You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
So I recently uploaded some documents containing text that I was very certain would be picked up in a similarity search. I even prompted in my query words directly from the document. The issue is that the similarity search returns other documents (which I admit have similar content as well).
I have a sneaking suspicion something is wrong on my end but I can't really determine what's up. I've been adding documents to my vector store and processing them for months without issues, so this is quite strange.
I can't provide the document since it contains sensitive information, so that's why I was curious if there was some way to essentially do the following:
Specifically retrieve a document from vector store (Pinecone allows metadata filtering)
Determine its similarity to one another.
I have done a similarity comparison directly between the two strings. The score is pretty good, and yet the other documents with lower scores are being returned instead.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Checked other resources
Commit to Help
Example Code
Description
So I recently uploaded some documents containing text that I was very certain would be picked up in a similarity search. I even prompted in my query words directly from the document. The issue is that the similarity search returns other documents (which I admit have similar content as well).
I have a sneaking suspicion something is wrong on my end but I can't really determine what's up. I've been adding documents to my vector store and processing them for months without issues, so this is quite strange.
I can't provide the document since it contains sensitive information, so that's why I was curious if there was some way to essentially do the following:
I have done a similarity comparison directly between the two strings. The score is pretty good, and yet the other documents with lower scores are being returned instead.
System Info
python 3.11.1
langchain_openai 0.3.7
Beta Was this translation helpful? Give feedback.
All reactions