graphrag
graphrag copied to clipboard
microsoft
A modular graph-based Retrieval-Augmented Generation (RAG) system
### Do you need to file an issue? - [ ] I have searched the existing issues and this bug is not already filed. - [ ] My model is...
## Description Implement dynamic community selection to improve global search result. Currently, we select the community reports by specifying a specific community level, prior to the map-reduce operation, while fast,...
### Do you need to file an issue? - [ ] I have searched the existing issues and this feature is not already filed. - [ ] My model is...
- Added Milvus Vector Store ## Description - Added Milvus Vector Store ## Proposed Changes [List the specific changes made in this pull request.] ## Checklist - [x] I have...
- Added PostgreSQL vector store ## Description Added PostgreSQL vector store ## Proposed Changes [List the specific changes made in this pull request.] ## Checklist - [x] I have tested...
### Do you need to file an issue? - [X] I have searched the existing issues and this bug is not already filed. - [ ] My model is hosted...
### Describe the bug When using create_final_entities_new.parquet instead of create_final_entities.parquet in output directory, an error occurs during local query after incremental indexing： File "/home/lile/graphrag/graphrag/query/__main__.py", line 83, in run_local_search( File "/home/lile/graphrag/graphrag/query/cli.py",...
disable cache search in graphrag/llm/base/caching_llm.py: history_string = None makes index creation much faster . why ?
## Description [Provide a brief description of the changes made in this pull request.] ## Related Issues [Reference any related issues or tasks that this pull request addresses.] ## Proposed...
## Description This adds support for [Astra DB](https://www.datastax.com/products/datastax-astra) as vector store. ## Checklist - [x] I have tested these changes locally. - [x] I have reviewed the code changes. -...
