---
title: Getting Started with Datadog
description: Datadog, the leading service for cloud-scale monitoring.
breadcrumbs: Docs > Infrastructure > Datadog Resource Catalog
---

# gcp_aiplatform_cached_content{% #gcp_aiplatform_cached_content %}

## `ancestors`{% #ancestors %}

**Type**: `UNORDERED_LIST_STRING`

## `contents`{% #contents %}

**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `contents`**Description**: Optional. Input only. Immutable. The content to cache

- `parts`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `parts`**Description**: Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
  - `code_execution_result`**Type**: `STRUCT`**Provider name**: `codeExecutionResult`**Description**: Optional. Result of executing the [ExecutableCode].
    - `outcome`**Type**: `STRING`**Provider name**: `outcome`**Description**: Required. Outcome of the code execution.**Possible values**:
      - `OUTCOME_UNSPECIFIED` - Unspecified status. This value should not be used.
      - `OUTCOME_OK` - Code execution completed successfully.
      - `OUTCOME_FAILED` - Code execution finished but with a failure. `stderr` should contain the reason.
      - `OUTCOME_DEADLINE_EXCEEDED` - Code execution ran for too long, and was cancelled. There may or may not be a partial output present.
    - `output`**Type**: `STRING`**Provider name**: `output`**Description**: Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
  - `executable_code`**Type**: `STRUCT`**Provider name**: `executableCode`**Description**: Optional. Code generated by the model that is meant to be executed.
    - `code`**Type**: `STRING`**Provider name**: `code`**Description**: Required. The code to be executed.
    - `language`**Type**: `STRING`**Provider name**: `language`**Description**: Required. Programming language of the `code`.**Possible values**:
      - `LANGUAGE_UNSPECIFIED` - Unspecified language. This value should not be used.
      - `PYTHON` - Python >= 3.10, with numpy and simpy available.
  - `file_data`**Type**: `STRUCT`**Provider name**: `fileData`**Description**: Optional. URI based data.
    - `file_uri`**Type**: `STRING`**Provider name**: `fileUri`**Description**: Required. URI.
    - `gcp_display_name`**Type**: `STRING`**Provider name**: `displayName`**Description**: Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is not currently used in the Gemini GenerateContent calls.
    - `mime_type`**Type**: `STRING`**Provider name**: `mimeType`**Description**: Required. The IANA standard MIME type of the source data.
  - `function_call`**Type**: `STRUCT`**Provider name**: `functionCall`**Description**: Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
    - `name`**Type**: `STRING`**Provider name**: `name`**Description**: Required. The name of the function to call. Matches [FunctionDeclaration.name].
  - `function_response`**Type**: `STRUCT`**Provider name**: `functionResponse`**Description**: Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
    - `name`**Type**: `STRING`**Provider name**: `name`**Description**: Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
  - `inline_data`**Type**: `STRUCT`**Provider name**: `inlineData`**Description**: Optional. Inlined bytes data.
    - `gcp_display_name`**Type**: `STRING`**Provider name**: `displayName`**Description**: Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is not currently used in the Gemini GenerateContent calls.
    - `mime_type`**Type**: `STRING`**Provider name**: `mimeType`**Description**: Required. The IANA standard MIME type of the source data.
  - `text`**Type**: `STRING`**Provider name**: `text`**Description**: Optional. Text part (can be code).
  - `video_metadata`**Type**: `STRUCT`**Provider name**: `videoMetadata`**Description**: Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
    - `end_offset`**Type**: `STRING`**Provider name**: `endOffset`**Description**: Optional. The end offset of the video.
    - `start_offset`**Type**: `STRING`**Provider name**: `startOffset`**Description**: Optional. The start offset of the video.
- `role`**Type**: `STRING`**Provider name**: `role`**Description**: Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.

## `create_time`{% #create_time %}

**Type**: `TIMESTAMP`**Provider name**: `createTime`**Description**: Output only. Creation time of the cache entry.

## `expire_time`{% #expire_time %}

**Type**: `TIMESTAMP`**Provider name**: `expireTime`**Description**: Timestamp of when this resource is considered expired. This is *always* provided on output, regardless of what was sent on input.

## `gcp_display_name`{% #gcp_display_name %}

**Type**: `STRING`**Provider name**: `displayName`**Description**: Optional. Immutable. The user-generated meaningful display name of the cached content.

