Open rickywu opened 1 month ago
Your xinference embedded model doesn't start. You need to install xinference and download the startup embedded model m3e-base, I prefer bge-m3.
@xldistance I'm sure it's started, I start embeding model first then LLM
@xldistance I'm sure it's started, I start embeding model first then LLM You can try export API_BASE_EMBEDDING="http://127.0.0.1:9997/v1"
I didn't config TAVILY_API_KEY
LLM and embedding served by xinference, but always get logs like this:
2024-08-02 15:45:51,474 - openai._base_client - INFO - Retrying request to /embeddings in 0.971267 seconds