Wei Yang (William) Submit HW5 – Hybrid Retrieval#10
Open
williamgoodhouses-rgb wants to merge 2 commits intomainfrom
Open
Wei Yang (William) Submit HW5 – Hybrid Retrieval#10williamgoodhouses-rgb wants to merge 2 commits intomainfrom
williamgoodhouses-rgb wants to merge 2 commits intomainfrom
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 contains my Week 5 homework submission for the MLE in GenAI course.
The notebook extends the Week 4 RAG pipeline by:
Building a SQLite embedding database for document chunks
Implementing FAISS semantic search and SQL keyword search
Combining both into a hybrid retrieval strategy
Evaluating FAISS-only, SQL-only, and hybrid retrieval using hit@3
(Optional) Exposing the hybrid retriever via a FastAPI endpoint
Notebook: Wei_Yang_week5_submission.ipynb
The hybrid approach shows improved retrieval coverage compared to single-method baselines.