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

posthttps://{service-endpoint}/v1/{parent}:augmentPrompt

Where{service-endpoint} is one of thesupported service endpoints.

Path parameters

parentstring

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.

modelobject (Model)

Optional. metadata of the backend deployed model.

data_sourceUnion type
The data source for retrieving contexts.data_source can be only one of the following:
vertexRagStoreobject (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
modelstring

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

modelVersionstring

Optional. The model version of the backend deployed model.

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

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-06-27 UTC.