Skip to content
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

[FEATURE] Get an AsyncOpenAI client for a serving endpoint. #847

Open
mbelak-dtml opened this issue Jan 2, 2025 · 0 comments
Open

[FEATURE] Get an AsyncOpenAI client for a serving endpoint. #847

mbelak-dtml opened this issue Jan 2, 2025 · 0 comments
Labels
Feature Request The issue is a request for enhancement or new functionality rather than a bug. Triaged The issue has been reviewed. Issues without a “Triaged” label require triage/review.

Comments

@mbelak-dtml
Copy link

Problem Statement
Currently, WorkspaceClient enables getting an OpenAI client via .serving_endpoints.get_open_ai_client, which is very convenient. However, it does not support AsyncOpenAI, which enables asynchronous calls to serving endpoints.

Proposed Solution

Add a new method (get_async_open_ai_client) with the same functionality as get_open_ai_client , except returning an AsyncOpenAI instance.

@parthban-db parthban-db added Feature Request The issue is a request for enhancement or new functionality rather than a bug. Triaged The issue has been reviewed. Issues without a “Triaged” label require triage/review. labels Jan 31, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Feature Request The issue is a request for enhancement or new functionality rather than a bug. Triaged The issue has been reviewed. Issues without a “Triaged” label require triage/review.
Projects
None yet
Development

No branches or pull requests

2 participants