Closed jtokash closed 1 year ago
same
Same problem. Can anyone call the openapi for gpt-4 or you need to be granted access?
Same problem. Can anyone call the openapi for gpt-4 or you need to be granted access?
From what I can tell you need to sign up on a waitlist for gpt-4 API
Same. I have access to GPT4, but still get this error whenever evaluate_code
is run.
Can you disable and only have it run on 3.5?
I get the same, but I'm not running in gpt3only mode. It was when the AI had written a bot and tried to evaluate the code.
To disable gpt-4 just edit the configuration, set SMART_LLM_MODEL="gpt-3.5-turbo"
in .env
.
@ljleb 's response is correct - there are 2 models referenced in .env. I only had one set to 3.5.
PINECONE_API_KEY=your-pinecone-api-key PINECONE_ENV=your-pinecone-region OPENAI_API_KEY= ELEVENLABS_API_KEY= SMART_LLM_MODEL="gpt-3.5-turbo-0301" FAST_LLM_MODEL="gpt-3.5-turbo" GOOGLE_API_KEY= CUSTOM_SEARCH_ENGINE_ID= USE_AZURE=False OPENAI_API_BASE=your-base-url-for-azure OPENAI_API_VERSION=api-version-for-azure OPENAI_DEPLOYMENT_ID=deployment-id-for-azure IMAGE_PROVIDER=dalle HUGGINGFACE_API_TOKEN=
--gpt3only also resolves, don't have to set the env variable
To disable gpt-4 just edit the configuration, set
SMART_LLM_MODEL="gpt-3.5-turbo"
in.env
.
--gpt3only also resolves, don't have to set the env variable
@omni-webdev --gpt3only also resolves, don't have to set the env variable
Unless it has been fixed, (I assume it has been fixed by now?) there was an issue last week making this flag useless for code.
@ljleb looks like it was fixed, no more gpt4 errors with the flag
Command evaluate_code returned: Error: The model: gpt-4
does not exist
I have openAPI key with credits and the following in .env file, what am I missing?
SMART_LLM_MODEL=gpt-4 FAST_LLM_MODEL=gpt-3.5-turbo
Having paid OpenAI account doesn't neccessarily mean you have access to GPT4 (neither does ChatGPT Plus subscription), currently the only way to get access to GPT4 is through waitlist: https://openai.com/waitlist/gpt-4-api
@styk-tv I still get this error and all I get is: SYSTEM:
Command evaluate_code returned: Error: The model: gpt-4
does not exist
although in .env I have:
"SMART_LLM_MODEL="gpt-3.5-turbo" FAST_LLM_MODEL=gpt-3.5-turbo"
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=
SYSTEM: Command evaluate_code returned: Error: The model: gpt-4
does not exist
I didn't know so i waste 0.17 token. why is it spending money and my time?....
Having paid OpenAI account doesn't neccessarily mean you have access to GPT4 (neither does ChatGPT Plus subscription), currently the only way to get access to GPT4 is through waitlist: https://openai.com/waitlist/gpt-4-api
It's still able to use gtp-3.5-turbo and that's where your tokens are being spent, access to the API is not free
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= SYSTEM: Command evaluate_code returned: Error: The model:
gpt-4
does not exist I didn't know so i waste 0.17 token. why is it spending money and my time?....
Please are working hard on the project. if u think it wasting your time , DON'T USE IT
When running with --gpt3only mode, I receive this error when Auto-GPT tries to 'execute' code.
SYSTEM: Command evaluate_code returned: Error: The model:
gpt-4
does not exist