serving
serving copied to clipboard
An OpenAPI specification of REST API
Please go to Stack Overflow for help and support:
https://stackoverflow.com/questions/tagged/tensorflow-serving
If you open a GitHub issue, here is our policy:
- It must be a bug, a feature request, or a significant problem with documentation (for small docs fixes please send a PR instead).
- The form below must be filled out.
Here's why we have that policy: TensorFlow developers respond to issues. We want to focus on work that benefits the whole community, e.g., fixing bugs and adding features. Support only helps individuals. GitHub also notifies thousands of people when issues are filed. We want them to see you communicating an interesting problem, rather than being redirected to Stack Overflow.
Feature Request
If this is a feature request, please fill out the following form in full:
Describe the problem the feature is intended to solve
It'd be great if there was an OpenAPI spec for the TF Serving REST API. Developers can generate clients for it in many programming languages.
Describe the solution
OpenAPI specification for the REST API
Describe alternatives you've considered
NA
Additional context
Are we considering adding the specification to this repo and supporting it officially? If yes, then I'd like to contribute. Or should we keep it an independent/community effort, and maybe I create a repo of my own.
I have started working on it here. I'll keep this issue updated.
This spec is stil WIP. I'm open to suggestions. If someone wants to see the rendered documentation, visit this.
It would be very useful for us to have this feature. Are there any news on this one?
@ghost,
TensorFlow Serving has two API surfaces (HTTP and gRPC), both of which implement the PredictionService API. Both API surfaces are highly tuned and add minimal latency.
In case if you are interested in contributing to the project to introduce OpenAPI specification for the REST API, you're more than welcomed to send a PR and we'll be happy to review it. Thank you!
@singhniraj08 could potentially help here, was the vision a hard coded open API spec or a spec that'd be worked out from the model signature?
@leohoare I don't think the model signature really matters and it should suffice to indicate the expected response body as per the docs?
https://www.tensorflow.org/tfx/serving/api_rest#request_format https://www.tensorflow.org/tfx/serving/api_rest#request_format_2
This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.
This issue was closed due to lack of activity after being marked stale for past 7 days.