Method: locations.augmentPrompt

Full name: projects.locations.augmentPrompt

Given an input prompt, it returns augmented prompt from vertex rag store to guide LLM towards generating grounded responses.

Endpoint

post https://{service-endpoint}/v1/{parent}:augmentPrompt

Where {service-endpoint} is one of the supported service endpoints.

Path parameters

parent string

Required. The resource name of the Location from which to augment prompt. The users must have permission to make a call in the project. Format: projects/{project}/locations/{location}.

Request body

The request body contains data with the following structure:

Fields
contents[] object (Content)

Optional. Input content to augment, only text format is supported for now.

model object (Model)

Optional. metadata of the backend deployed model.

data_source Union type
The data source for retrieving contexts. data_source can be only one of the following:
vertexRagStore object (VertexRagStore)

Optional. Retrieves contexts from the Vertex RagStore.

Response body

Response message for locations.augmentPrompt.

If successful, the response body contains data with the following structure:

Fields
augmentedPrompt[] object (Content)

Augmented prompt, only text format is supported for now.

facts[] object (Fact)

Retrieved facts from RAG data sources.

JSON representation 
{
  "augmentedPrompt": [
    {
      object (Content)
    }
  ],
  "facts": [
    {
      object (Fact)
    }
  ]
}

Model

metadata of the backend deployed model.

Fields
model string

Optional. The model that the user will send the augmented prompt for content generation.

modelVersion string

Optional. The model version of the backend deployed model.

JSON representation 
{
  "model": string,
  "modelVersion": string
}