mismatched_organization error

[yaqinamy]

when comparing local llama2 model with GPT4, got error:

ERROR Failed to send a test chat completion to the GPT deployment due to error: evaluate.py:110
Error code: 401 - {'error': {'message': 'OpenAI-Organization header should match organization for API key', 'type': 'invalid_request_error',
'param': None, 'code': 'mismatched_organization'}

[pamelafox]

So are you using llama2 via ollama for the actual evaluation?

[yaqinamy]

Yes Pamela, I am learning from your video using llama2 via ollama which I deployed local and GPT4 deployed at azure.

[pamelafox]

Okay, so to clarify:

• You are using GPT4 for the evaluation?
• You are using llama2 for the chat application itself?

The error in your report shows an issue with the evaluation model, which would be GPT-4. But you shouldn't need to specify OpenAI organization for an Azure model. Do the logs indicate whether it's trying to use Azure or OpenAI.com?

You should see the logs from this code:

ai-rag-chat-evaluator/scripts/service_setup.py

Line 14 in 7b5d503

if os.environ.get("AZURE_OPENAI_KEY"):