Replies: 1 comment 3 replies
-
Hi @sinaayyy! As you plan to use both BM25 and dense embeddings, I'd suggest using a document store that inherently support both methods. The document stores that support BM25 and allow customizing vector search in various ways are |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello, I am working on an intelligent research project with a view to commercialization. I plan to use two retriever models bm25 and DPR type with a reader model type Roberta.
I've read about the different possible document stores (open source and free). However I can't decide which one would be the most adapted to be open source and free. Could someone help me?
Thanks
Beta Was this translation helpful? Give feedback.
All reactions