feat: GEPA optimizers #56
Merged
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
enitrat
force-pushed
the
feat/gepa-optimization
branch
8 times, most recently
from
4d2bfea to
0a126a3
Compare
enitrat
force-pushed
the
feat/gepa-optimization
branch
from
0a126a3 to
aa5d8b0
Compare
enitrat
force-pushed
the
feat/gepa-optimization
branch
from
c17ef5c to
a857785
Compare
enitrat
changed the title
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Outdated suggestions cannot be applied.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.
Summary
This PR implements GEPA (Generalized Expectation-Preservation Algorithm) optimization for the query processing program using DSPy's optimization framework. The change enhances the RAG pipeline's retrieval capabilities through optimized prompting (+5 basis points), but notably will make it easy to switch models in the future.
Key Changes
• GEPA Optimization Implementation: Applied DSPy's GEPA optimizer to the query processing program to improve search term extraction and documentation source identification
• Enhanced Dataset: Added comprehensive user queries dataset (
user_queries.json) with thousands of query examples for a good train, val, test set• Optimized Programs: Updated optimized configurations for RAG pipeline, MCP program, and retrieval program with improved prompts
• Retrieval Judge Integration: Enhanced document retrieval with better relevance filtering and metadata extraction
• Code Cleanup: Removed obsolete optimizer implementations and streamlined the optimization framework