discoveryengine/v1beta/search_service.proto

// Copyright 2022 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

syntax = "proto3";

package google.cloud.discoveryengine.v1beta;

import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/cloud/discoveryengine/v1beta/common.proto";
import "google/cloud/discoveryengine/v1beta/document.proto";
import "google/protobuf/struct.proto";

option csharp_namespace = "Google.Cloud.DiscoveryEngine.V1Beta";
option go_package = "cloud.google.com/go/discoveryengine/apiv1beta/discoveryenginepb;discoveryenginepb";
option java_multiple_files = true;
option java_outer_classname = "SearchServiceProto";
option java_package = "com.google.cloud.discoveryengine.v1beta";
option objc_class_prefix = "DISCOVERYENGINE";
option php_namespace = "Google\\Cloud\\DiscoveryEngine\\V1beta";
option ruby_package = "Google::Cloud::DiscoveryEngine::V1beta";

// Service for search.
service SearchService {
  option (google.api.default_host) = "discoveryengine.googleapis.com";
  option (google.api.oauth_scopes) =
      "https://www.googleapis.com/auth/cloud-platform";

  // Performs a search.
  rpc Search(SearchRequest) returns (SearchResponse) {
    option (google.api.http) = {
      post: "/v1beta/{serving_config=projects/*/locations/*/dataStores/*/servingConfigs/*}:search"
      body: "*"
      additional_bindings {
        post: "/v1beta/{serving_config=projects/*/locations/*/collections/*/dataStores/*/servingConfigs/*}:search"
        body: "*"
      }
      additional_bindings {
        post: "/v1beta/{serving_config=projects/*/locations/*/collections/*/engines/*/servingConfigs/*}:search"
        body: "*"
      }
    };
  }
}

// Request message for
// [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
// method.
message SearchRequest {
  // Specifies the image query input.
  message ImageQuery {
    oneof image {
      // Base64 encoded image bytes. Supported image formats: JPEG, PNG, and
      // BMP.
      string image_bytes = 1;
    }
  }

  // A struct to define data stores to filter on in a search call.
  message DataStoreSpec {
    // Required. Full resource name of
    // [DataStore][google.cloud.discoveryengine.v1beta.DataStore], such as
    // `projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}`.
    string data_store = 1 [
      (google.api.field_behavior) = REQUIRED,
      (google.api.resource_reference) = {
        type: "discoveryengine.googleapis.com/DataStore"
      }
    ];
  }

  // A facet specification to perform faceted search.
  message FacetSpec {
    // Specifies how a facet is computed.
    message FacetKey {
      // Required. Supported textual and numerical facet keys in
      // [Document][google.cloud.discoveryengine.v1beta.Document] object, over
      // which the facet values are computed. Facet key is case-sensitive.
      string key = 1 [(google.api.field_behavior) = REQUIRED];

      // 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.
      repeated Interval intervals = 2;

      // 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.
      repeated string restricted_values = 3;

      // 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.
      repeated string prefixes = 4;

      // Only get facet values that contains 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.
      repeated string contains = 5;

      // True to make facet keys case insensitive when getting faceting
      // values with prefixes or contains; false otherwise.
      bool case_insensitive = 6;

      // The order in which documents are returned.
      //
      // Allowed values are:
      //
      // * "count desc", which means order by
      // [SearchResponse.Facet.values.count][google.cloud.discoveryengine.v1beta.SearchResponse.Facet.FacetValue.count]
      // descending.
      //
      // * "value desc", which means order by
      // [SearchResponse.Facet.values.value][google.cloud.discoveryengine.v1beta.SearchResponse.Facet.FacetValue.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][google.cloud.discoveryengine.v1beta.SearchRequest.FacetSpec.FacetKey.intervals].
      string order_by = 7;
    }

    // Required. The facet key specification.
    FacetKey facet_key = 1 [(google.api.field_behavior) = REQUIRED];

