Retriever Provider¶
Retriever Provider gives an Agent a search tool over documents stored in a vector collection. Point it at the same collection and embedding setup used for ingestion so the Agent can bring relevant source passages into its answers.
- Category: Tool
- Purpose: Provides a vector search tool to agents
- Inputs: Vector store and embeddings connections
- Outputs:
retriever_tool- Search tool for agents - Configuration:
- Credential: PostgreSQL connection (required)
- Collection Name: Must match the collection name used in Vector Store Orchestrator exactly. A mismatch returns no results without raising an error
- Search Type:
similarity(closest matches) ormmr(relevant but diverse matches). Defaultsimilarity - Search K: 1–50, default 6. Number of chunks to retrieve
- Score Threshold: 0.0–1.0, step 0.05, default 0.0. Labelled Inclusive to Strict. Raising it prevents weakly related chunks from reaching the agent
- Enable Metadata Filtering: Default off. Reveals the two fields below
- Metadata Filter: Filter rules as JSON, matched against metadata added in Vector Store Orchestrator
- Filter Strategy:
exact,contains, oror. Defaultexact