Feature/metadata #183
Closed
Feature/metadata #183
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This comment was marked as resolved.
This comment was marked as resolved.
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
franzbischoff
commented
Sep 11, 2023
Member
|
moved to #241 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As discussed with @timothycarambat , this implements the PyMuPDF that is quick and handles Unicode better.
Also, allows us to use actual PDF metadata as 'title', 'author', etc, to populate the embedded metadata for further references when searching.
One thing I find out is that the window that shows the references of the searches is not handling Unicode on 'title' field, but it is on the text body. This should be fixed.
Known bug: lanceDB insists in assume the Scheme is different when differerent filetypes are uploaded for embedding. Pinecone handle this ok.
I've reviewed the documentation and the actual tables created by lanceDB and could not figure out.
The rest works fine.