feat: improve GraphRAG extraction quality and remove HuggingFace provider#9
Merged
Merged
Conversation
…ider - Drop HuggingFace TGI provider; keep only Azure OpenAI and Ollama - Add gleaning (multi-pass entity extraction) inspired by Microsoft GraphRAG - Default 1 gleaning pass catches 30-50% more entities - Configurable via indexing.max_gleanings in config - Improve entity extraction prompt with few-shot examples, expanded entity types (Document, Metric, Process), weight guidance, and implicit relationship extraction instructions - Add entity name normalization (case-insensitive, whitespace-collapsed) to prevent duplicate entities like "Apple Inc" vs "apple inc" - Add relationship deduplication by (source, target, predicate) to prevent duplicate edges in the knowledge graph - Fix Louvain modularity gain formula to use the standard calculation: ΔQ = [k_i_in/(2m)] - [sigma_tot * k_i / (2m²)] The previous formula was missing the removal cost term https://claude.ai/code/session_011Ryet7uu9j6VyzNGmUuaaj
Comprehensive guide for completing the langchaingo migration in a new sandbox with network access. Includes exact code for provider adapter, chunker rewrite, API notes, and step-by-step instructions. https://claude.ai/code/session_011Ryet7uu9j6VyzNGmUuaaj
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
No description provided.