Fix Azure OpenAI support broken with openai>=1.0.0#310
Open
cwmuller wants to merge 7 commits intoz3z1ma:mainfrom
Open
Fix Azure OpenAI support broken with openai>=1.0.0#310cwmuller wants to merge 7 commits intoz3z1ma:mainfrom
cwmuller wants to merge 7 commits intoz3z1ma:mainfrom
Conversation
- Add retry logic for rate limits - Add Azure AD authentication (EnvironmentCredential + DefaultAzureCredential) - Add test coverage
cwmuller
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Using --synthesize with the openai-azure llm-provider caused errors due to the code referencing entry points deprecated since openai version 0.28. Since dbt 1.2.2 had pinned a later version of openai, the openai-azure provider was effectively broken. I've made the changes necessary be able to use the azure-openai provider with openai>=1.0.
I also added azure AD authentication and some retry logic for handling rate limiting.
In summary:
The changes work with our setup. All test_llm.py tests seem to pass; unfortunately, it would be hard for me perform any end to end testing with any other providers.