Interface VertexRagStore

Retrieve from Vertex RAG Store for grounding. This data type is not supported in Gemini API.

interface VertexRagStore {
    ragCorpora?: string[];
    ragResources?: VertexRagStoreRagResource[];
    ragRetrievalConfig?: RagRetrievalConfig;
    similarityTopK?: number;
    storeContext?: boolean;
    vectorDistanceThreshold?: number;
}

Properties

ragCorpora? ragResources? ragRetrievalConfig? similarityTopK? storeContext? vectorDistanceThreshold?

Properties

OptionalragCorpora

ragCorpora?: string[]

Optional. Deprecated. Please use rag_resources instead.

OptionalragResources

ragResources?: VertexRagStoreRagResource[]

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.

OptionalragRetrievalConfig

ragRetrievalConfig?: RagRetrievalConfig

Optional. The retrieval config for the Rag query.

OptionalsimilarityTopK

similarityTopK?: number

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

OptionalstoreContext

storeContext?: boolean

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.

OptionalvectorDistanceThreshold

vectorDistanceThreshold?: number

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

Settings

On This Page

Properties