-
Notifications
You must be signed in to change notification settings - Fork 44.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
How to get Auto-GPT to work with request to Azure Open AI deployed models? #3959
Comments
When I try using token from azure login I get this error log:
File "C:\Python311\Lib\site-packages\openai\api_requestor.py", line 682, in _interpret_response_line |
We don't have access to azure so we can't really help here. Unless we get access we may need to remove the functionality. If you have access and can put us in touch, that would be lovely. |
@ntindle just FTR, but I believe access to Azure is typically pretty inexpensive. I pay for a single-user enterprise license for an Office 365 tenant (and it comes with azure) for only $12/month - it also comes with the rest of everything that comes with an enterprise license (Sharepoint, DataVerse/CRM, Power Automate, etc.). I am mostly unfamiliar with how to actually use Azure, but from my peers I've heard that it isn't expensive to use. Usually only costing a few cents on single-user accounts. Not saying that you should go out and buy a license, but if you are interested, it isn't expensive. |
The OpenAI api for azure is closed access right now so even if we have an azure account (which we do) we don't have access to the open ai services through it |
Well, if @Mitrandir-main is proficient with Azure, I'm assuming they are probably decent with programming. If that is the case, @Mitrandir-main, we would happily welcome you to the team. |
Which Operating System are you using?
Windows
Which version of Auto-GPT are you using?
Latest Release
GPT-3 or GPT-4?
GPT-3.5
Steps to reproduce 🕹
No response
Current behavior 😯
Hello,
I am trying to use my Azure gpt-3.5 model deployment for Auto-GPT, but when I enter prompt I always get Authorization error.
I run gpt3 only mode as I dont have gpt 4 acess still.
Where should i get the value for OPENAI_API_KEY from, I have tried with the endpoint key and authorization token from Azure login.
Do you have any suggestions on where the problem might be?
This is my .env
OPENAI_API_KEY= "I put endpoint key here"
USE_AZURE=True
This is my azure.yaml
azure_api_type: azure_ad
azure_api_base: https://name-here.openai.azure.com
azure_api_version: 2023-03-15-preview
azure_model_map:
fast_llm_model_deployment_id: "model gpt3 name"
smart_llm_model_deployment_id: "model gpt3 name"
embedding_model_deployment_id: "model ada2 name"
Expected behavior 🤔
Auto_GPT runs fine but is not able to respond and do requests to Azure Open AI API, has anyone got similar problems with getting Auto_GPT to work with Aure?
Your prompt 📝
#
Your Logs 📒
The text was updated successfully, but these errors were encountered: