@google-cloud/discoveryengine 0.8.0 → 1.1.0

package/build/protos/google/cloud/discoveryengine/v1beta/search_service.proto

@@ -56,6 +56,15 @@ service SearchService {
 // [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 facet specification to perform faceted search.
   message FacetSpec {
     // Specifies how a facet is computed.
@@ -65,7 +74,7 @@ message SearchRequest {
       // 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 bucketized into intervals. Must be set
+      // 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;
@@ -73,22 +82,22 @@ message SearchRequest {
       // 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 will only
-      // contain "Action > 2022". Only supported on textual fields. Maximum
+      // "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 will only contain "Action > 2022" and "Action > 2021".
+      // "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 will only contain "Action > 2022" and "Sci-Fi > 2022".
+      // "category" facet only contains "Action > 2022" and "Sci-Fi > 2022".
       // Only supported on textual fields. Maximum is 10.
       repeated string contains = 5;
 
@@ -121,7 +130,7 @@ message SearchRequest {
 
     // 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 will be coerced to 300.
+    // above 300 are coerced to 300.
     //
     // If this field is negative, an  `INVALID_ARGUMENT`  is returned.
     int32 limit = 2;
@@ -158,15 +167,15 @@ message SearchRequest {
 
     // Enables dynamic position for this facet. If set to true, the position of
     // this facet among all facets in the response is determined automatically.
-    // It will be ordered together with dynamic facets if dynamic
-    // facets is enabled. If set to false, the position of this facet in the
-    // response will be the same as in the request, and it will be ranked before
+    // 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 will be determined
+    // that the position of rating facet in response is determined
     // automatically.
     //
     // Another example, assuming you have the following facets in the request:
@@ -177,13 +186,13 @@ message SearchRequest {
     //
     // * "brands", enable_dynamic_position = false
     //
-    // And also you have a dynamic facets enable, which will generate a facet
-    // 'gender'. Then the final order of the facets in the response can be
+    // 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" will always be
-    // ranked at 1st and 2nd position since their enable_dynamic_position are
-    // false.
+    // 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;
   }
 
@@ -253,6 +262,11 @@ message SearchRequest {
     // 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.
@@ -281,72 +295,141 @@ message SearchRequest {
     Mode mode = 1;
   }
 
-  // The specification that configs the desired behavior of the UCS content
-  // search.
+  // A specification for configuring the behavior of content search.
   message ContentSearchSpec {
-    // The specification that configs the snippet in the search results.
+    // A specification for configuring snippets in a search response.
     message SnippetSpec {
-      // Max number of snippets returned in each search result.
-      //
-      // A snippet is an infomartive summary of a content with highlighting for
-      // UI rendering.
-      //
-      // If the matching snippets is less than the max_snippet_count, return all
-      // of the snippets; otherwise, return the max_snippet_count.
-      //
-      // At most 5 snippets will be returned for each SearchResult.
-      int32 max_snippet_count = 1;
-
-      // if true, only snippet reference is returned.
-      bool reference_only = 2;
+      // [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;
     }
 
-    // The specification that configs the summary in the search response.
+    // A specification for configuring a summary returned in a search
+    // response.
     message SummarySpec {
-      // The number of top results the summary should be generated from.
-      // If the number of returned results is less than summary_result_count,
-      // then the summary would be derived from all the results; otherwise, the
-      // summary would be derived from the top results.
+      // 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 5 results can be used for generating summary.
+      // At most five 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;
+
+      // Language code for Summary. Use language tags defined by
+      // [BCP47][https://www.rfc-editor.org/rfc/bcp/bcp47.txt].
+      string language_code = 6;
     }
 