    // Maximum of facet values that should be returned for this facet. If
    // unspecified, defaults to 20. The maximum allowed value is 300. Values
    // above 300 are coerced to 300.
    //
    // If this field is negative, an  `INVALID_ARGUMENT`  is returned.
    int32 limit = 2;

    // List of keys to exclude when faceting.
    //
    //
    // By default,
    // [FacetKey.key][google.cloud.discoveryengine.v1beta.SearchRequest.FacetSpec.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][google.cloud.discoveryengine.v1beta.SearchRequest.FacetSpec.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.
    repeated string excluded_filter_keys = 3;

    // 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.
    bool enable_dynamic_position = 4;
  }

  // Boost specification to boost certain documents.
  message BoostSpec {
    // Boost applies to documents which match a condition.
    message ConditionBoostSpec {
      // Specification for custom ranking based on customer specified attribute
      // value. It provides more controls for customized ranking than the simple
      // (condition, boost) combination above.
      message BoostControlSpec {
        // 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).
        message ControlPoint {
          // 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: `[nD][T[nH][nM][nS]]`.
          string attribute_value = 1;

          // The value between -1 to 1 by which to boost the score if the
          // attribute_value evaluates to the value specified above.
          float boost_amount = 2;
        }

        // The attribute(or function) for which the custom ranking is to be
        // applied.
        enum AttributeType {
          // Unspecified AttributeType.
          ATTRIBUTE_TYPE_UNSPECIFIED = 0;

          // The value of the numerical field will be used to dynamically update
          // the boost amount. In this case, the attribute_value (the x value)
          // of the control point will be the actual value of the numerical
          // field for which the boost_amount is specified.
          NUMERICAL = 1;

          // For the freshness use case the attribute value will be the duration
          // between the current time and the date in the datetime field
          // specified. The value must be formatted as an XSD `dayTimeDuration`
          // value (a restricted subset of an ISO 8601 duration value). The
          // pattern for this is: `[nD][T[nH][nM][nS]]`.
          // E.g. `5D`, `3DT12H30M`, `T24H`.
          FRESHNESS = 2;
        }

        // The interpolation type to be applied. Default will be linear
        // (Piecewise Linear).
        enum InterpolationType {
          // Interpolation type is unspecified. In this case, it defaults to
          // Linear.
          INTERPOLATION_TYPE_UNSPECIFIED = 0;

          // Piecewise linear interpolation will be applied.
          LINEAR = 1;
        }

        // The name of the field whose value will be used to determine the
        // boost amount.
        string field_name = 1;

        // 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).
        AttributeType attribute_type = 2;

        // The interpolation type to be applied to connect the control points
        // listed below.
        InterpolationType interpolation_type = 3;

        // The control points used to define the curve. The monotonic function
        // (defined through the interpolation_type above) passes through the
        // control points listed here.
        repeated ControlPoint control_points = 4;
      }

      // An expression which specifies a boost condition. The syntax and
      // supported fields are the same as a filter expression. See
      // [SearchRequest.filter][google.cloud.discoveryengine.v1beta.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"))`
      string condition = 1;

      // 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.
      float boost = 2;

      // Complex specification for custom ranking based on customer defined
      // attribute value.
      BoostControlSpec boost_control_spec = 3;
    }

    // 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.
    repeated ConditionBoostSpec condition_boost_specs = 1;
  }

  // Specification to determine under which conditions query expansion should
  // occur.
  message QueryExpansionSpec {
    // Enum describing under which condition query expansion should occur.
    enum Condition {
      // Unspecified query expansion condition. In this case, server behavior
      // defaults to
      // [Condition.DISABLED][google.cloud.discoveryengine.v1beta.SearchRequest.QueryExpansionSpec.Condition.DISABLED].
      CONDITION_UNSPECIFIED = 0;

