> ## Documentation Index > Fetch the complete documentation index at: https://docs.apowerb.com/llms.txt > Use this file to discover all available pages before exploring further. # Get Adk App Info > Returns the detailed info for a given ADK app. ## OpenAPI ````yaml /api-reference/openapi.json get /apps/{app_name}/app-info openapi: 3.1.0 info: title: apowerb API description: REST API of the apowerb agentic framework (open-source edition). version: 0.1.2 license: name: MIT url: https://github.com/apowerb/apowerb/blob/main/LICENSE servers: - url: https://api.example.com description: Your apowerb instance - url: http://localhost:8000 description: Local stack security: [] paths: /apps/{app_name}/app-info: get: summary: Get Adk App Info description: Returns the detailed info for a given ADK app. operationId: get_adk_app_info_apps__app_name__app_info_get parameters: - name: app_name in: path required: true schema: type: string title: App Name responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AppInfo' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: AppInfo: properties: name: type: string title: Name rootAgentName: type: string title: Rootagentname description: type: string title: Description language: type: string enum: - yaml - python title: Language isComputerUse: type: boolean title: Iscomputeruse default: false agents: anyOf: - additionalProperties: $ref: '#/components/schemas/AgentInfo' type: object - type: 'null' title: Agents type: object required: - name - rootAgentName - description - language title: AppInfo HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError AgentInfo: properties: name: type: string title: Name description: type: string title: Description instruction: type: string title: Instruction tools: items: $ref: '#/components/schemas/Tool' type: array title: Tools sub_agents: items: type: string type: array title: Sub Agents type: object required: - name - description - instruction - tools - sub_agents title: AgentInfo ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError Tool: properties: retrieval: anyOf: - $ref: '#/components/schemas/Retrieval' - type: 'null' 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. This field is not supported in Gemini API. computerUse: anyOf: - $ref: '#/components/schemas/ComputerUse' - type: 'null' description: >- Optional. Tool to support the model interacting directly with the computer. If enabled, it automatically populates computer-use specific Function Declarations. fileSearch: anyOf: - $ref: '#/components/schemas/FileSearch' - type: 'null' description: >- Optional. FileSearch tool type. Tool to retrieve knowledge from Semantic Retrieval corpora. This field is not supported in Vertex AI. googleSearch: anyOf: - $ref: '#/components/schemas/GoogleSearch' - type: 'null' description: >- Optional. GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. googleMaps: anyOf: - $ref: '#/components/schemas/GoogleMaps' - type: 'null' description: |- Optional. Tool that allows grounding the model's response with geospatial context related to the user's query. codeExecution: anyOf: - $ref: '#/components/schemas/ToolCodeExecution' - type: 'null' description: >- Optional. CodeExecution tool type. Enables the model to execute code as part of generation. enterpriseWebSearch: anyOf: - $ref: '#/components/schemas/EnterpriseWebSearch' - type: 'null' description: >- Optional. Tool to support searching public web data, powered by Vertex AI Search and Sec4 compliance. This field is not supported in Gemini API. functionDeclarations: anyOf: - items: $ref: '#/components/schemas/FunctionDeclaration' type: array - type: 'null' title: 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 512 function declarations can be provided. googleSearchRetrieval: anyOf: - $ref: '#/components/schemas/GoogleSearchRetrieval' - type: 'null' description: >- Optional. Specialized retrieval tool that is powered by Google Search. parallelAiSearch: anyOf: - $ref: '#/components/schemas/ToolParallelAiSearch' - type: 'null' description: >- Optional. If specified, Vertex AI will use Parallel.ai to search for information to answer user queries. The search results will be grounded on Parallel.ai and presented to the model for response generation. This field is not supported in Gemini API. urlContext: anyOf: - $ref: '#/components/schemas/UrlContext' - type: 'null' description: Optional. Tool to support URL context retrieval. mcpServers: anyOf: - items: $ref: '#/components/schemas/McpServer' type: array - type: 'null' title: Mcpservers description: >- Optional. MCP Servers to connect to. This field is not supported in Vertex AI. exaAiSearch: anyOf: - $ref: '#/components/schemas/ToolExaAiSearch' - type: 'null' description: >- Optional. Uses Exa.ai to search for information to answer user queries. The search results will be grounded on Exa.ai and presented to the model for response generation. This field is not supported in Gemini API. additionalProperties: false type: object title: Tool description: Tool details of a tool that the model may use to generate a response. Retrieval: properties: disableAttribution: anyOf: - type: boolean - type: 'null' title: Disableattribution description: Optional. Deprecated. This option is no longer supported. externalApi: anyOf: - $ref: '#/components/schemas/ExternalApi' - type: 