Host on JCloud#
First, you need a Flow YAML file for deploy. A minimum YAML file is as follows:
jtype: Flow executors: - uses: jinahub+docker://CLIPTorchEncoder
jtype: Flow executors: - uses: jinahub+docker://CLIPOnnxEncoder
port is unnecessary here as JCloud will assign a new hostname and port for any deployed service.
Executors must start with
jinahub+docker:// as it is required by JCloud. We currently provide containerized executors
jinahub+docker://CLIPOnnxEncoder on Jina Hub. They are automatically synced on the new release of
To enable GPU on JCloud, you need to configure it in the YAML file and use prebuilt docker GPU images. For example,
jtype: Flow executors: - uses: jinahub+docker://CLIPTorchEncoder/latest-gpu jcloud: resources: gpu: shared
Please refer here for more details on using GPU in JCloud.
Notice that you must specify a docker image GPU tag for your executor to utilize the GPU. For example
See the ‘Tag’ section in CLIPTorchEncoder and CLIPOnnxEncoder for docker image GPU tags.
jc deploy torch-flow.yml
jc deploy onnx-flow.yml
If Flow is successfully deployed you will see:
You can now connect to it via client by setting
server as the URL given by JCloud:
from clip_client import Client c = Client( 'grpcs://174eb69ba3.wolf.jina.ai' ) # This is the URL you get from previous step c.profile()