How to store Colqwen model's embeddings in PG vector
Hi, Is it necessary for byaldi to always create a new .byaldi folder and store the embeddings in a folder? Can we store the embeddings in a traditional vector database like pg-vector instead of storing them in the same file? If it's possible, please let me know.
same question
You can store the vectors in a vector database like postgres, but it wouldn't be efficient for querying due to the late interaction mechanism that we use with multi-modal RAG. Better to use vespa.ai for multi-vector retrieval as is the case w multi-modal retrieval
There is an example here : https://github.com/pgvector/pgvector-python/blob/master/examples/colpali/exact.py