top | item 46909084

(no title)

RevEng | 24 days ago

The article shows an example of hybrid search using RRF.

discuss

order

storus|24 days 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.