VertexAiRagClientTool
A client-side retrieval tool that fetches context from a Vertex AI RAG corpus.
Unlike VertexAiRagRetrieval, which grounds the model natively via vertexRagStore, this tool runs the retrieval itself: run queries the Vertex AI RAG service through a VertexAiRagClient and returns the matching context texts, so it works on any model as an ordinary function tool. The corpus and vectorDistanceThreshold are fixed per instance; the model supplies query and an optional similarityTopK per call.
Constructors
Types
Fluent builder for VertexAiRagClientTool, 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.
Functions
Returns a workflow node that runs this tool as a fixed step: the predecessor's output becomes the tool's arguments, and the tool's result becomes the node's output.
Returns the underlying function declaration.
Processes the LLM request before it is sent.