feat: integrate RAG into hypothesis generation #267
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Outdated suggestions cannot be applied.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.
Description
This PR integrates Retrieval-Augmented Generation (RAG) into the hypothesis generation process for Kaggle scenarios. It enhances the
KGHypothesisGen
class to leverage relevant information from a knowledge base when generating hypotheses.Key changes:
KGHypothesisGen
prepare_context
method to perform RAG searchMotivation and Context
This change improves the quality and relevance of generated hypotheses by providing additional context from a knowledge base. It allows the model to consider a broader range of information when formulating hypotheses, potentially leading to more insightful and accurate proposals.
Related issue: #[Issue number if applicable]
How Has This Been Tested?
pytest qlib/tests/test_all_pipeline.py
under upper directory ofqlib
.tests/test_kg_hypothesis_gen.py
to verify RAG integration.Screenshots of Test Results (if appropriate):
Types of changes
📚 Documentation preview 📚: https://RDAgent--267.org.readthedocs.build/en/267/