Package com.google.genai.types
Class VertexRagStore
java.lang.Object
com.google.genai.JsonSerializable
com.google.genai.types.VertexRagStore
Retrieve from Vertex RAG Store for grounding.
-
Nested Class Summary
Nested Classes -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionstatic VertexRagStore.Builder
builder()
Instantiates a builder for VertexRagStore.static VertexRagStore
Deserializes a JSON string to a VertexRagStore object.Optional.abstract Optional<List<VertexRagStoreRagResource>>
Optional.abstract Optional<RagRetrievalConfig>
Optional.Optional.Optional.abstract VertexRagStore.Builder
Creates a builder with the same values as this instance.Optional.Methods inherited from class com.google.genai.JsonSerializable
stringToJsonNode, toJson
-
Constructor Details
-
VertexRagStore
public VertexRagStore()
-
-
Method Details
-
ragCorpora
Optional. Deprecated. Please use rag_resources instead. -
ragResources
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
Optional. The retrieval config for the Rag query. -
similarityTopK
Optional. Number of top k results to return from the selected corpora. -
storeContext
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
Optional. Only return results with vector distance smaller than the threshold. -
builder
Instantiates a builder for VertexRagStore. -
toBuilder
Creates a builder with the same values as this instance. -
fromJson
Deserializes a JSON string to a VertexRagStore object.
-