      // Disabled query expansion. Only the exact search query is used, even if
      // [SearchResponse.total_size][google.cloud.discoveryengine.v1beta.SearchResponse.total_size]
      // is zero.
      DISABLED = 1;

      // Automatic query expansion built by the Search API.
      AUTO = 2;
    }

    // The condition under which query expansion should occur. Default to
    // [Condition.DISABLED][google.cloud.discoveryengine.v1beta.SearchRequest.QueryExpansionSpec.Condition.DISABLED].
    Condition condition = 1;

    // 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.
    bool pin_unexpanded_results = 2;
  }

  // The specification for query spell correction.
  message SpellCorrectionSpec {
    // Enum describing under which mode spell correction should occur.
    enum Mode {
      // Unspecified spell correction mode. In this case, server behavior
      // defaults to
      // [Mode.AUTO][google.cloud.discoveryengine.v1beta.SearchRequest.SpellCorrectionSpec.Mode.AUTO].
      MODE_UNSPECIFIED = 0;

      // Search API will try to find a spell suggestion if there
      // is any and put in the
      // [SearchResponse.corrected_query][google.cloud.discoveryengine.v1beta.SearchResponse.corrected_query].
      // The spell suggestion will not be used as the search query.
      SUGGESTION_ONLY = 1;

      // Automatic spell correction built by the Search API. Search will
      // be based on the corrected query if found.
      AUTO = 2;
    }

    // The mode under which spell correction should take effect to
    // replace the original search query. Default to
    // [Mode.AUTO][google.cloud.discoveryengine.v1beta.SearchRequest.SpellCorrectionSpec.Mode.AUTO].
    Mode mode = 1;
  }

  // A specification for configuring the behavior of content search.
  message ContentSearchSpec {
    // A specification for configuring snippets in a search response.
    message SnippetSpec {
      // [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.
      int32 max_snippet_count = 1 [deprecated = true];

      // [DEPRECATED] This field is deprecated and will have no affect on the
      // snippet.
      bool reference_only = 2 [deprecated = true];

      // 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.
      bool return_snippet = 3;
    }

    // A specification for configuring a summary returned in a search
    // response.
    message SummarySpec {
      // Specification of the prompt to use with the model.
      message ModelPromptSpec {
        // Text at the beginning of the prompt that instructs the assistant.
        // Examples are available in the user guide.
        string preamble = 1;
      }

      // Specification of the model.
      message ModelSpec {
        // 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).
        string version = 1;
      }

      // 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 can be used to generate a summary.
      int32 summary_result_count = 1;

      // 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.
      bool include_citations = 2;

      // 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.
      bool ignore_adversarial_query = 3;

      // 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.
      bool ignore_non_summary_seeking_query = 4;

      // If specified, the spec will be used to modify the prompt provided to
      // the LLM.
      ModelPromptSpec model_prompt_spec = 5;

      // 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.
      string language_code = 6;

      // If specified, the spec will be used to modify the model specification
      // provided to the LLM.
      ModelSpec model_spec = 7;

      // 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.
      bool use_semantic_chunks = 8;
    }

    // A specification for configuring the extractive content in a search
    // response.
    message ExtractiveContentSpec {
      // 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][google.cloud.discoveryengine.v1beta.SearchResponse.SearchResult].
      int32 max_extractive_answer_count = 1;

      // The max number of extractive segments returned in each search result.
      // Only applied if the
      // [DataStore][google.cloud.discoveryengine.v1beta.DataStore] is set to
      // [DataStore.ContentConfig.CONTENT_REQUIRED][google.cloud.discoveryengine.v1beta.DataStore.ContentConfig.CONTENT_REQUIRED]
      // or
      // [DataStore.solution_types][google.cloud.discoveryengine.v1beta.DataStore.solution_types]
      // is
      // [SOLUTION_TYPE_CHAT][google.cloud.discoveryengine.v1beta.SolutionType.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`.
      int32 max_extractive_segment_count = 2;

