Seq2seq demo with python node#

Build image#

From the root of the repository run:

git clone
cd model_server
make python_image

Deploy OpenVINO Model Server with the Python calculator#


  • image of OVMS with Python support and Optimum installed

Mount the ./servable which contains:

  • and - python scripts which are required for execution and use Hugging Face utilities with optimum-intel acceleration.

  • config.json - which defines which servables should be loaded

  • graph.pbtxt - which defines MediaPipe graph containing python node

cd demos/python_demos/seq2seq_translation
docker run -it --rm -p 9000:9000 -v ${PWD}/servable:/workspace openvino/model_server:py --config_path /workspace/config.json --port 9000

Requesting translation#

Install client requirements

pip3 install -r requirements.txt 

Run the client script

python3 --url localhost:9000

Expected output:

He never went out without a book under his arm, and he often came back with two.

Il n'est jamais sorti sans un livre sous son bras, et il est souvent revenu avec deux.