Open Greenhub-1215 opened 1 week ago
You may need to use a model with larger parameters, I tried llama3.1-70b and it didn't work, finally using deepseek-chat worked!
well, it might work while using API key, however, we must use local LLM and embedding model due to some restrictions from the project we're now working on.
Do you need to file an issue?
Describe the issue
GraphRAG failed to create final entities, while using local LLM and local Embedding Model.
embedding model is a fschat server, and LLM is Qwen2.5-7B, run by a vllm OpenAI server.
Steps to reproduce
GraphRAG Config Used
Logs and screenshots
indexing-engine.log
Additional Information