-
Notifications
You must be signed in to change notification settings - Fork 33
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
Add support for AzureOpenAI #131
Conversation
@ajac-zero thanks for opening this -- will take a look and we will definitely get this in soon. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for this contribution! Will you please add tests for this (there are tests for other vectorizers you can follow along) and also a small addition to the docs user_guide
for vectorizers. Thanks!
Sure thing, @tylerhutcherson. I've added the Azure vectorizer to the vectorizer test loop and a new section for Azure OpenAI in the vectorizers notebook. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
So close! Left one small typo comment, then I will merge. I will fast follow with a commit to add the env vars to our github actions scripts.
**Objective** Added a new TextVectorizer for the AzureOpenAI API, which is based on the AzureOpenAI and AsyncAzureOpenAI classes from openai>=1.0.0. **Reason** Compatibility with Azure OpenAI is an important feature for developers that are building enterprise AI applications with Azure Cloud. Particularly for use cases where privacy is a concern, and data must stay within their cloud tenant. My team particularly wants to integrate Semantic Cache (with Azure Cache for Redis Enterprise). Since we rely on the Azure OpenAI API, I created this new vectorizer to add that functionality. --------- Co-authored-by: Anibal <a8065384@banorte.com> Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>
Objetive
Added a new TextVectorizer for the AzureOpenAI API, which is based on the AzureOpenAI and AsyncAzureOpenAI classes from openai>=1.0.0.
Reason
Compatibility with Azure OpenAI is an important feature for developers that are building enterprise AI applications with Azure Cloud. Particularly for use cases where privacy is a concern, and data must stay within their cloud tenant.
My team particularly wants to integrate Semantic Cache (with Azure Cache for Redis Enterprise). Since we rely on the Azure OpenAI API, I created this new vectorizer to add that functionality.