-    // The specification that configs the extractive content in search results.
+    // A specification for configuring the extractive content in a search
+    // response.
     message ExtractiveContentSpec {
-      // The max number of extractive answers returned in each search result.
+      // 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 precise and contextually relevant answer to
+      // document, which provides a precise and contextually relevant answer to
       // the search query.
       //
       // If the number of matching answers is less than the
-      // extractive_answer_count, return all of the answers; otherwise, return
-      // the extractive_answer_count.
+      // `max_extractive_answer_count`, return all of the answers. Otherwise,
+      // return the `max_extractive_answer_count`.
       //
-      // At most 5 answers will be returned for each SearchResult.
+      // At most one answer is 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 which is relevant to the search query and in general more
-      // verbose than an extrative answer. The segment could then be used as
+      // 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 the
-      // max_extractive_segment_count, return all of the segments; otherwise,
-      // return the max_extractive_segment_count.
-      //
-      // Currently one segment will be returned for each SearchResult.
+      // 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. 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 there is no snippet spec provided, there will be no snippet in the
-    // search result.
+    // If `snippetSpec` is not specified, snippets are not included in the
+    // search response.
     SnippetSpec snippet_spec = 1;
 
-    // If there is no summary spec provided, there will be no summary in the
+    // If `summarySpec` is not specified, summaries are not included in the
     // search response.
     SummarySpec summary_spec = 2;
 
@@ -355,6 +438,22 @@ message SearchRequest {
     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/dataStores/default_data_store/servingConfigs/default_serving_config`.
   // This field is used to identify the serving configuration name, set
@@ -378,9 +477,12 @@ message SearchRequest {
   // 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. If unspecified, defaults to a reasonable value. The maximum
-  // allowed value is 100. Values above 100 will be coerced to 100.
+  // allowed value is 100. Values above 100 are coerced to 100.
   //
   // If this field is negative, an  `INVALID_ARGUMENT`  is returned.
   int32 page_size = 4;
@@ -412,17 +514,18 @@ message SearchRequest {
   // If this field is unrecognizable, an  `INVALID_ARGUMENT`  is returned.
   string filter = 7;
 
-  // The order in which documents are returned. Document can be ordered by
+  // 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. OrderBy expression is
+  // object. Leave it unset if ordered by relevance. `order_by` expression is
   // case-sensitive.
   //
-  // If this field is unrecognizable, an  `INVALID_ARGUMENT`  is returned.
+  // If this field is unrecognizable, an `INVALID_ARGUMENT` is returned.
   string order_by = 8;
 
   // Information about the end user.
-  // Highly recommended for analytics. The user_agent string in UserInfo will
-  // be used to deduce device_type for analytics.
+  // 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.
@@ -446,11 +549,11 @@ message SearchRequest {
   map<string, google.protobuf.Value> params = 11;
 
   // The query expansion specification that specifies the conditions under which
-  // query expansion will occur.
+  // query expansion occurs.
   QueryExpansionSpec query_expansion_spec = 13;
 
   // The spell correction specification that specifies the mode under
-  // which spell correction will take effect.
+  // which spell correction takes effect.
   SpellCorrectionSpec spell_correction_spec = 14;
 
   // A unique identifier for tracking visitors. For example, this could be
@@ -469,12 +572,42 @@ message SearchRequest {
   // characters. Otherwise, an  `INVALID_ARGUMENT`  error is returned.
   string user_pseudo_id = 15;
 
-  // The content search spec that configs the desired behavior of content
-  // search.
+  // 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.embedding_spec.embedding_vectors.vector][] and the document
+  // embedding that is provided in
+  // [SearchRequest.embedding_spec.embedding_vectors.field_path][].
+  //
+  // If [SearchRequest.embedding_spec.embedding_vectors.field_path][] is not
+  // provided, it will use [ServingConfig.embedding_config.field_paths][].
+  EmbeddingSpec embedding_spec = 23;
+
+  // The ranking expression controls the customized ranking on retrieval
+  // documents. This overrides [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
-  // [ContentConfig.PUBLIC_WEBSITE][].
+  // website search.
   bool safe_search = 20;
 
   // The user labels applied to a resource must meet the following requirements:
@@ -510,6 +643,9 @@ message SearchResponse {
     // 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.
@@ -556,12 +692,85 @@ message SearchResponse {
 
     // 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;
+    }
+
+    // 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;
+  }
+
+  // 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.
@@ -614,4 +823,7 @@ message SearchResponse {
 
   // Controls applied as part of the Control service.
   repeated string applied_controls = 10;
+
+  // Query expansion information for the returned results.
+  QueryExpansionInfo query_expansion_info = 14;
 }