'null' description: Use data source powered by external API for grounding. vertexAiSearch: anyOf: - $ref: '#/components/schemas/VertexAISearch' - type: 'null' description: Set to use data source powered by Vertex AI Search. vertexRagStore: anyOf: - $ref: '#/components/schemas/VertexRagStore' - type: 'null' description: >- Set to use data source powered by Vertex RAG store. User data is uploaded via the VertexRagDataService. additionalProperties: false type: object title: Retrieval description: >- Defines a retrieval tool that model can call to access external knowledge. This data type is not supported in Gemini API. ComputerUse: properties: environment: anyOf: - $ref: '#/components/schemas/Environment' - type: 'null' description: Required. The environment being operated. excludedPredefinedFunctions: anyOf: - items: type: string type: array - type: 'null' title: Excludedpredefinedfunctions description: >- Optional. By default, [predefined functions](https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use#supported-actions) are included in the final model call. Some of them can be explicitly excluded from being automatically included. This can serve two purposes: 1. Using a more restricted / different action space. 2. Improving the definitions / instructions of predefined functions. enablePromptInjectionDetection: anyOf: - type: boolean - type: 'null' title: Enablepromptinjectiondetection description: >- Optional. Enables the prompt injection detection check on computer-use request. disabledSafetyPolicies: anyOf: - items: $ref: '#/components/schemas/SafetyPolicy' type: array - type: 'null' title: Disabledsafetypolicies description: >- Optional. Disabled safety policies for computer use. This field is not supported in Vertex AI. additionalProperties: false type: object title: ComputerUse description: Tool to support computer use. FileSearch: properties: fileSearchStoreNames: anyOf: - items: type: string type: array - type: 'null' title: Filesearchstorenames description: >- Required. The names of the file_search_stores to retrieve from. Example: `fileSearchStores/my-file-search-store-123` topK: anyOf: - type: integer - type: 'null' title: Topk description: Optional. The number of semantic retrieval chunks to retrieve. metadataFilter: anyOf: - type: string - type: 'null' title: Metadatafilter description: >- Optional. Metadata filter to apply to the semantic retrieval documents and chunks. additionalProperties: false type: object title: FileSearch description: >- The FileSearch tool that retrieves knowledge from Semantic Retrieval corpora. Files are imported to Semantic Retrieval corpora using the ImportFile API. This data type is not supported in Vertex AI. GoogleSearch: properties: searchTypes: anyOf: - $ref: '#/components/schemas/SearchTypes' - type: 'null' description: >- Optional. The set of search types to enable. If not set, web search is enabled by default. blockingConfidence: anyOf: - $ref: '#/components/schemas/PhishBlockThreshold' - type: 'null' description: >- Optional. Sites with confidence level chosen & above this value will be blocked from the search results. This field is not supported in Gemini API. excludeDomains: anyOf: - items: type: string type: array - type: 'null' title: Excludedomains description: >- Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. Example: ["amazon.com", "facebook.com"]. This field is not supported in Gemini API. timeRangeFilter: anyOf: - $ref: '#/components/schemas/google__genai__types__Interval' - type: 'null' description: >- Optional. Filter search results to a specific time range. If customers set a start time, they must set an end time (and vice versa). This field is not supported in Vertex AI. additionalProperties: false type: object title: GoogleSearch description: |- GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google. GoogleMaps: properties: authConfig: anyOf: - $ref: '#/components/schemas/google__genai__types__AuthConfig' - type: 'null' description: >- The authentication config to access the API. Only API key is supported. This field is not supported in Gemini API. enableWidget: anyOf: - type: boolean - type: 'null' title: Enablewidget description: >- Deprecated. The Google Maps contextual widget behavior in Grounding with Google Maps is being deprecated; this field is planned for removal and no longer has any effect once removed. Optional. Whether to return a widget context token in the GroundingMetadata of the response. groundingTypes: anyOf: - $ref: '#/components/schemas/GoogleMapsGroundingTypes' - type: 'null' description: >- Optional. Specifies the types of Google Maps grounding to enable. This field is not supported in Gemini API. additionalProperties: false type: object title: GoogleMaps description: Tool to retrieve knowledge from Google Maps. ToolCodeExecution: properties: {} additionalProperties: false type: object title: ToolCodeExecution description: >- Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. This data type is not supported in Gemini API. EnterpriseWebSearch: properties: blockingConfidence: anyOf: - $ref: '#/components/schemas/PhishBlockThreshold' - type: 'null' description: >- Optional. Sites with confidence level chosen & above this value will be blocked from the search results. excludeDomains: anyOf: - items: type: string type: array - type: 'null' title: Excludedomains description: >- Optional. List of domains to be excluded from the search results. The default limit is 2000 domains. additionalProperties: false type: object title: EnterpriseWebSearch description: >- Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. This data type is not supported in Gemini API. FunctionDeclaration: properties: description: anyOf: - type: string - type: 'null' title: Description description: >- Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. name: anyOf: - type: string - type: 'null' title: 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, colons and dashes, with a maximum length of 128. parameters: anyOf: - $ref: '#/components/schemas/Schema' - type: 'null' 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 parametersJsonSchema: anyOf: - {} - type: 'null' title: Parametersjsonschema description: >- Optional. Describes the parameters to the function in JSON Schema format. The schema must describe an object where the properties are the parameters to the function. For example: ``` { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "integer" } }, "additionalProperties": false, "required": ["name", "age"], "propertyOrdering": ["name", "age"] } ``` This field is mutually exclusive with `parameters`. response: anyOf: - $ref: '#/components/schemas/Schema' - type: 'null' 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. responseJsonSchema: anyOf: - {} - type: 'null' title: Responsejsonschema description: >- Optional. Describes the output from this function in JSON Schema format. The value specified by the schema is the response value of the function. This field is mutually exclusive with `response`. behavior: anyOf: - $ref: '#/components/schemas/Behavior' - type: 'null' description: >- Optional. Specifies the function Behavior. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method. additionalProperties: false type: object title: FunctionDeclaration description: >- Structured representation of a function declaration as defined by the [OpenAPI 3.0 specification](https://spec.openapis.org/oas/v3.0.3). Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a `Tool` by the model and executed by the client. GoogleSearchRetrieval: properties: dynamicRetrievalConfig: anyOf: - $ref: '#/components/schemas/DynamicRetrievalConfig' - type: 'null' description: Specifies the dynamic retrieval configuration for the given source. additionalProperties: false type: object title: GoogleSearchRetrieval description: Tool to retrieve public web data for grounding, powered by Google. ToolParallelAiSearch: properties: apiKey: anyOf: - type: string - type: 'null' title: Apikey description: >- Optional. The API key for ParallelAiSearch. If an API key is not provided, the system will attempt to verify access by checking for an active Parallel.ai subscription through the Google Cloud Marketplace. See https://docs.parallel.ai/search/search-quickstart for more details. customConfigs: anyOf: - additionalProperties: true type: object - type: 'null' title: Customconfigs description: >- Optional. Custom configs for ParallelAiSearch. This field can be used to pass any parameter from the Parallel.ai Search API. See the Parallel.ai documentation for the full list of available parameters and their usage: https://docs.parallel.ai/api-reference/search-beta/search Currently only `source_policy`, `excerpts`, `max_results`, `mode`, `fetch_policy` can be set via this field. For example: { "source_policy": { "include_domains": ["google.com", "wikipedia.org"], "exclude_domains": ["example.com"] }, "fetch_policy": { "max_age_seconds": 3600 } } additionalProperties: false type: object title: ToolParallelAiSearch description: >- ParallelAiSearch tool type. A tool that uses the Parallel.ai search engine for grounding. This data type is not supported in Gemini API. UrlContext: properties: {} additionalProperties: false type: object title: UrlContext description: Tool to support URL context. McpServer: properties: name: anyOf: - type: string - type: 'null' title: Name description: The name of the MCPServer. streamableHttpTransport: anyOf: - $ref: '#/components/schemas/StreamableHttpTransport' - type: 'null' description: A transport that can stream HTTP requests and responses. additionalProperties: false type: object title: McpServer description: >- A MCPServer is a server that can be called by the model to perform actions. It is a server that implements the MCP protocol. Next ID: 6. This data type is not supported in Vertex AI. ToolExaAiSearch: properties: apiKey: anyOf: - type: string - type: 'null' title: Apikey description: Required. The API key for ExaAiSearch. customConfigs: anyOf: - additionalProperties: true type: object - type: 'null' title: Customconfigs description: >- Optional. This field can be used to pass any parameter from the Exa.ai Search API. additionalProperties: false type: object title: ToolExaAiSearch description: >- ExaAiSearch tool type. A tool that uses the Exa.ai search engine for grounding. This data type is not supported in Gemini API. ExternalApi: properties: apiAuth: anyOf: - $ref: '#/components/schemas/ApiAuth' - type: 'null' description: >- The authentication config to access the API. Deprecated. Please use auth_config