      // 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`.
      bool return_extractive_segment_score = 3;

      // Specifies whether to also include the adjacent from each selected
      // segments.
      // Return at most `num_previous_segments` segments before each selected
      // segments.
      int32 num_previous_segments = 4;

      // Return at most `num_next_segments` segments after each selected
      // segments.
      int32 num_next_segments = 5;
    }

    // If `snippetSpec` is not specified, snippets are not included in the
    // search response.
    SnippetSpec snippet_spec = 1;

    // If `summarySpec` is not specified, summaries are not included in the
    // search response.
    SummarySpec summary_spec = 2;

    // If there is no extractive_content_spec provided, there will be no
    // extractive answer in the search response.
    ExtractiveContentSpec extractive_content_spec = 3;
  }

  // The specification that uses customized query embedding vector to do
  // semantic document retrieval.
  message EmbeddingSpec {
    // Embedding vector.
    message EmbeddingVector {
      // Embedding field path in schema.
      string field_path = 1;

      // Query embedding vector.
      repeated float vector = 2;
    }

    // The embedding vector used for retrieval. Limit to 1.
    repeated EmbeddingVector embedding_vectors = 1;
  }

  // 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.
  string serving_config = 1 [
    (google.api.field_behavior) = REQUIRED,
    (google.api.resource_reference) = {
      type: "discoveryengine.googleapis.com/ServingConfig"
    }
  ];

  // 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.
  string branch = 2 [(google.api.resource_reference) = {
    type: "discoveryengine.googleapis.com/Branch"
  }];

  // Raw search query.
  string query = 3;

  // Raw image query.
  ImageQuery image_query = 19;

  // Maximum number of [Document][google.cloud.discoveryengine.v1beta.Document]s
  // 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.
  int32 page_size = 4;

  // A page token received from a previous
  // [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
  // call. Provide this to retrieve the subsequent page.
  //
  // When paginating, all other parameters provided to
  // [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
  // must match the call that provided the page token. Otherwise, an
  //  `INVALID_ARGUMENT`  error is returned.
  string page_token = 5;

  // A 0-indexed integer that specifies the current offset (that is, starting
  // result location, amongst the
  // [Document][google.cloud.discoveryengine.v1beta.Document]s deemed by the API
  // as relevant) in search results. This field is only considered if
  // [page_token][google.cloud.discoveryengine.v1beta.SearchRequest.page_token]
  // is unset.
  //
  // If this field is negative, an  `INVALID_ARGUMENT`  is returned.
  int32 offset = 6;

  // A list of data store specs to apply on a search call.
  repeated DataStoreSpec data_store_specs = 32;

  // 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)
  string filter = 7;

  // 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][google.cloud.discoveryengine.v1beta.SearchRequest.filter].
  string canonical_filter = 29;

  // The order in which documents are returned. Documents can be ordered by
  // a field in an [Document][google.cloud.discoveryengine.v1beta.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.
  string order_by = 8;

  // Information about the end user.
  // Highly recommended for analytics.
  // [UserInfo.user_agent][google.cloud.discoveryengine.v1beta.UserInfo.user_agent]
  // is used to deduce `device_type` for analytics.
  UserInfo user_info = 21;

  // 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.
  repeated FacetSpec facet_specs = 9;

  // Boost specification to boost certain documents.
  // For more information on boosting, see
  // [Boosting](https://cloud.google.com/retail/docs/boosting#boost)
  BoostSpec boost_spec = 10;

  // 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.
  //    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.
  //    Example:
  //    search_type: 1
  map<string, google.protobuf.Value> params = 11;

  // The query expansion specification that specifies the conditions under which
  // query expansion occurs.
  QueryExpansionSpec query_expansion_spec = 13;

  // The spell correction specification that specifies the mode under
  // which spell correction takes effect.
  SpellCorrectionSpec spell_correction_spec = 14;

