v1beta version instead before we launch this feature to public GA. Or ask for allowlisting through Google Support team. # Session specification. Can be used only when `session` is set.
"queryId": "A String", # If set, the search result gets stored to the "turn" specified by this query ID. Example: Let's say the session looks like this: session { name: ".../sessions/xxx" turns { query { text: "What is foo?" query_id: ".../questions/yyy" } answer: "Foo is ..." } turns { query { text: "How about bar then?" query_id: ".../questions/zzz" } } } The user can call /search API with a request like this: session: ".../sessions/xxx" session_spec { query_id: ".../questions/zzz" } Then, the API stores the search result, associated with the last turn. The stored search result can be used by a subsequent /answer API call (with the session ID and the query ID specified). Also, it is possible to call /search and /answer in parallel with the same session ID & query ID.
"searchResultPersistenceCount": 42, # The number of top search results to persist. The persisted search results can be used for the subsequent /answer api call. This field is simliar to the `summary_result_count` field in SearchRequest.ContentSearchSpec.SummarySpec.summary_result_count. At most 10 results for documents mode, or 50 for chunks mode.
},
"spellCorrectionSpec": { # The specification for query spell correction. # The spell correction specification that specifies the mode under which spell correction takes effect.
"mode": "A String", # The mode under which spell correction replaces the original search query. Defaults to Mode.AUTO.
},
"userInfo": { # Information of an end user. # Information about the end user. Highly recommended for analytics. UserInfo.user_agent is used to deduce `device_type` for analytics.
"userAgent": "A String", # User agent as included in the HTTP header. The field must be a UTF-8 encoded string with a length limit of 1,000 characters. Otherwise, an `INVALID_ARGUMENT` error is returned. This should not be set when using the client side event reporting with GTM or JavaScript tag in UserEventService.CollectUserEvent or if UserEvent.direct_user_request is set.
"userId": "A String", # Highly recommended for logged-in users. Unique identifier for logged-in user, such as a user name. Don't set for anonymous users. Always use a hashed value for this ID. Don't set the field to the same fixed ID for different users. This mixes the event history of those users together, which results in degraded model quality. The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
},
"userLabels": { # The user labels applied to a resource must meet the following requirements: * Each resource can have multiple labels, up to a maximum of 64. * Each label must be a key-value pair. * Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters. * Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed. * The key portion of a label must be unique. However, you can use the same key with multiple resources. * Keys must start with a lowercase letter or international character. See [Google Cloud Document](https://cloud.google.com/resource-manager/docs/creating-managing-labels#requirements) for more details.
"a_key": "A String",
},
"userPseudoId": "A String", # A unique identifier for tracking visitors. For example, this could be implemented with an HTTP cookie, which should be able to uniquely identify a visitor on a single device. This unique identifier should not change if the visitor logs in or out of the website. This field should NOT have a fixed value such as `unknown_visitor`. This should be the same identifier as UserEvent.user_pseudo_id and CompleteQueryRequest.user_pseudo_id The field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an `INVALID_ARGUMENT` error is returned.
}
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 SearchService.Search method.
"attributionToken": "A String", # A unique search token. This should be included in the UserEvent logs resulting from this search, which enables accurate attribution of search model performance. This also helps to identify a request during the customer support scenarios.
"correctedQuery": "A String", # Contains the spell corrected query, if found. If the spell correction type is AUTOMATIC, then the search results are based on corrected_query. Otherwise the original query is used for search.
"facets": [ # Results of facets requested by user.
{ # A facet result.
"dynamicFacet": True or False, # Whether the facet is dynamically generated.
"key": "A String", # The key for this facet. For example, `"colors"` or `"price"`. It matches SearchRequest.FacetSpec.FacetKey.key.
"values": [ # The facet values for this field.
{ # A facet value which contains value names and their count.
"count": "A String", # Number of items that have this facet value.
"interval": { # A floating point interval. # Interval value for a facet, such as 10, 20) for facet "price". It matches [SearchRequest.FacetSpec.FacetKey.intervals.
"exclusiveMaximum": 3.14, # Exclusive upper bound.
"exclusiveMinimum": 3.14, # Exclusive lower bound.
"maximum": 3.14, # Inclusive upper bound.
