Open mustangs0786 opened 1 month ago
Hi Team after digging for some time i found this section of code under file
Path: "graphrag/query/structured_search/local_search/search.py"
response = await self.llm.generate( messages=search_messages, streaming=True, callbacks=self.callbacks, **self.llm_params, )
By making streaming = False, issue got resolve,
same goes for global search file
I request ream to bring this variable as user input, by keeping it in settings.yaml file
thanks
Do you need to file an issue?
Describe the issue
Hi i after creating parquet file , when I am hitting the query
I am getting error back
raise self._make_sttus_error_fromresponse(err.response) from None openai.Permissiondeniederror: error code : 403 {detial : stream object no attribute usage}
as per I understood, my gpt instance does not support streaming of the response, hence this error I am seeing. to solve this is there any setting in graph rag, so it will expect complete response in the end rather then waiting for streaming answer. thanks
Steps to reproduce
No response
GraphRAG Config Used
Logs and screenshots
No response
Additional Information