Comment by RevEng 3 hours ago The article shows an example of hybrid search using RRF. 1 comment RevEng Reply storus 3 hours ago With BM25 which has a far worse/non-generalizable performance than sparse embeddings Pinecone supports. Moreover you get a latency hit from RRF that makes it challenging to use for e.g. real-time multimodal chat agents.
storus 3 hours ago With BM25 which has a far worse/non-generalizable performance than sparse embeddings Pinecone supports. Moreover you get a latency hit from RRF that makes it challenging to use for e.g. real-time multimodal chat agents.
With BM25 which has a far worse/non-generalizable performance than sparse embeddings Pinecone supports. Moreover you get a latency hit from RRF that makes it challenging to use for e.g. real-time multimodal chat agents.