"minimum": 3.14, # Inclusive lower bound.
},
"value": "A String", # Text value of a facet, such as "Black" for facet "colors".
},
],
},
],
"nextPageToken": "A String", # A token that can be sent as SearchRequest.page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.
"queryExpansionInfo": { # Information describing query expansion including whether expansion has occurred. # Query expansion information for the returned results.
"expandedQuery": True or False, # Bool describing whether query expansion has occurred.
"pinnedResultCount": "A String", # Number of pinned results. This field will only be set when expansion happens and SearchRequest.QueryExpansionSpec.pin_unexpanded_results is set to true.
},
"redirectUri": "A String", # The URI of a customer-defined redirect page. If redirect action is triggered, no search is performed, and only redirect_uri and attribution_token are set in the response.
"results": [ # A list of matched documents. The order represents the ranking.
{ # Represents the search results.
"chunk": { # Chunk captures all raw metadata information of items to be recommended or searched in the chunk mode. # The chunk data in the search response if the SearchRequest.ContentSearchSpec.search_result_mode is set to CHUNKS.
"chunkMetadata": { # Metadata of the current chunk. This field is only populated on SearchService.Search API. # Output only. Metadata of the current chunk.
"nextChunks": [ # The next chunks of the current chunk. The number is controlled by SearchRequest.ContentSearchSpec.ChunkSpec.num_next_chunks. This field is only populated on SearchService.Search API.
# Object with schema name: GoogleCloudDiscoveryengineV1Chunk
],
"previousChunks": [ # The previous chunks of the current chunk. The number is controlled by SearchRequest.ContentSearchSpec.ChunkSpec.num_previous_chunks. This field is only populated on SearchService.Search API.
# Object with schema name: GoogleCloudDiscoveryengineV1Chunk
],
},
"content": "A String", # Content is a string from a document (parsed content).
"derivedStructData": { # Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.
"a_key": "", # Properties of the object.
},
"documentMetadata": { # Document metadata contains the information of the document of the current chunk. # Metadata of the document from the current chunk.
"structData": { # Data representation. The structured JSON data for the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"a_key": "", # Properties of the object.
},
"title": "A String", # Title of the document.
"uri": "A String", # Uri of the document.
},
"id": "A String", # Unique chunk ID of the current chunk.
"name": "A String", # The full resource name of the chunk. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}/chunks/{chunk_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"pageSpan": { # Page span of the chunk. # Page span of the chunk.
"pageEnd": 42, # The end page of the chunk.
"pageStart": 42, # The start page of the chunk.
},
"relevanceScore": 3.14, # Output only. Represents the relevance score based on similarity. Higher score indicates higher chunk relevance. The score is in range [-1.0, 1.0]. Only populated on SearchService.SearchResponse.
},
"document": { # Document captures all raw metadata information of items to be recommended or searched. # The document data snippet in the search response. Only fields that are marked as `retrievable` are populated.
"content": { # Unstructured data linked to this document. # The unstructured data linked to this document. Content must be set if this document is under a `CONTENT_REQUIRED` data store.
"mimeType": "A String", # The MIME type of the content. Supported types: * `application/pdf` (PDF, only native PDFs are supported for now) * `text/html` (HTML) * `application/vnd.openxmlformats-officedocument.wordprocessingml.document` (DOCX) * `application/vnd.openxmlformats-officedocument.presentationml.presentation` (PPTX) * `text/plain` (TXT) See https://www.iana.org/assignments/media-types/media-types.xhtml.
"rawBytes": "A String", # The content represented as a stream of bytes. The maximum length is 1,000,000 bytes (1 MB / ~0.95 MiB). Note: As with all `bytes` fields, this field is represented as pure binary in Protocol Buffers and base64-encoded string in JSON. For example, `abc123!?$*&()'-=@~` should be represented as `YWJjMTIzIT8kKiYoKSctPUB+` in JSON. See https://developers.google.com/protocol-buffers/docs/proto3#json.
"uri": "A String", # The URI of the content. Only Cloud Storage URIs (e.g. `gs://bucket-name/path/to/file`) are supported. The maximum file size is 2.5 MB for text-based formats, 200 MB for other formats.