instead. apiSpec: anyOf: - $ref: '#/components/schemas/ApiSpec' - type: 'null' description: The API spec that the external API implements. authConfig: anyOf: - $ref: '#/components/schemas/google__genai__types__AuthConfig' - type: 'null' description: The authentication config to access the API. elasticSearchParams: anyOf: - $ref: '#/components/schemas/ExternalApiElasticSearchParams' - type: 'null' description: Parameters for the elastic search API. endpoint: anyOf: - type: string - type: 'null' title: Endpoint description: >- The endpoint of the external API. The system will call the API at this endpoint to retrieve the data for grounding. Example: https://acme.com:443/search simpleSearchParams: anyOf: - $ref: '#/components/schemas/ExternalApiSimpleSearchParams' - type: 'null' description: Parameters for the simple search API. additionalProperties: false type: object title: ExternalApi description: >- Retrieve from data source powered by external API for grounding. The external API is not owned by Google, but need to follow the pre-defined API spec. This data type is not supported in Gemini API. VertexAISearch: properties: dataStoreSpecs: anyOf: - items: $ref: '#/components/schemas/VertexAISearchDataStoreSpec' type: array - type: 'null' title: Datastorespecs description: >- Specifications that define the specific DataStores to be searched, along with configurations for those data stores. This is only considered for Engines with multiple data stores. It should only be set if engine is used. datastore: anyOf: - type: string - type: 'null' title: Datastore description: >- Optional. Fully-qualified Vertex AI Search data store resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}` engine: anyOf: - type: string - type: 'null' title: Engine description: >- Optional. Fully-qualified Vertex AI Search engine resource ID. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}` filter: anyOf: - type: string - type: 'null' title: Filter description: Optional. Filter strings to be passed to the search API. maxResults: anyOf: - type: integer - type: 'null' title: Maxresults description: >- Optional. Number of search results to return per query. The default value is 10. The maximumm allowed value is 10. additionalProperties: false type: object title: VertexAISearch description: |- Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder. This data type is not supported in Gemini API. VertexRagStore: properties: ragCorpora: anyOf: - items: type: string type: array - type: 'null' title: Ragcorpora description: Optional. Deprecated. Please use rag_resources instead. ragResources: anyOf: - items: $ref: '#/components/schemas/VertexRagStoreRagResource' type: array - type: 'null' title: 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. ragRetrievalConfig: anyOf: - $ref: '#/components/schemas/RagRetrievalConfig' - type: 'null' description: Optional. The retrieval config for the Rag query. similarityTopK: anyOf: - type: integer - type: 'null' title: Similaritytopk description: >- Optional. Number of top k results to return from the selected corpora. storeContext: anyOf: - type: boolean - type: 'null' title: Storecontext description: >- Optional. Currently only supported for Gemini Multimodal Live API. In Gemini Multimodal Live API, if `store_context` bool is specified, Gemini will leverage it to automatically memorize the interactions between the client and Gemini, and retrieve context when needed to augment the response generation for users' ongoing and future interactions. vectorDistanceThreshold: anyOf: - type: number - type: 'null' title: Vectordistancethreshold description: >- Optional. Only return results with vector distance smaller than the threshold. additionalProperties: false type: object title: VertexRagStore description: |- Retrieve from Vertex RAG Store for grounding. This data type is not supported in Gemini API. Environment: type: string enum: - ENVIRONMENT_UNSPECIFIED - ENVIRONMENT_BROWSER - ENVIRONMENT_MOBILE - ENVIRONMENT_DESKTOP title: Environment description: The environment being operated. SafetyPolicy: type: string enum: - SAFETY_POLICY_UNSPECIFIED - FINANCIAL_TRANSACTIONS - SENSITIVE_DATA_MODIFICATION - COMMUNICATION_TOOL - ACCOUNT_CREATION - DATA_MODIFICATION - USER_CONSENT_MANAGEMENT - LEGAL_TERMS_AND_AGREEMENTS title: SafetyPolicy description: SafetyPolicy SearchTypes: properties: webSearch: anyOf: - $ref: '#/components/schemas/WebSearch' - type: 'null' description: >- Optional. Setting this field enables web search. Only text results are returned. imageSearch: anyOf: - $ref: '#/components/schemas/ImageSearch' - type: 'null' description: >- Optional. Setting this field enables image search. Image bytes are returned. additionalProperties: false type: object title: SearchTypes description: Different types of search that can be enabled on the GoogleSearch tool. PhishBlockThreshold: type: string enum: - PHISH_BLOCK_THRESHOLD_UNSPECIFIED - BLOCK_LOW_AND_ABOVE - BLOCK_MEDIUM_AND_ABOVE - BLOCK_HIGH_AND_ABOVE - BLOCK_HIGHER_AND_ABOVE - BLOCK_VERY_HIGH_AND_ABOVE - BLOCK_ONLY_EXTREMELY_HIGH title: PhishBlockThreshold description: >- Sites with confidence level chosen & above this value will be blocked from the search results. This enum is not supported in Gemini API. google__genai__types__Interval: properties: endTime: anyOf: - type: string format: date-time - type: 'null' title: Endtime description: >- Optional. Exclusive end of the interval. If specified, a Timestamp matching this interval will have to be before the end. startTime: anyOf: - type: string format: date-time - type: 'null' title: Starttime description: >- Optional. Inclusive start of the interval. If specified, a Timestamp matching this interval will have to be the same or after the start. additionalProperties: false type: object title: Interval description: >- Represents a time interval, encoded as a Timestamp start (inclusive) and a Timestamp end (exclusive). The start must be less than or equal to the end. When the start equals the end, the interval is empty (matches no time). When both start and end are unspecified, the interval matches any time. google__genai__types__AuthConfig: properties: apiKey: anyOf: - type: string - type: 'null' title: Apikey description: >- The authentication config to access the API. Only API key is supported. This field is not supported in Gemini API. apiKeyConfig: anyOf: - $ref: '#/components/schemas/ApiKeyConfig' - type: 'null' description: Config for API key auth. authType: anyOf: - $ref: '#/components/schemas/AuthType' - type: 'null' description: Type of auth scheme. googleServiceAccountConfig: anyOf: - $ref: '#/components/schemas/AuthConfigGoogleServiceAccountConfig' - type: 'null' description: Config for Google Service Account auth. httpBasicAuthConfig: anyOf: - $ref: '#/components/schemas/AuthConfigHttpBasicAuthConfig' - type: 'null' description: Config for HTTP Basic auth. oauthConfig: anyOf: - $ref: '#/components/schemas/AuthConfigOauthConfig' - type: 'null' description: Config for user oauth. oidcConfig: anyOf: - $ref: '#/components/schemas/AuthConfigOidcConfig' - type: 'null' description: Config for user OIDC auth. additionalProperties: false type: object title: AuthConfig description: The authentication config to access the API. GoogleMapsGroundingTypes: properties: places: anyOf: - $ref: '#/components/schemas/GoogleMapsPlaces' - type: 'null' description: >- Optional. Enables grounding with Google Maps Places. This is the default grounding type when no `GroundingTypes` are specified. routing: anyOf: - $ref: '#/components/schemas/GoogleMapsRouting' - type: 'null' description: >- Optional. Enables grounding with Google Maps Routing APIs (ComputeRoutes and SearchAlongRoute). additionalProperties: false type: object title: GoogleMapsGroundingTypes description: >- Defines the types of Google Maps grounding that can be enabled and their configurations. This data type is not supported in Gemini API. Schema: properties: additionalProperties: anyOf: - {} - type: 'null' title: Additionalproperties description: >- Optional. Can either be a boolean or an object; controls the presence of additional properties. defs: anyOf: - additionalProperties: $ref: '#/components/schemas/Schema' type: object - type: 'null' title: Defs description: >- Optional. A map of definitions for use by `ref` Only allowed at the root of the schema. ref: anyOf: - type: string - type: 'null' title: Ref description: >- Optional. Allows indirect references between schema nodes. The value should be a valid reference to a child of the root `defs`. For example, the following schema defines a reference to a schema node named "Pet": type: object properties: pet: ref: #/defs/Pet defs: Pet: type: object properties: name: type: string The value of the "pet" property is a reference to the schema node named "Pet". See details in https://json-schema.org/understanding-json-schema/structuring anyOf: anyOf: - items: $ref: '#/components/schemas/Schema' type: array - type: 'null' title: Anyof description: >- Optional. The instance must be valid against any (one or more) of the subschemas listed in `any_of`. default: anyOf: - {} - type: 'null' title: Default description: Optional. Default value to use if the field is not specified. description: anyOf: - type: string - type: 'null' title: Description description: >- Optional. Describes the data. The model uses this field to understand the purpose of the schema and how to use it. It is a best practice to provide a clear and descriptive explanation for the schema and its properties here, rather than in the prompt. enum: anyOf: - items: type: string type: array - type: 'null' title: Enum description: >- Optional. Possible values of the field. This field can be used to restrict a value to a fixed set of values. To mark a field as an enum, set `format` to `enum` and provide the list of possible values in `enum`. For example: 1. To define directions: `{type:STRING, format:enum, enum:["EAST", "NORTH", "SOUTH", "WEST"]}` 2. To define apartment numbers: `{type:INTEGER, format:enum, enum:["101", "201", "301"]}` example: anyOf: - {} - type: 'null' title: Example description: Optional. Example of an instance of this schema. format: anyOf: - type: string - type: 'null' title: Format description: >- Optional. The format of the data. For `NUMBER` type, format can be `float` or `double`. For `INTEGER` type, format can be `int32` or `int64`. For `STRING` type, format can be `email`, `byte`, `date`, `date-time`, `password`, and other formats to further refine the data type. items: anyOf: - $ref: '#/components/schemas/Schema' - type: 