VertexAiRagRetrieval
A built-in tool that uses Vertex AI RAG (Retrieval-Augmented Generation) to retrieve data.
The model runs retrieval internally via the Gemini-native vertexRagStore retrieval kind; the tool performs no local execution.
Types
Fluent builder for VertexAiRagRetrieval, provided primarily for Java callers. Any property left unset falls back to the same default as the constructor.
Properties
The custom metadata of the tool.
The description of the tool.
Whether the tool's final result will be delivered out-of-band. When true, the framework marks the call as long-running and uses the tool's return value as the function-response payload. Returning Unit means "no response yet": the FR event is suppressed so the function-call event (which carries the call id in longRunningToolIds and is thus the turn's final response) ends the turn without re-invoking the model. A non-Unit return -- including an explicit empty Map -- is treated as a real response and emitted. (Unit suppression aligns with Python; Java instead always emits {}.) The longRunningToolIds id also drives the resumable-mode pause gate so the invocation can be resumed later via a user-injected function-response.
Deprecated. Use ragResources instead. RagCorpora resource names.
The RAG sources to retrieve from (one corpus, or files from one corpus).
Number of top k results to return from the selected corpora.
Only return results with a vector distance below the threshold.
Functions
Returns the underlying function declaration.
Processes the LLM request before it is sent.