0votes
4 answersFAISS returns -1 as an index, or I can't map results back to my documents
index.search returns some IDs of -1, and I don't know how to get from the returned numbers back to my original documents.

Find answers to your programming questions.
index.search returns some IDs of -1, and I don't know how to get from the returned numbers back to my original documents.
With similaritysearchwithscore, the most relevant document has the lowest score. In another setup, all scores are high, even for unrelated text.
Re-embedding millions of documents is expensive. Can I map my old 768-dimensional vectors to the new model's 1024 dimensions?
I created a Pinecone index and now upserting or querying fails with a dimension error.
Adding or querying my Chroma collection fails with a dimension mismatch, even though my code didn't change.