coolboywcm commented on issue #297:
URL: 
https://github.com/apache/incubator-hugegraph-ai/issues/297#issuecomment-3153436276

   Hi, thanks for the reply.
   
   My setup:
   
   HugeGraph Server: hugegraph/hugegraph:1.5.0
   RAG Platform: hugegraph/rag:latest (pulled from Docker Hub)
   Deployment: Docker standalone (not Kubernetes or docker-compose)
   Network: Custom bridge network hugegraph-net
   
   The logs detail:
   
   INFO:     172.31.0.5:43172 - "POST /gradio_api/queue/join HTTP/1.1" 200 OK
   [08/05/25 05:46:27] WARNING  llm: Missing vector files:       
vector_index.py:46
                                /home/work/hugegraph-llm/src/hug                
   
                                egraph_llm/resources/hugegraph/g                
   
                                raph_vids/index.faiss,                          
   
                                /home/work/hugegraph-llm/src/hug                
   
                                egraph_llm/resources/hugegraph/g                
   
                                raph_vids/properties.pkl.                       
   
                                Need create a new one for it.                   
   
   [08/05/25 05:46:27] INFO     client: Retrieved API version     
huge_config.py:54
                                information from the server:                    
   
                                1.5.0.                                          
   
                       INFO     client: Retrieved API version     
huge_config.py:54
                                information from the server:                    
   
                                1.5.0.                                          
   
                       INFO     client: Retrieved API version     
huge_config.py:54
                                information from the server:                    
   
                                1.5.0.                                          
   
                       DEBUG    llm: Running operator:             
decorators.py:68
                                KeywordExtract                                  
   
   [08/05/25 05:46:37] INFO     llm: Token usage:                      
openai.py:73
                                {"completion_tokens":259,"prompt_token          
   
                                s":429,"total_tokens":688,"completion_          
   
                                tokens_details":{"accepted_prediction_          
   
                                tokens":null,"audio_tokens":null,"reas          
   
                                oning_tokens":253,"rejected_prediction          
   
                                _tokens":null},"prompt_tokens_details"          
   
                                :{"audio_tokens":null,"cached_tokens":          
   
                                0}}                                             
   
                       DEBUG    llm: Keyword extraction time: 
keyword_extract.py:65
                                9.33 seconds                                    
   
                       INFO     llm: User Query: Who is Sarah 
keyword_extract.py:72
                                ?                                               
   
                                                                                
   
                                Keywords: ['Sarah']                             
   
                       DEBUG    llm: Operator KeywordExtract       
decorators.py:74
                                finished in 9.40 seconds                        
   
                       DEBUG    llm: Running operator:             
decorators.py:68
                                SemanticIdQuery                                 
   
                       CRITICAL llm: Error code: 401 - {'message': 
rag_block.py:227
                                '请先登录', 'status': 10025,                       
                                'timestamp': 1754372797471}  
   
   Could you point me  the **correct configuration  filepath**
   [@dosu](https://go.dosu.dev/dosubot).
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to