From 9488ead080eb7e8e460f7525a5968efc7718e814 Mon Sep 17 00:00:00 2001 From: allegroai <> Date: Tue, 27 Feb 2024 09:44:20 +0200 Subject: [PATCH] Add async pipeline version --- examples/pipeline/readme.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/examples/pipeline/readme.md b/examples/pipeline/readme.md index a8ada83..83d2c42 100644 --- a/examples/pipeline/readme.md +++ b/examples/pipeline/readme.md @@ -15,8 +15,15 @@ Training a scikit-learn model (see example/sklearn) `clearml-serving --id model add --engine sklearn --endpoint "test_model_sklearn_b" --preprocess "examples/sklearn/preprocess.py" --name "train sklearn model" --project "serving examples"` 3. Create pipeline model endpoint: + +Threaded version + `clearml-serving --id model add --engine custom --endpoint "test_model_pipeline" --preprocess "examples/pipeline/preprocess.py"` +AsyncIO version + +`clearml-serving --id model add --engine custom_async --endpoint "test_model_pipeline" --preprocess "examples/pipeline/async_preprocess.py"` + 4. If you already have the `clearml-serving` docker-compose running, it might take it a minute or two to sync with the new endpoint. Or you can run the clearml-serving container independently `docker run -v ~/clearml.conf:/root/clearml.conf -p 8080:8080 -e CLEARML_SERVING_TASK_ID= clearml-serving:latest`