## `labels`{% #labels %}

**Type**: `UNORDERED_LIST_STRING`

## `model`{% #model %}

**Type**: `STRING`**Provider name**: `model`**Description**: Immutable. The name of the `Model` to use for cached content. Currently, only the published Gemini base models are supported, in form of projects/{PROJECT}/locations/{LOCATION}/publishers/google/models/{MODEL}

## `name`{% #name %}

**Type**: `STRING`**Provider name**: `name`**Description**: Immutable. Identifier. The server-generated resource name of the cached content Format: projects/{project}/locations/{location}/cachedContents/{cached_content}

## `organization_id`{% #organization_id %}

**Type**: `STRING`

## `parent`{% #parent %}

**Type**: `STRING`

## `project_id`{% #project_id %}

**Type**: `STRING`

## `project_number`{% #project_number %}

**Type**: `STRING`

## `region_id`{% #region_id %}

**Type**: `STRING`

## `resource_name`{% #resource_name %}

**Type**: `STRING`

## `system_instruction`{% #system_instruction %}

**Type**: `STRUCT`**Provider name**: `systemInstruction`**Description**: Optional. Input only. Immutable. Developer set system instruction. Currently, text only

- `parts`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `parts`**Description**: Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
  - `code_execution_result`**Type**: `STRUCT`**Provider name**: `codeExecutionResult`**Description**: Optional. Result of executing the [ExecutableCode].
    - `outcome`**Type**: `STRING`**Provider name**: `outcome`**Description**: Required. Outcome of the code execution.**Possible values**:
      - `OUTCOME_UNSPECIFIED` - Unspecified status. This value should not be used.
      - `OUTCOME_OK` - Code execution completed successfully.
      - `OUTCOME_FAILED` - Code execution finished but with a failure. `stderr` should contain the reason.
      - `OUTCOME_DEADLINE_EXCEEDED` - Code execution ran for too long, and was cancelled. There may or may not be a partial output present.
    - `output`**Type**: `STRING`**Provider name**: `output`**Description**: Optional. Contains stdout when code execution is successful, stderr or other description otherwise.
  - `executable_code`**Type**: `STRUCT`**Provider name**: `executableCode`**Description**: Optional. Code generated by the model that is meant to be executed.
    - `code`**Type**: `STRING`**Provider name**: `code`**Description**: Required. The code to be executed.
    - `language`**Type**: `STRING`**Provider name**: `language`**Description**: Required. Programming language of the `code`.**Possible values**:
      - `LANGUAGE_UNSPECIFIED` - Unspecified language. This value should not be used.
      - `PYTHON` - Python >= 3.10, with numpy and simpy available.
  - `file_data`**Type**: `STRUCT`**Provider name**: `fileData`**Description**: Optional. URI based data.
    - `file_uri`**Type**: `STRING`**Provider name**: `fileUri`**Description**: Required. URI.
    - `gcp_display_name`**Type**: `STRING`**Provider name**: `displayName`**Description**: Optional. Display name of the file data. Used to provide a label or filename to distinguish file datas. This field is only returned in PromptMessage for prompt management. It is not currently used in the Gemini GenerateContent calls.
    - `mime_type`**Type**: `STRING`**Provider name**: `mimeType`**Description**: Required. The IANA standard MIME type of the source data.
  - `function_call`**Type**: `STRUCT`**Provider name**: `functionCall`**Description**: Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
    - `name`**Type**: `STRING`**Provider name**: `name`**Description**: Required. The name of the function to call. Matches [FunctionDeclaration.name].
  - `function_response`**Type**: `STRUCT`**Provider name**: `functionResponse`**Description**: Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
    - `name`**Type**: `STRING`**Provider name**: `name`**Description**: Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
  - `inline_data`**Type**: `STRUCT`**Provider name**: `inlineData`**Description**: Optional. Inlined bytes data.
    - `gcp_display_name`**Type**: `STRING`**Provider name**: `displayName`**Description**: Optional. Display name of the blob. Used to provide a label or filename to distinguish blobs. This field is only returned in PromptMessage for prompt management. It is not currently used in the Gemini GenerateContent calls.
    - `mime_type`**Type**: `STRING`**Provider name**: `mimeType`**Description**: Required. The IANA standard MIME type of the source data.
  - `text`**Type**: `STRING`**Provider name**: `text`**Description**: Optional. Text part (can be code).
  - `video_metadata`**Type**: `STRUCT`**Provider name**: `videoMetadata`**Description**: Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
    - `end_offset`**Type**: `STRING`**Provider name**: `endOffset`**Description**: Optional. The end offset of the video.
    - `start_offset`**Type**: `STRING`**Provider name**: `startOffset`**Description**: Optional. The start offset of the video.
- `role`**Type**: `STRING`**Provider name**: `role`**Description**: Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.

