Tool

Tool details that the model may use to generate response.

A Tool is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval).

JSON representation 
{
  "functionDeclarations": [
    {
      object (FunctionDeclaration)
    }
  ],
  "retrieval": {
    object (Retrieval)
  }
}
Fields
functionDeclarations[]

object (FunctionDeclaration)

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][content.part.function_call] in the response. user should provide a [FunctionResponse][content.part.function_response] for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided.
retrieval

object (Retrieval)

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.

Retrieval

Defines a retrieval tool that model can call to access external knowledge.

JSON representation 
{
  "disableAttribution": boolean,

  // Union field source can be only one of the following:
  "vertexAiSearch": {
    object (VertexAISearch)
  },
  "vertexRagStore": {
    object (VertexRagStore)
  }
  // End of list of possible types for union field source.
}
Fields
disableAttribution

boolean

Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation.
Union field source. The source of the retrieval. source can be only one of the following:
vertexRagStore

object (VertexRagStore)

Set to use data source powered by Vertex RAG store. user data is uploaded via the VertexRagDataService.

VertexAISearch

Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation

JSON representation 
{
  "datastore": string
}
Fields
datastore

string

Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}

VertexRagStore

Retrieve from Vertex RAG Store for grounding.

JSON representation 
{
  "ragCorpora": [
    string
  ],
  "ragResources": [
    {
      object (RagResource)
    }
  ],
  "similarityTopK": integer,
  "vectorDistanceThreshold": number
}
Fields
ragCorpora[]

string

Optional. Deprecated. Please use ragResources instead.
ragResources[]

object (RagResource)

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.
similarityTopK

integer

Optional. Number of top k results to return from the selected corpora.
vectorDistanceThreshold

number

Optional. Only return results with vector distance smaller than the threshold.

RagResource

The definition of the Rag resource.

JSON representation 
{
  "ragCorpus": string,
  "ragFileIds": [
    string
  ]
}
Fields
ragCorpus

string

Optional. RagCorpora resource name. Format: projects/{project}/locations/{location}/ragCorpora/{ragCorpus}
ragFileIds[]

string

Optional. ragFileId. The files should be in the same ragCorpus set in ragCorpus field.