olehborysevych commented on code in PR #29507: URL: https://github.com/apache/beam/pull/29507#discussion_r1411148920
########## 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. 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]
