Retrieval Config • AI Agent SDK

RetrievalConfig: Unified configuration for Agent retrieval behavior.

RetrievalConfig

Defined in the Retrieval Config module.

Unified configuration for Agent retrieval behavior.

This is the SINGLE configuration surface that replaces:

• knowledge_config
• rag_config

Attributes: enabled: Whether retrieval is enabled (default: True if knowledge provided) policy: When to retrieve (auto, always, never) top_k: Number of chunks to retrieve min_score: Minimum relevance score threshold (0.0-1.0) max_context_tokens: Maximum tokens for retrieved context rerank: Whether to rerank results for better relevance hybrid: Whether to use hybrid retrieval (dense + keyword) citations: Whether to include source citations citations_mode: How to include citations (append, inline, hidden)

# Vector store configuration vector_store_provider: Vector store provider (chroma, mongodb, etc.) vector_store_config: Provider-specific configuration collection_name: Collection/index name persist_path: Path for persistent storage

# Embedding configuration embedder_provider: Embedding provider embedder_model: Embedding model name

# Advanced options auto_keywords: Keywords that trigger retrieval in auto mode auto_min_length: Minimum query length for auto retrieval context_template: Template for formatting retrieved context system_separation: Whether to use system prompt separation for safety

Properties

Methods

Source

Related Documentation