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...
### 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 bug is not already filed. - [X] My model is hosted on...
### Is your feature request related to a problem? Please describe. I am working on creating a News RAG model and would like to add the capability to filter results...
### Is your feature request related to a problem? Please describe. A big part of good rag is the quality of the input data. I would want to specifically prepare...
[Bug]: The overlay-defaults param does not provide default values for workflows using a vector store
### Describe the bug When a vector store is specified in the YAML configuration, attempting to execute an indexing job with the bash tool using the `--overlay-defaults` flag results in...
## Description Fix bug about non-ascii encoding like Chinese. In the cache stage, Chinese characters will be stored as /uxxxx; In the summarize stage, Chinese characters will be read as...
### Describe the bug I'm using smaller models and was trying to update the input length (`max_input_length` under `community_reports` in `settings.yaml`, but when generating the community report, the `max_token` in...
## 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...
Right now GraphRAG only natively supports models hosted by OpenAI and Azure. Many users would like to run additional models, including alternate APIs, SLMs, or models running locally. As a...
