feat(retrieval): implement Hybrid Search (Vector + BM25) and ColBERT Reranking#56
Open
swamy18 wants to merge 11 commits intofeld-m:mainfrom
Open
feat(retrieval): implement Hybrid Search (Vector + BM25) and ColBERT Reranking#56swamy18 wants to merge 11 commits intofeld-m:mainfrom
swamy18 wants to merge 11 commits intofeld-m:mainfrom
Conversation
This factory class implements the Factory design pattern to create a hybrid retriever component that uses Query Fusion to combine multiple retrieval results.
This class defines the configuration parameters needed for initializing and operating the hybrid retriever, extending the base RetrieverConfiguration.
Add hybrid retrieval configuration with various settings.
…l and reranking featureses and usage instructions Removed duplicate features and added new usage instructions for Hybrid Retrieval.
…ration for HybridRetrieverridRetrieverFactory Refactor HybridRetrieverFactory to include BM25Retriever and update configuration handling.
…wkflow Added a step for type checking using mypy.
feat(augmentation): add main app entry point for Chainlit UI
Updated README to enhance formatting and clarify usage instructions.docs: update README with correct CLI usage and hybrid search features
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request introduces significant enhancements to the retrieval pipeline, including Hybrid Search and ColBERT reranking, along with production-ready configurations and a new user interface.
Key Changes:
QueryFusionRetrievercombining Vector search (ChromaDB) and BM25 for improved relevance.ColBERTreranker to the retrieval pipeline for more precise document ranking.src/augmentation/app.pyusing Chainlit for a chat-based user interface.mypytype checking.README.mdwith detailed instructions on how to run the new hybrid search and app.