olehborysevych commented on code in PR #29507: URL: https://github.com/apache/beam/pull/29507#discussion_r1411150275
########## learning/prompts/documentation-lookup/17_advanced_ai_ml.md: ########## @@ -0,0 +1,18 @@ +Prompt: +What are AI and ML capabilities in Apache Beam? +Response: +Apache Beam has a number of built-in [AI and ML capabilities](https://beam.apache.org/documentation/ml/overview/) that enable you to: +- Process large datasets for both preprocessing and model inference. +- Conduct exploratory data analysis and smoothly scale up data pipelines in production as part of your MLOps ecosystem. +- Run your models in production with varying data loads, both in batch and streaming + +See [here](https://beam.apache.org/documentation/patterns/ai-platform/) for common AI Platform integration patterns in Apache Baam. + +The recommended way to implement inference in Apache Beam is by using the [RunInference API](https://beam.apache.org/documentation/sdks/python-machine-learning/). See [here](https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_pytorch_tensorflow_sklearn.ipynb) for more details of how to use RunInference for PyTorch, scikit-learn, and TensorFlow. + +Using pre-trained models in Apache Beam is also supported with [PyTorch](https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_pytorch.ipynb), [Scikit-learn](https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_sklearn.ipynb), and [Tensorflow](https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_tensorflow.ipynb). Running inference on [custom models](https://beam.apache.org/documentation/ml/about-ml/#use-custom-models) is also supported. + +Apache Beam also supports automatic model refresh, which allows you to update models, hot swapping them in a running streaming pipeline with no pause in processing the stream of data, avoiding downtime. See [here](https://beam.apache.org/documentation/ml/about-ml/#automatic-model-refresh) for more details. +More on Apache Beam ML innovations for production can be found [here](https://cloud.google.com/blog/products/ai-machine-learning/dataflow-ml-innovations-on-apache-beam/). + +For more hands-on examples of using Apache Beam ML integration see [here](https://beam.apache.org/documentation/patterns/bqml/) Review Comment: Done -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
