Optimize the recall strategy of the vector database

gpt-open / rag-gpt

RAG-GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.

Apache License 2.0

333 stars 54 forks source link

Optimize the recall strategy of the vector database #23

Closed blmdxiao closed 7 months ago

blmdxiao commented 7 months ago

collection_metadata = {"hnsw:space": "cosine"} replace 'l2' with 'cosine'.