Simplifying RealTime ML Pipelines with Quix Streams: An Open Source Python Library for ML Engineers by Javier Blanco Cordero @ Quix

As data volume and velocity continue to increase, the need for realtime machine learning (ML) is becoming more pressing. However, building realtime ML pipelines can be complex and timeconsuming, requiring expertise in both ML and streaming application development. This talk will address this problem by introducing Quix Streams, an opensource Python library that makes it easy for data scientists and ML engineers to build realtime ML pipelines without having to learn the intricacies of building a streaming application from scratch. In this talk, we’ll cover:

The growing importance of realtime ML in today's application stack, and the use cases for realtime ML processing.
A comparison of different ML architectures (batch, requestresponse, stream, and hybrid) and their pros and cons
The current state of streaming architecture, which is typically Javabased, and the challenges this poses for data scientists and ML engineers who primarily work in Python
An overview of Quix Streams and its features, including a demo of how to use it to build realtime ML pipelines

This talk is relevant for data scientists, ML engineers, and software engineers who are looking to adopt new technologies and practices in order to build realtime ML pipelines and stay current in their field.

The 5th annual Python Web Conf (#PWC2023) inspired attendees to use technology for good. The conference attracted 315 attendees from over 30 countries across 15 time zones. The highly engaging format featured 70 speakers, 5 tracks (including 64 talks and 5 tutorials) and took place virtually on March 1317, 2023 on LoudSwarm by Six Feet Up.

More information about the conference can be found at: https://2023.pythonwebconf.com