Adding Support for Image Generation with AzureOpenAI

[marlenezw]

This PR adds support for image generation with the AzureOpenAI API and Dalle.
This capability was added to AzureOpenai in a recent release and more information can be found here.

The API should use the following structure that will work with Prompty and Promptflow

client = AzureOpenAI(
    api_version="2024-02-01",  
    api_key=os.environ["AZURE_OPENAI_API_KEY"],  
    azure_endpoint=os.environ['AZURE_OPENAI_ENDPOINT']
)

result = client.images.generate(
    model="dalle3", # the name of your DALL-E 3 deployment
    prompt="a close-up of a bear walking throughthe forest",
    n=1
)

[wangchao1230]

pls add some e2e test on this

[marlenezw]

Will do

[wangchao1230]

why is it hard coded a n parameter here? How about other parameters?

[marlenezw]

I hardcoded that in when I was testing. I'll remove that

[marlenezw]

I haven't added any other parameters because I just wanted something that works for our build demo. These are the 3 main parameters for a quick start. I'll try and in more if I can.

[github-actions]

Hi, thank you for your interest in helping to improve the prompt flow experience and for your contribution. We've noticed that there hasn't been recent engagement on this pull request. If this is still an active work stream, please let us know by pushing some changes or leaving a comment.

[github-actions]

Hi, thank you for your contribution. Since there has not been recent engagement, we are going to close this out. Feel free to reopen if you'd like to continue working on these changes. Please be sure to remove the no-recent-activity label; otherwise, this is likely to be closed again with the next cleanup pass.