  // 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][google.cloud.discoveryengine.v1beta.UserEvent.user_pseudo_id]
  // and
  // [CompleteQueryRequest.user_pseudo_id][google.cloud.discoveryengine.v1beta.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.
  string user_pseudo_id = 15;

  // A specification for configuring the behavior of content search.
  ContentSearchSpec content_search_spec = 24;

  // Uses the provided embedding to do additional semantic document retrieval.
  // The retrieval is based on the dot product of
  // [SearchRequest.EmbeddingSpec.EmbeddingVector.vector][google.cloud.discoveryengine.v1beta.SearchRequest.EmbeddingSpec.EmbeddingVector.vector]
  // and the document embedding that is provided in
  // [SearchRequest.EmbeddingSpec.EmbeddingVector.field_path][google.cloud.discoveryengine.v1beta.SearchRequest.EmbeddingSpec.EmbeddingVector.field_path].
  //
  // If
  // [SearchRequest.EmbeddingSpec.EmbeddingVector.field_path][google.cloud.discoveryengine.v1beta.SearchRequest.EmbeddingSpec.EmbeddingVector.field_path]
  // is not provided, it will use
  // [ServingConfig.EmbeddingConfig.field_path][google.cloud.discoveryengine.v1beta.ServingConfig.embedding_config].
  EmbeddingSpec embedding_spec = 23;

  // The ranking expression controls the customized ranking on retrieval
  // documents. This overrides
  // [ServingConfig.ranking_expression][google.cloud.discoveryengine.v1beta.ServingConfig.ranking_expression].
  // The ranking expression is a single function or multiple functions that are
  // joint by "+".
  //   * ranking_expression = function, { " + ", function };
  // Supported functions:
  //   * double * relevance_score
  //   * double * dotProduct(embedding_field_path)
  // Function variables:
  //   `relevance_score`: pre-defined keywords, used for measure relevance
  //   between query and document.
  //   `embedding_field_path`: the document embedding field
  //   used with query embedding vector.
  //   `dotProduct`: embedding function between embedding_field_path and query
  //   embedding vector.
  //
  //  Example ranking expression:
  //    If document has an embedding field doc_embedding, the ranking expression
  //    could be `0.5 * relevance_score + 0.3 * dotProduct(doc_embedding)`.
  string ranking_expression = 26;

  // Whether to turn on safe search. This is only supported for
  // website search.
  bool safe_search = 20;

  // 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.
  map<string, string> user_labels = 22;
}

// Response message for
// [SearchService.Search][google.cloud.discoveryengine.v1beta.SearchService.Search]
// method.
message SearchResponse {
  // Represents the search results.
  message SearchResult {
    // [Document.id][google.cloud.discoveryengine.v1beta.Document.id] of the
    // searched [Document][google.cloud.discoveryengine.v1beta.Document].
    string id = 1;

    // The document data snippet in the search response. Only fields that are
    // marked as retrievable are populated.
    Document document = 2;

    // Google provided available scores.
    map<string, DoubleList> model_scores = 4;
  }

  // A facet result.
  message Facet {
    // A facet value which contains value names and their count.
    message FacetValue {
      // A facet value which contains values.
      oneof facet_value {
        // Text value of a facet, such as "Black" for facet "colors".
        string value = 1;

        // Interval value for a facet, such as [10, 20) for facet "price". It
        // matches
        // [SearchRequest.FacetSpec.FacetKey.intervals][google.cloud.discoveryengine.v1beta.SearchRequest.FacetSpec.FacetKey.intervals].
        Interval interval = 2;
      }

      // Number of items that have this facet value.
      int64 count = 3;
    }

    // The key for this facet. E.g., "colors" or "price". It matches
    // [SearchRequest.FacetSpec.FacetKey.key][google.cloud.discoveryengine.v1beta.SearchRequest.FacetSpec.FacetKey.key].
    string key = 1;

    // The facet values for this field.
    repeated FacetValue values = 2;

    // Whether the facet is dynamically generated.
    bool dynamic_facet = 3;
  }

  // Guided search result. The guided search helps user to refine the search
  // results and narrow down to the real needs from a broaded search results.
  message GuidedSearchResult {
    // Useful attribute for search result refinements.
    message RefinementAttribute {
      // Attribute key used to refine the results e.g. 'movie_type'.
      string attribute_key = 1;

      // Attribute value used to refine the results e.g. 'drama'.
      string attribute_value = 2;
    }

    // A list of ranked refinement attributes.
    repeated RefinementAttribute refinement_attributes = 1;

    // Suggested follow-up questions.
    repeated string follow_up_questions = 2;
  }

  // Summary of the top N search result specified by the summary spec.
  message Summary {
    // Safety Attribute categories and their associated confidence scores.
    message SafetyAttributes {
      // The display names of Safety Attribute categories associated with the
      // generated content. Order matches the Scores.
      repeated string categories = 1;

      // The confidence scores of the each category, higher
      // value means higher confidence. Order matches the Categories.
      repeated float scores = 2;
    }

    // Citation metadata.
    message CitationMetadata {
      // Citations for segments.
      repeated Citation citations = 1;
    }

    // Citation info for a segment.
    message Citation {
      // Index indicates the start of the segment, measured in bytes/unicode.
      int64 start_index = 1;

      // End of the attributed segment, exclusive.
      int64 end_index = 2;

      // Citation sources for the attributed segment.
      repeated CitationSource sources = 3;
    }

    // Citation source.
    message CitationSource {
      // Document reference index from SummaryWithMetadata.references.
      // It is 0-indexed and the value will be zero if the reference_index is
      // not set explicitly.
      int64 reference_index = 4;
    }

    // Document reference.
    message Reference {
      // Chunk content.
      message ChunkContent {
        // Chunk textual content.
        string content = 1;

        // Page identifier.
        string page_identifier = 2;
      }

      // Title of the document.
      string title = 1;

      // Required.
      // [Document.name][google.cloud.discoveryengine.v1beta.Document.name] of
      // the document. Full resource name of the referenced document, in the
      // format
      // `projects/*/locations/*/collections/*/dataStores/*/branches/*/documents/*`.
      string document = 2 [
        (google.api.field_behavior) = REQUIRED,
        (google.api.resource_reference) = {
          type: "discoveryengine.googleapis.com/Document"
        }
      ];

      // Cloud Storage or HTTP uri for the document.
      string uri = 3;

      // List of cited chunk contents derived from document content.
      repeated ChunkContent chunk_contents = 4;
    }

    // Summary with metadata information.
    message SummaryWithMetadata {
      // Summary text with no citation information.
      string summary = 1;

      // Citation metadata for given summary.
      CitationMetadata citation_metadata = 2;

      // Document References.
      repeated Reference references = 3;
    }

    // An Enum for summary-skipped reasons.
    enum SummarySkippedReason {
      // Default value. The summary skipped reason is not specified.
      SUMMARY_SKIPPED_REASON_UNSPECIFIED = 0;

      // The adversarial query ignored case.
      //
      // Only populated when
      // [SummarySpec.ignore_adversarial_query][google.cloud.discoveryengine.v1beta.SearchRequest.ContentSearchSpec.SummarySpec.ignore_adversarial_query]
      // is set to `true`.
      ADVERSARIAL_QUERY_IGNORED = 1;

      // The non-summary seeking query ignored case.
      //
      // Only populated when
      // [SummarySpec.ignore_non_summary_seeking_query][google.cloud.discoveryengine.v1beta.SearchRequest.ContentSearchSpec.SummarySpec.ignore_non_summary_seeking_query]
      // is set to `true`.
      NON_SUMMARY_SEEKING_QUERY_IGNORED = 2;

