karthiksoman
commented
10 months ago Hi @cswangxiaowei Here the issue is that your API_KEY is not accessible for the openai library to authenticate. This is because your .gpt_config.env file is in /workspaces/KG_RAG folder. There are two solutions for this:
Solution 1: Move .gpt_config.env to your $HOME folder and retry running it.
Solution 2: Keep .gpt_config.env where it currently is, but update this line of config.yaml with the correct path of your .gpt_config.env file.
On a different note: Since the objective of KG-RAG is to address biomedical queries, I would strongly suggest to try some disease related queries to test it (instead of non-biomedical queries like Who are you?. For such queries you can use direct GPT calls) An example query can be (feel free to change it as per your interest): What are the genes associated with multiple sclerosis?
Let me know if this issue gets resolved for you.
cswangxiaowei
Davy-Chendy
May I know if my format for the API_key is correct? I use API_KEY=XXXXXX, and put the key directly in /workspaces/KG_RAG/.gpt_config.env. However, after finishing setup and building the vectorDB, I cannot call OPENAI. P.S. My key is correct, and I try to generate a new key, but it is not working.
The error is: (kg_rag) @cswangxiaowei ➜ /workspaces/KG_RAG (main) $ python -m kg_rag.rag_based_generation.GPT.text_generation -g "gpt-4"
Enter your question : who are you? Retrieving context from SPOKE graph... Calling OpenAI... Calling OpenAI... Calling OpenAI... Calling OpenAI... Calling OpenAI... Traceback (most recent call last): File "/home/codespace/.local/lib/python3.10/site-packages/tenacity/init.py", line 382, in call result = fn(*args, *kwargs) File "/workspaces/KG_RAG/kg_rag/utility.py", line 183, in fetch_GPT_response response = openai.ChatCompletion.create( File "/home/codespace/.local/lib/python3.10/site-packages/openai/api_resources/chat_completion.py", line 25, in create return super().create(args, **kwargs) File "/home/codespace/.local/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 151, in create ) = cls.__prepare_create_request( File "/home/codespace/.local/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 108, in prepare_create_request requestor = api_requestor.APIRequestor( File "/home/codespace/.local/lib/python3.10/site-packages/openai/api_requestor.py", line 139, in init__ self.api_key = key or util.default_api_key() File "/home/codespace/.local/lib/python3.10/site-packages/openai/util.py", line 186, in default_api_key raise openai.error.AuthenticationError( openai.error.AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key =', or you can set the environment variable OPENAI_API_KEY=). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path = '. You can generate API keys in the OpenAI web interface. See https://platform.openai.com/account/api-keys for details.
The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "/opt/conda/envs/kg_rag/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/opt/conda/envs/kg_rag/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/workspaces/KG_RAG/kg_rag/rag_based_generation/GPT/text_generation.py", line 56, in
main()
File "/workspaces/KG_RAG/kg_rag/rag_based_generation/GPT/text_generation.py", line 44, in main
context = retrieve_context(question, vectorstore, embedding_function_for_context_retrieval, node_context_df, CONTEXT_VOLUME, QUESTION_VS_CONTEXT_SIMILARITY_PERCENTILE_THRESHOLD, QUESTION_VS_CONTEXT_MINIMUM_SIMILARITY)
File "/workspaces/KG_RAG/kg_rag/utility.py", line 248, in retrieve_context
entities = disease_entity_extractor_v2(question)
File "/workspaces/KG_RAG/kg_rag/utility.py", line 232, in disease_entity_extractor_v2
resp = get_GPT_response(prompt_updated, system_prompts["DISEASE_ENTITY_EXTRACTION"], chat_model_id, chat_deployment_id, temperature=0)
File "/home/codespace/.local/lib/python3.10/site-packages/joblib/memory.py", line 655, in call
return self._cached_call(args, kwargs)[0]
File "/home/codespace/.local/lib/python3.10/site-packages/joblib/memory.py", line 598, in _cached_call
out, metadata = self.call(*args, kwargs)
File "/home/codespace/.local/lib/python3.10/site-packages/joblib/memory.py", line 856, in call
output = self.func(*args, *kwargs)
File "/workspaces/KG_RAG/kg_rag/utility.py", line 203, in get_GPT_response
return fetch_GPT_response(instruction, system_prompt, chat_model_id, chat_deployment_id, temperature)
File "/home/codespace/.local/lib/python3.10/site-packages/tenacity/init.py", line 289, in wrapped_f
return self(f, args, kw)
File "/home/codespace/.local/lib/python3.10/site-packages/tenacity/init.py", line 379, in call
do = self.iter(retry_state=retry_state)
File "/home/codespace/.local/lib/python3.10/site-packages/tenacity/init.py", line 326, in iter
raise retry_exc from fut.exception()
tenacity.RetryError: RetryError[<Future at 0x7f5c931e94b0 state=finished raised AuthenticationError>]