microsoft
Using Azure OpenAI for the GitHub repo sample gives errors
When trying to use Azure OpenAI for the GitHub repo example I get an error saying the particular model is not available.
To Reproduce Steps to reproduce the behavior:
- Go to 'Completion Model" tab in the GitHub repo bot example
- Click on Azure OpenAI
- Enter the Azure OpenAI Key and the Endpoint
- It correctly goes and is able to enumerate the model names.
- However on selecting a model and clicking Save gives the following error
- See error
Expected behavior Expected behavior is that this works. Btw this example works fine when using OpenAI key.
Additional context It appears to me that somehow it is looking for the wrong name of the model. Also I did check that I am able to use the model successfully from within the Azure OpenAI service itself. I also waited for several hours to make sure that the model was successfully deployed in the Azure OpenAI service.
Also the Chat Summary App works fine with Azure OpenAI with the same endpoint, key, modelname etc.
I believe this is due to the samples currently expecting text completion endpoints, not chat completion endpoints (which 3.5 turbo and 4 require).
We added additional validation to the github sample that does not exist in the prior chat sample which may explain that discrepancy - I expect it to fail there also.
Do you have davinci-003 available to try?
I actually had this error myself today, in both completion and embedding steps.
I found out that my deployment needs to be named exactly the same as the model in order to get it working. I think I can get it to replicate again, just create a model deployment with a different name than the model name.
This is the screenshot where model and deployment have different names:
