Workflow Inference API is listening on port 8080 and only accessible from localhost by default. To change the default setting, see TorchServe Configuration.
The TorchServe server supports the following APIs:
- Predictions API - Gets predictions from the served model
To get predictions from a workflow, make a REST call to /wfpredict/{workflow_name}:
POST /wfpredict/{workflow_name}
curl -O https://raw.githubusercontent.com/pytorch/serve/master/docs/images/kitten_small.jpg
curl http://localhost:8080/wfpredict/myworkflow -T kitten_small.jpgThe result is JSON object returning the response bytes from the leaf node of the workflow DAG.