},
"derivedStructData": { # Output only. This field is OUTPUT_ONLY. It contains derived data that are not in the original input document.
"a_key": "", # Properties of the object.
},
"id": "A String", # Immutable. The identifier of the document. Id should conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters.
"indexStatus": { # Index status of the document. # Output only. The index status of the document. * If document is indexed successfully, the index_time field is populated. * Otherwise, if document is not indexed due to errors, the error_samples field is populated. * Otherwise, index_status is unset.
"errorSamples": [ # A sample of errors encountered while indexing the document. If this field is populated, the document is not indexed due to errors.
{ # 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).
"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.
},
],
"indexTime": "A String", # The time when the document was indexed. If this field is populated, it means the document has been indexed.
},
"indexTime": "A String", # Output only. The last time the document was indexed. If this field is set, the document could be returned in search results. This field is OUTPUT_ONLY. If this field is not populated, it means the document has never been indexed.
"jsonData": "A String", # The JSON string representation of the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"name": "A String", # Immutable. The full resource name of the document. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/branches/{branch}/documents/{document_id}`. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
"parentDocumentId": "A String", # The identifier of the parent document. Currently supports at most two level document hierarchy. Id should conform to [RFC-1034](https://tools.ietf.org/html/rfc1034) standard with a length limit of 63 characters.
"schemaId": "A String", # The identifier of the schema located in the same data store.
"structData": { # The structured JSON data for the document. It should conform to the registered Schema or an `INVALID_ARGUMENT` error is thrown.
"a_key": "", # Properties of the object.
},
},
"id": "A String", # Document.id of the searched Document.
},
],
"sessionInfo": { # Information about the session. # Session information. Only set if SearchRequest.session is provided. See its description for more details.
"name": "A String", # Name of the session. If the auto-session mode is used (when SearchRequest.session ends with "-"), this field holds the newly generated session name.
"queryId": "A String", # Query ID that corresponds to this search API call. One session can have multiple turns, each with a unique query ID. By specifying the session name and this query ID in the Answer API call, the answer generation happens in the context of the search results from this search call.
},
"summary": { # Summary of the top N search results specified by the summary spec. # A summary as part of the search results. This field is only returned if SearchRequest.ContentSearchSpec.summary_spec is set.
"safetyAttributes": { # Safety Attribute categories and their associated confidence scores. # A collection of Safety Attribute categories and their associated confidence scores.
"categories": [ # The display names of Safety Attribute categories associated with the generated content. Order matches the Scores.
"A String",
],
"scores": [ # The confidence scores of the each category, higher value means higher confidence. Order matches the Categories.
3.14,
],
},
"summarySkippedReasons": [ # Additional summary-skipped reasons. This provides the reason for ignored cases. If nothing is skipped, this field is not set.
"A String",
],
"summaryText": "A String", # The summary content.
"summaryWithMetadata": { # Summary with metadata information. # Summary with metadata information.
"citationMetadata": { # Citation metadata. # Citation metadata for given summary.
"citations": [ # Citations for segments.
{ # Citation info for a segment.
"endIndex": "A String", # End of the attributed segment, exclusive.
"sources": [ # Citation sources for the attributed segment.
{ # Citation source.
"referenceIndex": "A String", # Document reference index from SummaryWithMetadata.references. It is 0-indexed and the value will be zero if the reference_index is not set explicitly.
},
],
"startIndex": "A String", # Index indicates the start of the segment, measured in bytes/unicode.
},
],
},
"references": [ # Document References.
{ # Document reference.
"chunkContents": [ # List of cited chunk contents derived from document content.
{ # Chunk content.
"content": "A String", # Chunk textual content.
"pageIdentifier": "A String", # Page identifier.
},
],
"document": "A String", # Required. Document.name of the document. Full resource name of the referenced document, in the format `projects/*/locations/*/collections/*/dataStores/*/branches/*/documents/*`.
"title": "A String", # Title of the document.
"uri": "A String", # Cloud Storage or HTTP uri for the document.
},
],
"summary": "A String", # Summary text with no citation information.
},
},
"totalSize": 42, # The estimated total count of matched items irrespective of pagination. The count of results returned by pagination may be less than the total_size that matches.
}
searchLite_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.
search_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.