'null' description: >- Optional. If type is `ARRAY`, `items` specifies the schema of elements in the array. maxItems: anyOf: - type: integer - type: 'null' title: Maxitems description: >- Optional. If type is `ARRAY`, `max_items` specifies the maximum number of items in an array. maxLength: anyOf: - type: integer - type: 'null' title: Maxlength description: >- Optional. If type is `STRING`, `max_length` specifies the maximum length of the string. maxProperties: anyOf: - type: integer - type: 'null' title: Maxproperties description: >- Optional. If type is `OBJECT`, `max_properties` specifies the maximum number of properties that can be provided. maximum: anyOf: - type: number - type: 'null' title: Maximum description: >- Optional. If type is `INTEGER` or `NUMBER`, `maximum` specifies the maximum allowed value. minItems: anyOf: - type: integer - type: 'null' title: Minitems description: >- Optional. If type is `ARRAY`, `min_items` specifies the minimum number of items in an array. minLength: anyOf: - type: integer - type: 'null' title: Minlength description: >- Optional. If type is `STRING`, `min_length` specifies the minimum length of the string. minProperties: anyOf: - type: integer - type: 'null' title: Minproperties description: >- Optional. If type is `OBJECT`, `min_properties` specifies the minimum number of properties that can be provided. minimum: anyOf: - type: number - type: 'null' title: Minimum description: >- Optional. If type is `INTEGER` or `NUMBER`, `minimum` specifies the minimum allowed value. nullable: anyOf: - type: boolean - type: 'null' title: Nullable description: Optional. Indicates if the value of this field can be null. pattern: anyOf: - type: string - type: 'null' title: Pattern description: >- Optional. If type is `STRING`, `pattern` specifies a regular expression that the string must match. properties: anyOf: - additionalProperties: $ref: '#/components/schemas/Schema' type: object - type: 'null' title: Properties description: >- Optional. If type is `OBJECT`, `properties` is a map of property names to schema definitions for each property of the object. propertyOrdering: anyOf: - items: type: string type: array - type: 'null' title: Propertyordering description: >- Optional. Order of properties displayed or used where order matters. This is not a standard field in OpenAPI specification, but can be used to control the order of properties. required: anyOf: - items: type: string type: array - type: 'null' title: Required description: >- Optional. If type is `OBJECT`, `required` lists the names of properties that must be present. title: anyOf: - type: string - type: 'null' title: Title description: Optional. Title for the schema. type: anyOf: - $ref: '#/components/schemas/Type' - type: 'null' description: Optional. Data type of the schema field. additionalProperties: false type: object title: Schema description: >- Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema-object). More fields may be added in the future as needed. Behavior: type: string enum: - UNSPECIFIED - BLOCKING - NON_BLOCKING title: Behavior description: >- Specifies the function Behavior. If not specified, the system keeps the current function call behavior. This field is currently only supported by the BidiGenerateContent method. DynamicRetrievalConfig: properties: dynamicThreshold: anyOf: - type: number - type: 'null' title: Dynamicthreshold description: >- Optional. The threshold to be used in dynamic retrieval. If not set, a system default value is used. mode: anyOf: - $ref: '#/components/schemas/DynamicRetrievalConfigMode' - type: 'null' description: The mode of the predictor to be used in dynamic retrieval. additionalProperties: false type: object title: DynamicRetrievalConfig description: Describes the options to customize dynamic retrieval. StreamableHttpTransport: properties: headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Headers description: >- Optional: Fields for authentication headers, timeouts, etc., if needed. sseReadTimeout: anyOf: - type: string - type: 'null' title: Ssereadtimeout description: Timeout for SSE read operations. terminateOnClose: anyOf: - type: boolean - type: 'null' title: Terminateonclose description: Whether to close the client session when the transport closes. timeout: anyOf: - type: string - type: 'null' title: Timeout description: HTTP timeout for regular operations. url: anyOf: - type: string - type: 'null' title: Url description: >- The full URL for the MCPServer endpoint. Example: "https://api.example.com/mcp". additionalProperties: false type: object title: StreamableHttpTransport description: |- A transport that can stream HTTP requests and responses. Next ID: 6. This data type is not supported in Vertex AI. ApiAuth: properties: apiKeyConfig: anyOf: - $ref: '#/components/schemas/ApiAuthApiKeyConfig' - type: 'null' description: The API secret. additionalProperties: false type: object title: ApiAuth description: >- The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. This data type is not supported in Gemini API. ApiSpec: type: string enum: - API_SPEC_UNSPECIFIED - SIMPLE_SEARCH - ELASTIC_SEARCH title: ApiSpec description: |- The API spec that the external API implements. This enum is not supported in Gemini API. ExternalApiElasticSearchParams: properties: index: anyOf: - type: string - type: 'null' title: Index description: The ElasticSearch index to use. numHits: anyOf: - type: integer - type: 'null' title: Numhits description: >- Optional. Number of hits (chunks) to request. When specified, it is passed to Elasticsearch as the `num_hits` param. searchTemplate: anyOf: - type: string - type: 'null' title: Searchtemplate description: The ElasticSearch search template to use. additionalProperties: false type: object title: ExternalApiElasticSearchParams description: |- The search parameters to use for the ELASTIC_SEARCH spec. This data type is not supported in Gemini API. ExternalApiSimpleSearchParams: properties: {} additionalProperties: false type: object title: ExternalApiSimpleSearchParams description: |- The search parameters to use for SIMPLE_SEARCH spec. This data type is not supported in Gemini API. VertexAISearchDataStoreSpec: properties: dataStore: anyOf: - type: string - type: 'null' title: Datastore description: >- Full resource name of DataStore, such as Format: `projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}` filter: anyOf: - type: string - type: 'null' title: Filter description: >- Optional. Filter specification to filter documents in the data store specified by data_store field. For more information on filtering, see [Filtering](https://cloud.google.com/generative-ai-app-builder/docs/filter-search-metadata) additionalProperties: false type: object title: VertexAISearchDataStoreSpec description: >- Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec. This data type is not supported in Gemini API. VertexRagStoreRagResource: properties: ragCorpus: anyOf: - type: string - type: 'null' title: Ragcorpus description: >- Optional. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` ragFileIds: anyOf: - items: type: string type: array - type: 'null' title: Ragfileids description: >- Optional. rag_file_id. The files should be in the same rag_corpus set in rag_corpus field. additionalProperties: false type: object title: VertexRagStoreRagResource description: |- The definition of the Rag resource. This data type is not supported in Gemini API. RagRetrievalConfig: properties: filter: anyOf: - $ref: '#/components/schemas/RagRetrievalConfigFilter' - type: 'null' description: Optional. Config for filters. hybridSearch: anyOf: - $ref: '#/components/schemas/RagRetrievalConfigHybridSearch' - type: 'null' description: Optional. Config for Hybrid Search. ranking: anyOf: - $ref: '#/components/schemas/RagRetrievalConfigRanking' - type: 'null' description: Optional. Config for ranking and reranking. topK: anyOf: - type: integer - type: 'null' title: Topk description: Optional. The number of contexts to retrieve. additionalProperties: false type: object title: RagRetrievalConfig description: |- Specifies the context retrieval config. This data type is not supported in Gemini API. WebSearch: properties: {} additionalProperties: false type: object title: WebSearch description: |- Standard web search for grounding and related configurations. Only text results are returned. ImageSearch: properties: {} additionalProperties: false type: object title: ImageSearch description: Image search for grounding and related configurations. ApiKeyConfig: properties: apiKeySecret: anyOf: - type: string - type: 'null' title: Apikeysecret description: >- Optional. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If both `api_key_secret` and `api_key_string` are specified, this field takes precedence over `api_key_string`. - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. apiKeyString: anyOf: - type: string - type: 'null' title: Apikeystring description: Optional. The API key to be used in the request directly. httpElementLocation: anyOf: - $ref: '#/components/schemas/HttpElementLocation' - type: 'null' description: Optional. The location of the API key. name: anyOf: - type: string - type: 'null' title: Name description: >- Optional. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. additionalProperties: false type: object title: ApiKeyConfig description: |- Config for authentication with API key. This data type is not supported in Gemini API. AuthType: type: string enum: - AUTH_TYPE_UNSPECIFIED - NO_AUTH - API_KEY_AUTH - HTTP_BASIC_AUTH - GOOGLE_SERVICE_ACCOUNT_AUTH - OAUTH - OIDC_AUTH title: AuthType description: Type of auth scheme. This enum is not supported in Gemini API. AuthConfigGoogleServiceAccountConfig: properties: serviceAccount: anyOf: - type: string - type: 'null' title: Serviceaccount description: >- Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. additionalProperties: false type: object title: AuthConfigGoogleServiceAccountConfig description: |- Config for Google Service Account Authentication. This data type is not supported in Gemini API. AuthConfigHttpBasicAuthConfig: properties: credentialSecret: anyOf: - type: string - type: 'null' title: Credentialsecret description: >- Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. additionalProperties: false type: object title: AuthConfigHttpBasicAuthConfig description: |- Config for HTTP Basic Authentication. This data type is not supported in Gemini API. AuthConfigOauthConfig: properties: accessToken: anyOf: - type: string - type: 'null' title: Accesstoken description: >- Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. serviceAccount: anyOf: - type: string - type: 'null' title: Serviceaccount description: >- The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. additionalProperties: false type: object title: AuthConfigOauthConfig description: Config for user oauth. This data type is not supported in Gemini API. AuthConfigOidcConfig: properties: idToken: anyOf: - type: string - type: 'null' title: Idtoken description: >- OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. serviceAccount: anyOf: - type: string - type: 'null' title: Serviceaccount description: >- The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). additionalProperties: false type: object title: AuthConfigOidcConfig description: |- Config for user OIDC auth. This data type is not supported in Gemini API. GoogleMapsPlaces: properties: {} additionalProperties: false type: object title: GoogleMapsPlaces description: >- Grounding with Google Maps Places data (e.g. QueryPlaces). This is the default Google Maps grounding type when no other type is specified. This data type is not supported in Gemini API. GoogleMapsRouting: properties: {} additionalProperties: false type: object title: GoogleMapsRouting description: >- Grounding with Google Maps Routing APIs (ComputeRoutes and SearchAlongRoute). This data type is not supported in Gemini API. Type: type: string enum: - TYPE_UNSPECIFIED - STRING - NUMBER - INTEGER - BOOLEAN - ARRAY - OBJECT - 'NULL' title: Type description: Data type of the schema field. DynamicRetrievalConfigMode: type: string enum: - MODE_UNSPECIFIED - MODE_DYNAMIC title: DynamicRetrievalConfigMode description: The mode of the predictor to be used in dynamic retrieval. ApiAuthApiKeyConfig: properties: apiKeySecretVersion: anyOf: - type: string - type: 'null' title: Apikeysecretversion description: >- Required. The SecretManager secret version resource name storing API key. e.g. projects/{project}/secrets/{secret}/versions/{version} apiKeyString: anyOf: - type: string - type: 'null' title: Apikeystring description: >- The API key string. Either this or `api_key_secret_version` must be set. additionalProperties: false type: object title: ApiAuthApiKeyConfig description: The API secret. This data type is not supported in Gemini API. RagRetrievalConfigFilter: properties: metadataFilter: anyOf: - type: string - type: 'null' title: Metadatafilter description: Optional. String for metadata filtering. vectorDistanceThreshold: anyOf: - type: number - type: 'null' title: Vectordistancethreshold description: >- Optional. Only returns contexts with vector distance smaller than the threshold. vectorSimilarityThreshold: anyOf: - type: number - type: 'null' title: Vectorsimilaritythreshold description: >- Optional. Only returns contexts with vector similarity larger than the threshold. additionalProperties: false type: object title: RagRetrievalConfigFilter description: Config for filters. This data type is not supported in Gemini API. RagRetrievalConfigHybridSearch: properties: alpha: anyOf: - type: number - type: 'null' title: Alpha description: >- Optional. Alpha value controls the weight between dense and sparse vector search results. The range is [0, 1], while 0 means sparse vector search only and 1 means dense vector search only. The default value is 0.5 which balances sparse and dense vector search equally. additionalProperties: false type: object title: RagRetrievalConfigHybridSearch description: Config for Hybrid Search. This data type is not supported in Gemini API. RagRetrievalConfigRanking: properties: llmRanker: anyOf: - $ref: '#/components/schemas/RagRetrievalConfigRankingLlmRanker' - type: 'null' description: Optional. Config for LlmRanker. rankService: anyOf: - $ref: '#/components/schemas/RagRetrievalConfigRankingRankService' - type: 'null' description: Optional. Config for Rank Service. additionalProperties: false type: object title: RagRetrievalConfigRanking description: |- Config for ranking and reranking. This data type is not supported in Gemini API. HttpElementLocation: type: string enum: - HTTP_IN_UNSPECIFIED - HTTP_IN_QUERY - HTTP_IN_HEADER - HTTP_IN_PATH - HTTP_IN_BODY - HTTP_IN_COOKIE title: HttpElementLocation description: The location of the API key. This enum is not supported in Gemini API. RagRetrievalConfigRankingLlmRanker: properties: modelName: anyOf: - type: string - type: 'null' title: 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). additionalProperties: false type: object title: RagRetrievalConfigRankingLlmRanker description: Config for LlmRanker. This data type is not supported in Gemini API. RagRetrievalConfigRankingRankService: properties: modelName: anyOf: - type: string - type: 'null' title: Modelname description: >- Optional. The model name of the rank service. Format: `semantic-ranker-512@latest` additionalProperties: false type: object title: RagRetrievalConfigRankingRankService description: Config for Rank Service. This data type is not supported in Gemini API. ```` ## Related topics - [List Metrics Info](/api-reference/evaluation/list-metrics-info.md) - [List Apps](/api-reference/list-apps.md) - [Get App Graph Dot](/api-reference/debug/get-app-graph-dot.md) - [Get Session History](/api-reference/adk/get-session-history.md) - [Get Session Trace](/api-reference/adk/get-session-trace.md)