Retrying request to /embeddings

[rickywu]

I didn't config TAVILY_API_KEY

export TAVILY_API_KEY=""

export INPUT_DIR="xxx/input/artifacts"

export GRAPHRAG_API_KEY=""

export GRAPHRAG_API_KEY_EMBEDDING=""

export GRAPHRAG_LLM_MODEL="Qwen1.5-14B-Chat-GPTQ-Int4"

export API_BASE="http://172.17.22.174:9997/v1"

export API_BASE_EMBEDDING="http://172.17.22.174:9997/v1"

export GRAPHRAG_EMBEDDING_MODEL="m3e-base"

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

[xldistance]

Your xinference embedded model doesn't start. You need to install xinference and download the startup embedded model m3e-base, I prefer bge-m3.

[rickywu]

@xldistance I'm sure it's started, I start embeding model first then LLM

[xldistance]

@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"