graphrag
graphrag copied to clipboard
microsoft
A modular graph-based Retrieval-Augmented Generation (RAG) system
### Is your feature request related to a problem? Please describe. milvus is very fast and efficient so i want to use it for vector storage for this. ### Describe...
## Description When I config strategy with nltk type for entity_extraction, it doesn't take effect. ## Related Issues ## Proposed Changes - read strategy from config and set it to...
### Describe the issue In `graphrag/index/graph/extractors/graph/prompts.py`, GRAPH_EXTRACTION_PROMPT miss closeing bracket in line 15. This is fine for large LLM, but it might have an impact on smaller one. ### Steps...
## Description initialize config with LocalSearchConfig and GlobalSearchConfig ## Proposed Changes settings.yaml: graphrag/index/init_content.py ## Checklist - [X] I have tested these changes locally. - [X] I have reviewed the code...
## Description This PR enforces a minimum of 3 few shot examples used in the final entity & relation extraction prompts. It also adds a KNN, content-based selection method for...
### Discussed in https://github.com/microsoft/graphrag/discussions/536 Originally posted by **streetstylecoder** July 13, 2024 , for example here when I am working on a businesss proposals , where there are hundreds of files...
### Describe the bug question = "Tell me about Agent Mercer" result = await search_engine.asearch(question) print(result.response) ### print(result.context_data["entities"].head()) print(result.context_data["relationships"].head()) print(result.context_data["reports"].head()) ...... check entities is ok, but print(result.context_data["relationships"].head()) ~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^ KeyError: 'relationships'...
Added a notebook as discussed with @stevetru1 to load the result data of a GraphRAG indexing run into Neo4j. Put it in the folder: https://github.com/microsoft/graphrag/tree/main/examples_notebooks/neo4j
## Description Changed the documentation to reflect that user configurations are stored in settings.yaml instead of .env. This ensures users are directed to the correct file for adjusting input data...
### Describe the bug GraphRAG parsing parameters missed completely the controlled parameters for LLM, such as temperature, n, top_p. Although these are in the settings.yaml file (described below) but using...
