[Gen-Ai-Orchestrator] Add title to embedded documents for better retrieval #1639
Conversation
This file contains 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
|
@GuirriecP is it still draft ? |
|
@vsct-jburet Yes it is. We will draft PRs to tell the Arkéa team members that the work is done, pending review. We will only push final, mergeable PRs to the repo when they have been reviewed. |
Benvii
requested changes
Jul 8, 2024
| """Add 'title' from metadata to Document's page_content for better semantic search.""" | ||
| for doc in splitted_docs: | ||
| # Store the original page_content in the metadata | ||
| doc.metadata['original_text'] = doc.page_content |
There was a problem hiding this comment.
This will multiple by 2 the weight of a database from the previous implementation for small DB it's not an issue for bigger ones this will have consequent storage (and cost) impact.
|
@assouktim were did you fix this PR ? is there a new branch somewhere ? thanks in advance |
|
Replaced by #1732 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Adds the 'Title' entry of input CSV to embedded documents:
Fixes #1638