[FEATURE] Get an AsyncOpenAI
client for a serving endpoint.
#847
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.
Problem Statement
Currently,
WorkspaceClient
enables getting anOpenAI
client via.serving_endpoints.get_open_ai_client
, which is very convenient. However, it does not supportAsyncOpenAI
, which enables asynchronous calls to serving endpoints.Proposed Solution
Add a new method (
get_async_open_ai_client
) with the same functionality asget_open_ai_client
, except returning anAsyncOpenAI
instance.The text was updated successfully, but these errors were encountered: