Miłosz Żeglarski

Could you share more details? You mention python in the title. Do you mean python mediapipe package or do you want to execute python code in mediapipe graph in OVMS?...

Well, python execution is enabled via separate node in the mediapipe graph (there is a dedicated calculator for that). Checkout: https://github.com/openvinotoolkit/model_server/blob/main/docs/python_support/quickstart.md I suppose the easiest solution would be to have...

Could you share Kubernetes deployment configuration? I can see you are running with DEBUG log level - can you share logs from the server in your deployment with a few...

Okay, from the logs it looks like prediction takes ~1.4 s. Are you sure there are no resource constrains for your deployment? If standalone server and K8S deployment run on...

Your standalone server does not have CPU limitations, but your Kubernetes deployment does. Please try removing CPU from limits and requests in resources field and check if performance gets closer...

> Now, this issue is occurring in every deployment. We are running inference containers outside the cluster. So you observe the same issue outside Kubernetes? > Could you help us...

Looks like your JSON is correct. Is it possible to change `true/false` values to `1/0` in `span_mask`?

Hi @HPUedCSLearner, `ignore_eos` as well as other text generation specific parameters are available via OpenAI API which is not supported via Python nodes. To use OpenAI API try: demo: https://github.com/openvinotoolkit/model_server/tree/main/demos/continuous_batching...

Could you share `graph.pbtxt`? Seems like the error is in parsing graph configuration.

In your `graph.pbtxt` in line 14 you're missing quotes - it should be: `tag_index: "LOOPBACK:0",`