## `tags`{% #tags %}

**Type**: `UNORDERED_LIST_STRING`

## `tool_config`{% #tool_config %}

**Type**: `STRUCT`**Provider name**: `toolConfig`**Description**: Optional. Input only. Immutable. Tool config. This config is shared for all tools

- `function_calling_config`**Type**: `STRUCT`**Provider name**: `functionCallingConfig`**Description**: Optional. Function calling config.
  - `allowed_function_names`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `allowedFunctionNames`**Description**: Optional. Function names to call. Only set when the Mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, model will predict a function call from the set of function names provided.
  - `mode`**Type**: `STRING`**Provider name**: `mode`**Description**: Optional. Function calling mode.**Possible values**:
    - `MODE_UNSPECIFIED` - Unspecified function calling mode. This value should not be used.
    - `AUTO` - Default model behavior, model decides to predict either function calls or natural language response.
    - `ANY` - Model is constrained to always predicting function calls only. If 'allowed_function_names' are set, the predicted function calls will be limited to any one of 'allowed_function_names', else the predicted function calls will be any one of the provided 'function_declarations'.
    - `NONE` - Model will not predict any function calls. Model behavior is same as when not passing any function declarations.
- `retrieval_config`**Type**: `STRUCT`**Provider name**: `retrievalConfig`**Description**: Optional. Retrieval config.
  - `language_code`**Type**: `STRING`**Provider name**: `languageCode`**Description**: The language code of the user.
  - `lat_lng`**Type**: `STRUCT`**Provider name**: `latLng`**Description**: The location of the user.
    - `latitude`**Type**: `DOUBLE`**Provider name**: `latitude`**Description**: The latitude in degrees. It must be in the range [-90.0, +90.0].
    - `longitude`**Type**: `DOUBLE`**Provider name**: `longitude`**Description**: The longitude in degrees. It must be in the range [-180.0, +180.0].

## `tools`{% #tools %}

**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `tools`**Description**: Optional. Input only. Immutable. A list of `Tools` the model may use to generate the next response

- `code_execution`**Type**: `STRUCT`**Provider name**: `codeExecution`**Description**: Optional. CodeExecution tool type. Enables the model to execute code as part of generation.

- `enterprise_web_search`**Type**: `STRUCT`**Provider name**: `enterpriseWebSearch`**Description**: Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance.

- `function_declarations`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `functionDeclarations`**Description**: Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 128 function declarations can be provided.

