This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
What does GraphRAG add to a standard RAG pipeline?
A replacement for vector search that removes embeddings
A knowledge graph so retrieval can follow relationships before ranking with embeddings
A new fine-tuned model trained on policies
When results are combined from vector and keyword searches, what simple method helps merge rankings?
L2 normalization of all vectors
Cross join of both result sets
Reciprocal Rank Fusion
What SQL statement is useful to check timing and confirm a vector index is used?
DESCRIBE TABLE on the target relation
EXPLAIN (ANALYZE, BUFFERS) followed by the query
VACUUM ANALYZE on the database
You must answer all questions before checking your work.
Was this page helpful?
Need help with this topic?
Want to try using Ask Learn to clarify or guide you through this topic?