Daniel Chalef

> https://{your-resource-name}.openai.azure.com/openai/deployments/{deployment-id}/embeddings?api-version=2024-02-01**/embeddings/** @mariaapostigo Can you try removing "/embeddings" from your `azure_endpoint` URL? The Graphiti code is very similar to Microsoft's instructions below, so I anticipate they're expecting the endpoint value...

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our [Contributor License Agreement](https://github.com/getzep/graphiti/blob/main/Zep-CLA.md) before we can accept your contribution. You can...

@jonit-dev Thanks for contributing. This PR covers a lot of varying ground. Would you please split it into smaller PRs that can be reviewed and merged independently?

Closing due to no response.

All contributors have signed the CLA ✍️ ✅Posted by the ****CLA Assistant Lite bot****.

This is awesome. Thanks for contributing. Please allow @prasmussen15 and team some time to review and comment. Thank you!

You'll need to restart your MCP Server using the `group_id` generated when you ingested the data. `uv run graphiti_mcp_server.py --group-id ` https://github.com/getzep/graphiti/tree/main/mcp_server#running-the-server If you can't recall the `group_id` used, you...

We strongly recommend using larger models capable of outputting well-formed JSON. Please see guidance in the Graphiti documentation on appropriate LLMs to use.

I have a suspicion that whatever node names that are being generated by the Ollama model are not being accepted by the OpenAI API. These should be non-empty strings, but...

@blaesild Thanks for your feedback. We're planning some work to do to reduce token usage. Additionally, I'm going to make `gpt-4o-mini` the default for the MCP server.