Standalone Knowledge Manager
Agentic RAG in Agent
When RAG is configured in an agent, the SDK automatically creates asearchKnowledge tool that the LLM can decide when to use. This is more efficient than always searching, as the LLM only searches when necessary.
Multiple Vector Stores
Managing Documents
Add text documents:RAG Interceptor & Rerank
Interceptor - Filter & Transform Results:reciprocal-rank-fusion- Standard RRF algorithmscore-boost- Boost results containing keywordsmetadata-weight- Weight by metadata field valuecustom- Custom scoring function
Next Steps
Agents
Learn about agents
Use Cases
See RAG examples