graphrag
graphrag copied to clipboard
microsoft
A modular graph-based Retrieval-Augmented Generation (RAG) system
## Description This PR adds SQL Server as a storage option for parquet outputs within the indexing pipeline. ## Related Issues This PR is similar to the CosmosDB storage support...
### Do you need to file an issue? - [x] I have searched the existing issues and this feature is not already filed. - [ ] My model is hosted...
## Description This PR fixes a bug in the `_reduce_response` function in the `search.py` file in global_search. A format call is made on the `self.reduce_system_prompt` string which contains a placeholder...
## Description Added a new `--raw-chunks` flag to expose the raw context data retrieved from the vector store before it's processed by the LLM. This feature enhances debugging and transparency...
### 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...
### Do you need to file an issue? - [ ] I have searched the existing issues and this bug is not already filed. - [ ] My model is...
### 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...
### 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...
### Do you need to file an issue? - [x] I have searched the existing issues and this feature is not already filed. - [ ] My model is hosted...
## Description - In the `community_reports_extractor` file Using .format() caused errors because the COMMUNITY_REPORT_PROMPT has other `{}` braces (e.g., in JSON examples). - Python .format() tries to parse those and...