      // The out-of-domain query ignored case.
      //
      // Google skips the summary if there are no high-relevance search results.
      // For example, the data store contains facts about company A but the
      // user query is asking questions about company B.
      OUT_OF_DOMAIN_QUERY_IGNORED = 3;

      // The potential policy violation case.
      //
      // Google skips the summary if there is a potential policy violation
      // detected. This includes content that may be violent or toxic.
      POTENTIAL_POLICY_VIOLATION = 4;

      // The LLM addon not enabled case.
      //
      // Google skips the summary if the LLM addon is not enabled.
      LLM_ADDON_NOT_ENABLED = 5;
    }

    // The summary content.
    string summary_text = 1;

    // Additional summary-skipped reasons. This provides the reason for ignored
    // cases. If nothing is skipped, this field is not set.
    repeated SummarySkippedReason summary_skipped_reasons = 2;

    // A collection of Safety Attribute categories and their associated
    // confidence scores.
    SafetyAttributes safety_attributes = 3;

    // Summary with metadata information.
    SummaryWithMetadata summary_with_metadata = 4;
  }

  // Debug information specifically related to forward geocoding issues arising
  // from Geolocation Search.
  message GeoSearchDebugInfo {
    // The address from which forward geocoding ingestion produced issues.
    string original_address_query = 1;

    // The error produced.
    string error_message = 2;
  }

  // Information describing query expansion including whether expansion has
  // occurred.
  message QueryExpansionInfo {
    // Bool describing whether query expansion has occurred.
    bool expanded_query = 1;

    // Number of pinned results. This field will only be set when expansion
    // happens and
    // [SearchRequest.QueryExpansionSpec.pin_unexpanded_results][google.cloud.discoveryengine.v1beta.SearchRequest.QueryExpansionSpec.pin_unexpanded_results]
    // is set to true.
    int64 pinned_result_count = 2;
  }

  // A list of matched documents. The order represents the ranking.
  repeated SearchResult results = 1;

  // Results of facets requested by user.
  repeated Facet facets = 2;

  // Guided search result.
  GuidedSearchResult guided_search_result = 8;

  // The estimated total count of matched items irrespective of pagination. The
  // count of
  // [results][google.cloud.discoveryengine.v1beta.SearchResponse.results]
  // returned by pagination may be less than the
  // [total_size][google.cloud.discoveryengine.v1beta.SearchResponse.total_size]
  // that matches.
  int32 total_size = 3;

  // A unique search token. This should be included in the
  // [UserEvent][google.cloud.discoveryengine.v1beta.UserEvent] logs resulting
  // from this search, which enables accurate attribution of search model
  // performance.
  string attribution_token = 4;

  // The URI of a customer-defined redirect page. If redirect action is
  // triggered, no search is performed, and only
  // [redirect_uri][google.cloud.discoveryengine.v1beta.SearchResponse.redirect_uri]
  // and
  // [attribution_token][google.cloud.discoveryengine.v1beta.SearchResponse.attribution_token]
  // are set in the response.
  string redirect_uri = 12;

  // A token that can be sent as
  // [SearchRequest.page_token][google.cloud.discoveryengine.v1beta.SearchRequest.page_token]
  // to retrieve the next page. If this field is omitted, there are no
  // subsequent pages.
  string next_page_token = 5;

  // 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.
  string corrected_query = 7;

  // A summary as part of the search results.
  // This field is only returned if
  // [SearchRequest.ContentSearchSpec.summary_spec][google.cloud.discoveryengine.v1beta.SearchRequest.ContentSearchSpec.summary_spec]
  // is set.
  Summary summary = 9;

  // Controls applied as part of the Control service.
  repeated string applied_controls = 10;

  // Debug information specifically related to forward geocoding issues arising
  // from Geolocation Search.
  repeated GeoSearchDebugInfo geo_search_debug_info = 16;

  // Query expansion information for the returned results.
  QueryExpansionInfo query_expansion_info = 14;
}