Nathan Evans
Nathan Evans
Consolidating Ollama-related issues: https://github.com/microsoft/graphrag/issues/657
Consolidating Ollama-related issues: https://github.com/microsoft/graphrag/issues/657
Consolidating alternate model issues here: #657
I also suggest trying the [auto-tuning function](https://microsoft.github.io/graphrag/posts/prompt_tuning/auto_prompt_tuning/) to tailor your entity extraction prompts to the specifics of your data domain before running ingest.
We have resolved several issues related to text encoding and JSON parsing that are rolled up into version [0.2.2](https://github.com/microsoft/graphrag/releases/tag/v0.2.2). Please try again with that version and re-open if this is...
PR https://github.com/microsoft/graphrag/pull/639 has been merged and included in GraphRAG 0.2.0, which enforces UTF-8 encoding. Please let us know if upgrading resolves your issue.
We have resolved several issues related to text encoding and JSON parsing that are rolled up into version [0.2.2](https://github.com/microsoft/graphrag/releases/tag/v0.2.2). Please try again with that version and re-open if this is...
> Seems like gpt4o does not support chat completion. will request gpt3.5 or gpt4 turbo and try again Have you tried this recently with gpt-4o? We've been using it quite...
We've released [2.1](https://github.com/microsoft/graphrag/releases/tag/v2.1.0) which supports JSON. I'll leave this open as markdown is not supported well yet.