  - `description`**Type**: `STRING`**Provider name**: `description`**Description**: Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function.
  - `name`**Type**: `STRING`**Provider name**: `name`**Description**: Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64.
  - `parameters`**Type**: `STRUCT`**Provider name**: `parameters`**Description**: Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
    - `description`**Type**: `STRING`**Provider name**: `description`**Description**: Optional. The description of the data.
    - `enum`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `enum`**Description**: Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
    - `format`**Type**: `STRING`**Provider name**: `format`**Description**: Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
    - `max_items`**Type**: `INT64`**Provider name**: `maxItems`**Description**: Optional. Maximum number of the elements for Type.ARRAY.
    - `max_length`**Type**: `INT64`**Provider name**: `maxLength`**Description**: Optional. Maximum length of the Type.STRING
    - `max_properties`**Type**: `INT64`**Provider name**: `maxProperties`**Description**: Optional. Maximum number of the properties for Type.OBJECT.
    - `maximum`**Type**: `DOUBLE`**Provider name**: `maximum`**Description**: Optional. Maximum value of the Type.INTEGER and Type.NUMBER
    - `min_items`**Type**: `INT64`**Provider name**: `minItems`**Description**: Optional. Minimum number of the elements for Type.ARRAY.
    - `min_length`**Type**: `INT64`**Provider name**: `minLength`**Description**: Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
    - `min_properties`**Type**: `INT64`**Provider name**: `minProperties`**Description**: Optional. Minimum number of the properties for Type.OBJECT.
    - `minimum`**Type**: `DOUBLE`**Provider name**: `minimum`**Description**: Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
    - `nullable`**Type**: `BOOLEAN`**Provider name**: `nullable`**Description**: Optional. Indicates if the value may be null.
    - `pattern`**Type**: `STRING`**Provider name**: `pattern`**Description**: Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
    - `property_ordering`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `propertyOrdering`**Description**: Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
    - `required`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `required`**Description**: Optional. Required properties of Type.OBJECT.
    - `title`**Type**: `STRING`**Provider name**: `title`**Description**: Optional. The title of the Schema.
    - `type`**Type**: `STRING`**Provider name**: `type`**Description**: Optional. The type of the data.**Possible values**:
      - `TYPE_UNSPECIFIED` - Not specified, should not be used.
      - `STRING` - OpenAPI string type
      - `NUMBER` - OpenAPI number type
      - `INTEGER` - OpenAPI integer type
      - `BOOLEAN` - OpenAPI boolean type
      - `ARRAY` - OpenAPI array type
      - `OBJECT` - OpenAPI object type
  - `response`**Type**: `STRUCT`**Provider name**: `response`**Description**: Optional. Describes the output from this function in JSON Schema format. Reflects the Open API 3.03 Response Object. The Schema defines the type used for the response value of the function.
    - `description`**Type**: `STRING`**Provider name**: `description`**Description**: Optional. The description of the data.
    - `enum`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `enum`**Description**: Optional. Possible values of the element of primitive type with enum format. Examples: 1. We can define direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} 2. We can define apartment number as : {type:INTEGER, format:enum, enum:["101", "201", "301"]}
    - `format`**Type**: `STRING`**Provider name**: `format`**Description**: Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc
    - `max_items`**Type**: `INT64`**Provider name**: `maxItems`**Description**: Optional. Maximum number of the elements for Type.ARRAY.
    - `max_length`**Type**: `INT64`**Provider name**: `maxLength`**Description**: Optional. Maximum length of the Type.STRING
    - `max_properties`**Type**: `INT64`**Provider name**: `maxProperties`**Description**: Optional. Maximum number of the properties for Type.OBJECT.
    - `maximum`**Type**: `DOUBLE`**Provider name**: `maximum`**Description**: Optional. Maximum value of the Type.INTEGER and Type.NUMBER
    - `min_items`**Type**: `INT64`**Provider name**: `minItems`**Description**: Optional. Minimum number of the elements for Type.ARRAY.
    - `min_length`**Type**: `INT64`**Provider name**: `minLength`**Description**: Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING
    - `min_properties`**Type**: `INT64`**Provider name**: `minProperties`**Description**: Optional. Minimum number of the properties for Type.OBJECT.
    - `minimum`**Type**: `DOUBLE`**Provider name**: `minimum`**Description**: Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER
    - `nullable`**Type**: `BOOLEAN`**Provider name**: `nullable`**Description**: Optional. Indicates if the value may be null.
    - `pattern`**Type**: `STRING`**Provider name**: `pattern`**Description**: Optional. Pattern of the Type.STRING to restrict a string to a regular expression.
    - `property_ordering`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `propertyOrdering`**Description**: Optional. The order of the properties. Not a standard field in open api spec. Only used to support the order of the properties.
    - `required`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `required`**Description**: Optional. Required properties of Type.OBJECT.
    - `title`**Type**: `STRING`**Provider name**: `title`**Description**: Optional. The title of the Schema.
    - `type`**Type**: `STRING`**Provider name**: `type`**Description**: Optional. The type of the data.**Possible values**:
      - `TYPE_UNSPECIFIED` - Not specified, should not be used.
      - `STRING` - OpenAPI string type
      - `NUMBER` - OpenAPI number type
      - `INTEGER` - OpenAPI integer type
      - `BOOLEAN` - OpenAPI boolean type
      - `ARRAY` - OpenAPI array type
      - `OBJECT` - OpenAPI object type

- `google_search`**Type**: `STRUCT`**Provider name**: `googleSearch`**Description**: Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.

- `google_search_retrieval`**Type**: `STRUCT`**Provider name**: `googleSearchRetrieval`**Description**: Optional. GoogleSearchRetrieval tool type. Specialized retrieval tool that is powered by Google search.

  - `dynamic_retrieval_config`**Type**: `STRUCT`**Provider name**: `dynamicRetrievalConfig`**Description**: Specifies the dynamic retrieval configuration for the given source.
    - `dynamic_threshold`**Type**: `FLOAT`**Provider name**: `dynamicThreshold`**Description**: Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used.
    - `mode`**Type**: `STRING`**Provider name**: `mode`**Description**: The mode of the predictor to be used in dynamic retrieval.**Possible values**:
      - `MODE_UNSPECIFIED` - Always trigger retrieval.
      - `MODE_DYNAMIC` - Run retrieval only when system decides it is necessary.

- `retrieval`**Type**: `STRUCT`**Provider name**: `retrieval`**Description**: Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation.

