Josh Bradley

I can understand the cost argument for development/testing reasons. What we’ve found so far is that use of OSS models leads to more noise in the knowledge graph and therefore...

At this time, lancedb is a necessary package. `graphrag` uses lancedb as the preferred choice for a local vector database at query time. There are a couple of issues/PR’s open...

I recently pushed a PR through that renamed the `reports` directory to `logs`. I also hooked up the logging to app insights so that it is easier to debug any...

If you're okay with sharing, please post the config file that you are using so we can understand your initial setup.

@Arvoid00 in some organizations, you may have an Azure Policy in place that applies additional NSG rules on top of APIM at deployment time. In my experience, this is what...

@Elizabeth819 the PR that @jasonclane is referring to has been merged. Can you try again and let me know if your problem still exist? I wasn't tracking that a python...

Can you describe the error you're encountering now when trying to use chinese docs? The underlying graphrag library does support text in multiple languages. The main issue is the text...

Thank you for this contribution. Please give us just a little time to decide on an appropriate approach to take for community contributions, to make it easy without too much...

This issue is still relevant. In situations of having low TPM or too many requests being made to the LLM, graphrag users are starting to open issues where this is...

Can you describe the environment you were running the deployment script from? A local computer or from Codespaces for example? Some people have reported that running a deployment from Codespaces...