Fixes #34: Modify similarity search to return all documents from vectordb #35
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
Update the similarity search to retrieve up to 1000 documents instead of using the default limit. This ensures the summarization chain has access to all available documents in the vector database, leading to more comprehensive summaries that consider the complete content.
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Outdated suggestions cannot be applied.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.
Pull Request Description
Overview
This pull request addresses issue #34 regarding the retrieval of documents using the
vectordb.similarity_search()method. The previous implementation returned only 4 documents when executingsearch = vectordb.similarity_search(" "). The objective of this fix is to enable the retrieval of a broader range of documents for effective summarization of the corpus.Changes Made
Rationale
The modification was necessary to meet the intended purpose of the search functionality, which is to provide a comprehensive summary based on all available texts. By increasing the limit on the number of retrieved documents, we can better serve users who require insights drawn from a more extensive dataset.
Outcome
With this update, users will now receive a complete summary based on a wider selection of documents rather than being restricted to a small, arbitrary subset. This addresses the concern raised in issue #34 and enhances the overall utility of the document retrieval feature.
Issue Reference
Fixes #34
Request for Review
I invite the team to review these changes and provide any feedback or suggestions. Thank you for your attention to this improvement!