Nathan Evans

Results 142 comments of Nathan Evans

Agree that this seems confusing. The human-readable ID for text_units is assigned from the index when we [load the data](https://github.com/microsoft/graphrag/blob/53268406fe2ce0a57f9535d87b9e68bf00f72d0f/graphrag/query/input/loaders/dfs.py#L283) for query. Text units were likely added to the query...

This should be done for any models/endpoints used in case there are config issues (completion, embeddings, custom step config, etc.). Could be part of a startup pipeline validation step.

Note that this feature will need to run up-front and synchronously. Part of our difficulty in catching exceptions and failing is that many pipeline steps run async and we do...

@AlonsoGuevara can you confirm #517 resolved this and it can be closed?

We are working on an injectable logger to help assess costs. In the meantime, here is a new article discussing GraphRAG costs: https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/graphrag-costs-explained-what-you-need-to-know/ba-p/4207978

This is a popular request, so I'm going to pin it and route other issues here.

Related: removing existing content, e.g., #585

Additional use case: adding files of a different type: https://github.com/microsoft/graphrag/issues/784

Please try again with version 2.2.1, which includes updates to the prompt template to resolve the `format` call removing too many braces