Is this a new feature, an improvement, or a change to existing functionality?

New Feature

How would you describe the priority of this feature request

High

Please provide a clear description of problem this feature solves

Provide an async POST endpoint for example "/generate/async/"

1. For long running jobs the endpoint should return a job-id that can be polled via a GET endpoint for e.g. " "/generate/async/job/<>"
2. Ideally the endpoint should be sync for up to "sync-timeout" seconds and fallback to async if the job doesn't complete by that time. When falling back to async it should return a job-id that can be polled.

Describe your ideal solution

A new endpoint "/generate/async" can be added for this purpose. Sample usage:
curl -X 'POST'
'http://localhost:8000/generate/async'
-H 'accept: application/json'
-H 'Content-Type: application/json'
-d '{"input_message": "What is LangSmith?,
"sync_timeout": 60"}'

Additional context

No response

Code of Conduct

• I agree to follow this project's Code of Conduct
• I have searched the open feature requests and have found no duplicates for this feature request