graphrag
graphrag copied to clipboard
A modular graph-based Retrieval-Augmented Generation (RAG) system
Detect process forks and recreate thread resources to prevent 'RuntimeError: threads can only be started once' in worker processes. - Add PID tracking for fork detection - Safe cleanup of...
### Do you need to file an issue? - [x] I have searched the existing issues and this feature is not already filed. - [x] My model is hosted on...
## Description Tiny corpora + `CacheType.memory` crashed with `ValueError: Columns must be same length as key` (and follow-on dtype issues). This PR hardens three spots: 1. **build_noun_graph._extract_edges** * Expand `edges`...
## Description Prompt tuning errors out when the number of chunks is less than the default LIMIT, saying "Auto-prompt generation failed: Cannot take a larger sample than population when 'replace=False'"...
### Do you need to file an issue? - [x] I have searched the existing issues and this bug is not already filed. - [x] My model is hosted on...
## Description Store LanceDB on a storage account, according to: https://lancedb.github.io/lancedb/guides/storage/#azure-blob-storage ## Related Issues None ## Proposed Changes Add storage_options to lancedb.connect. graphrag\vector_stores\lancedb.py ## Checklist - [x] I have tested...
Hi, I would like to know if GraphRAG supports CSV files exported from Neo4j as input for indexing. These CSV files typically contain multiple columns, including entities, entity relationships, and...
## Description [Provide a brief description of the changes made in this pull request.] Current local search module fails to integrate community reports because of mismatched community_id, this pr changed...