google-genai-kotlin/com.google.genai.kotlin.types/VertexRagStore

VertexRagStore

@Serializable

data class VertexRagStore(val ragCorpora: List<String>? = null, val ragResources: List<VertexRagStoreRagResource>? = null, val ragRetrievalConfig: RagRetrievalConfig? = null, val similarityTopK: Int? = null, val storeContext: Boolean? = null, val vectorDistanceThreshold: Double? = null)

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

Constructors

VertexRagStore

constructor(ragCorpora: List<String>? = null, ragResources: List<VertexRagStoreRagResource>? = null, ragRetrievalConfig: RagRetrievalConfig? = null, similarityTopK: Int? = null, storeContext: Boolean? = null, vectorDistanceThreshold: Double? = null)

Properties

ragCorpora

val ragCorpora: List<String>? = null

Optional. Deprecated. Please use rag_resources instead.

ragResources

val ragResources: List<VertexRagStoreRagResource>? = null

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

val ragRetrievalConfig: RagRetrievalConfig? = null

Optional. The retrieval config for the Rag query.

similarityTopK

val similarityTopK: Int? = null

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

storeContext

val storeContext: Boolean? = null

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

val vectorDistanceThreshold: Double? = null

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