  - `disable_attribution`**Type**: `BOOLEAN`**Provider name**: `disableAttribution`**Description**: Optional. Deprecated. This option is no longer supported.
  - `vertex_ai_search`**Type**: `STRUCT`**Provider name**: `vertexAiSearch`**Description**: Set to use data source powered by Vertex AI Search.
    - `datastore`**Type**: `STRING`**Provider name**: `datastore`**Description**: Optional. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}`
    - `engine`**Type**: `STRING`**Provider name**: `engine`**Description**: Optional. Fully-qualified Vertex AI Search engine resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}`
  - `vertex_rag_store`**Type**: `STRUCT`**Provider name**: `vertexRagStore`**Description**: Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService.
    - `rag_resources`**Type**: `UNORDERED_LIST_STRUCT`**Provider name**: `ragResources`**Description**: Optional. The representation of the rag source. It can be used to specify corpus only or ragfiles. Currently only support one corpus or multiple files from one corpus. In the future we may open up multiple corpora support.
      - `rag_corpus`**Type**: `STRING`**Provider name**: `ragCorpus`**Description**: Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`
      - `rag_file_ids`**Type**: `UNORDERED_LIST_STRING`**Provider name**: `ragFileIds`**Description**: Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field.
    - `rag_retrieval_config`**Type**: `STRUCT`**Provider name**: `ragRetrievalConfig`**Description**: Optional. The retrieval config for the Rag query.
      - `filter`**Type**: `STRUCT`**Provider name**: `filter`**Description**: Optional. Config for filters.
        - `metadata_filter`**Type**: `STRING`**Provider name**: `metadataFilter`**Description**: Optional. String for metadata filtering.
        - `vector_distance_threshold`**Type**: `DOUBLE`**Provider name**: `vectorDistanceThreshold`**Description**: Optional. Only returns contexts with vector distance smaller than the threshold.
        - `vector_similarity_threshold`**Type**: `DOUBLE`**Provider name**: `vectorSimilarityThreshold`**Description**: Optional. Only returns contexts with vector similarity larger than the threshold.
      - `ranking`**Type**: `STRUCT`**Provider name**: `ranking`**Description**: Optional. Config for ranking and reranking.
        - `llm_ranker`**Type**: `STRUCT`**Provider name**: `llmRanker`**Description**: Optional. Config for LlmRanker.
          - `model_name`**Type**: `STRING`**Provider name**: `modelName`**Description**: Optional. The model name used for ranking. See [Supported models](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference#supported-models).
        - `rank_service`**Type**: `STRUCT`**Provider name**: `rankService`**Description**: Optional. Config for Rank Service.
          - `model_name`**Type**: `STRING`**Provider name**: `modelName`**Description**: Optional. The model name of the rank service. Format: `semantic-ranker-512@latest`
      - `top_k`**Type**: `INT32`**Provider name**: `topK`**Description**: Optional. The number of contexts to retrieve.
    - `similarity_top_k`**Type**: `INT32`**Provider name**: `similarityTopK`**Description**: Optional. Number of top k results to return from the selected corpora.
    - `vector_distance_threshold`**Type**: `DOUBLE`**Provider name**: `vectorDistanceThreshold`**Description**: Optional. Only return results with vector distance smaller than the threshold.

## `ttl`{% #ttl %}

**Type**: `STRING`**Provider name**: `ttl`**Description**: Input only. The TTL for this resource. The expiration time is computed: now + TTL.

## `update_time`{% #update_time %}

**Type**: `TIMESTAMP`**Provider name**: `updateTime`**Description**: Output only. When the cache entry was last updated in UTC time.

## `usage_metadata`{% #usage_metadata %}

**Type**: `STRUCT`**Provider name**: `usageMetadata`**Description**: Output only. Metadata on the usage of the cached content.

- `audio_duration_seconds`**Type**: `INT32`**Provider name**: `audioDurationSeconds`**Description**: Duration of audio in seconds.
- `image_count`**Type**: `INT32`**Provider name**: `imageCount`**Description**: Number of images.
- `text_count`**Type**: `INT32`**Provider name**: `textCount`**Description**: Number of text characters.
- `total_token_count`**Type**: `INT32`**Provider name**: `totalTokenCount`**Description**: Total number of tokens that the cached content consumes.
- `video_duration_seconds`**Type**: `INT32`**Provider name**: `videoDurationSeconds`**Description**: Duration of video in seconds.

## `zone_id`{% #zone_id %}

**Type**: `STRING`