Closed gordingin closed 14 hours ago
Thanks for pointing it out. I changed the project structure and forgot to update the readmefile. I just updated it. Here is the correct instructions:
configs
folder and update the app_config.yml
file if needed..env
file and add your GPT API credentials.If you're using OpenAI directly:
OPENAI_API_KEY=
If you're using Azure OpenAI:
OPENAI_API_TYPE=
OPENAI_API_VERSION=
OPENAI_API_KEY=
OPENAI_API_BASE=
gpt_deployment_name=
embed_deployment_name=
Important Notes:
openai==0.28
, but OpenAI has updated their chat completion function in the latest versions. If you want to use the newer version:
I added the OPENAI key and now receive the error below. Since you make a comment that thing need to change and not sure how to do that, I will try to get the Azure Keys instead...
AttributeError: 'NoneType' object has no attribute 'lower'
Traceback:
File "/Users/ralph.krausse/git/LLM-Zero-to-Hundred/WebGPT/WebGPT_env/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 534, in _run_script
exec(code, module.dict)
File "/Users/ralph.krausse/git/LLM-Zero-to-Hundred/WebGPT/src/webgpt_app.py", line 103, in
yes, this error occurred because the system could not make a successful call to the models.
Hi, directions say the following
There is a configs folder but no config folder. I can create on and a file but what format is cfg.py in?
thx Ralph