graphrag
graphrag copied to clipboard
microsoft
A modular graph-based Retrieval-Augmented Generation (RAG) system
As part of pulling context for the response synthesis a lot of information is retrieved that is ultimately not used for the response. In some cases this is helpful while...
When running create_base_extracted_entities, the entity extraction seems to work fine (per checking the cache), but when the merge_graph stage runs, it fails silently. Other than a bunch of "error invoking...
## Problem Description In [line 144](https://github.com/microsoft/graphrag/blob/60a197fbd1421739542223fb78c86670b295f7c3/graphrag/index/workflows/v1/create_final_text_units.py#L144) of the [create_final_text_units.py](https://github.com/microsoft/graphrag/blob/60a197fbd1421739542223fb78c86670b295f7c3/graphrag/index/workflows/v1/create_final_text_units.py#L144) workflow the verb attempts to load the `text_embedding` column which does not exists in the dataframe when we define a vector...
reported by Kenneth Chen @ CELA; some batch uploads are failing on their end Docs: https://learn.microsoft.com/en-us/azure/search/search-what-is-data-import - they may be running into the 16MB per batch limit
We should use a generic line separator where it's appropriate. This _SHOULD NOT_ be included in prompt definitions.
Scipy 1.13.0 fails because the triu import changed or was deprecated. We need to find the alternative path or solution so we can upgrade to latest and remove the constraint...
Pipeline yields "corrupted" dataframes when Endpoint TPM thresholds have been exceeded to many times. We should provide options to determine the failure behavior on LLM-based operations, so we can fail...
e.g. graphrag-index.exe, graphrag-query.exe
[Documentation](https://microsoft.github.io/graphrag/posts/query/3-cli/) for the query environment variables is missing two variables that are required when running queries with Azure OpenAI. `GRAPHRAG_LLM_DEPLOYMENT_NAME` and `GRAPHRAG_EMBEDDING_DEPLOYMENT_NAME` are required variables when `GRAPHRAG_LLM_TYPE=azure_openai_chat` and `GRAPHRAG_EMBEDDING_TYPE=azure_openai_embedding` respectively....
Env Vars may be biased towards our deployed models, we should fine tune them to a more appropriate value or offer a mechanism for providing a certain Size or T-shirt...