It seems Azure Open AI stopped working in v0.29.0 about aider

[paul-gauthier]

Ah ok, thanks for working through this with me. We need to tell aider to use Azure for the "weak model" too:

Can you try this? Again, with no .aider.conf.yml. We're just adding: --weak-model azure/<your_deployment_name>

export AZURE_API_KEY=your-key-goes-here
export AZURE_API_VERSION=2023-05-15
export AZURE_API_BASE=https://example-endpoint.openai.azure.com
aider --model azure/<your_deployment_name> --weak-model azure/<your_deployment_name> 

[paul-gauthier]

Ok, thanks. I think I fixed the issue. Thanks again for all the help working through this and debugging it.

The change is available in the main branch. You can get it by installing the latest version from github:

python -m pip install --upgrade git+https://github.com/paul-gauthier/aider.git

If you have a chance to try it, let me know if it works better for you.

[mikeplavsky]

Thank you a lot. Now it works:

mike@MIKEP01-MAC aider % aider --model azure/gpt-4-turbo --weak-model azure/gpt-4-turbo
Aider v0.29.2-dev
Models: azure/gpt-4-turbo with udiff edit format, weak model azure/gpt-4-turbo
Git repo: .git with 155 files
Repo-map: using 1024 tokens
Use /help to see in-chat commands, run with --help to see cmd line args
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
> Please don't change any code, I am reading.

Understood, I'll wait for your instructions when you're ready.

[paul-gauthier]

Great! With this new version, you shouldn't need to manually specify --weak-model. Aider will automatically use the main model as the weak model for azure if none is specified. You can of course specify a different weak model if you'd like.

[mikeplavsky]

If I follow this example: https://docs.litellm.ai/docs/providers/azure#completion---using-env-variables with the same environment variables I get the answer from Azure OpenAI:

from litellm import completion
completion(model='azure/gpt-4-turbo', messages = [{ "content": "Hello, how are you?","role": "user"}])

ModelResponse(id='chatcmpl-9GeLLl8DLUFM36nGHm8MnH2eJmQxE', choices=[Choices(finish_reason='stop', index=0, message=Message(content="Hello! I'm just a computer program, so I don't have feelings, but I'm here and ready to assist you with any questions or tasks you have. How can I help you today?", role='assistant'))], created=1713755355, model='gpt-4', object='chat.completion', system_fingerprint='fp_2f57f81c11', usage=Usage(completion_tokens=40, prompt_tokens=13, total_tokens=53))

[paul-gauthier]

Thanks for trying aider and filing this issue. Sorry you're having trouble connecting to Azure. It's possible that something in the latest version isn't working quite right.

Can you try removing your .aider.conf.yml file and running aider like this:

export AZURE_API_KEY=your-key-goes-here
export AZURE_API_VERSION=2023-05-15
export AZURE_API_BASE=https://example-endpoint.openai.azure.com
aider --model azure/<your_deployment_name>

If that works I can make some changes to aider to make this simpler/easier.

[mikeplavsky]

Without .aider.config.yml and with

env | grep AZURE
AZURE_API_BASE=****
AZURE_API_VERSION=2024-02-15-preview
AZURE_API_KEY=****

aider --model azure/gpt-4-turbo
Aider v0.29.1
To use model gpt-3.5-turbo, please set these environment variables:- OPENAI_API_KEY

added this export OPENAI_API_KEY=$AZURE_API_KEY and it does not work either:

litellm.exceptions.AuthenticationError: OpenAIException - Error code: 401 - {'error': {'message': 'Incorrect API key provided: ******************** You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}

If I unset OPENAI_API_KEY and use this aider --model azure/gpt-4-turbo --weak-model azure/gpt-4-turbo it also crashes:

openai.openaiError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

[mikeplavsky]

aider --model azure/gpt-4-turbo --weak-model azure/gpt-4-turbo also crashes:

openai.openaiError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

And if export OPENAI_API_KEY=$AZURE_API_KEY it crashes with:

litellm.exceptions.AuthenticationError: OpenAIException - Error code: 401 - {'error': {'message': 'Incorrect API key provided: ********************. You can find your API key at https://platform.openai.com/account/api-keys.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_api_key'}}

[mikeplavsky]

Fixed