February 24-26, 2027
Montreal, Canada
Python Conference
The list of presentations is subject to change without notice.
Python
Working with natural language has always been complex. LLMs have made it more accessible, but production applications still face significant challenges, especially when dealing with multiple languages. This talk covers common pitfalls in multilingual audio and text workflows, along with practical approaches for selecting, evaluating, and combining speech-to-text and language models.
Python
In June 2026, OpenCV released version 5.0, its first major release since 2018. This talk uses live demos to explore its core features and newest additions. From Hough transforms and image stitching to object detection and facial recognition, attendees will see what OpenCV can do and how to apply it in their own projects.
Python
In Python 3.14, there are two ways to do single-process concurrency without being slowed down by the Global Interpreter Lock: Free threading and subinterpreters.
Now it's easier to do concurrent processing that's actually fast. We'll look at the models available to you, how to pick and choose between them, and why you might still want to have the GIL get in your way.
Now it's easier to do concurrent processing that's actually fast. We'll look at the models available to you, how to pick and choose between them, and why you might still want to have the GIL get in your way.
Python
From ChatGPT text boxes to Claude Code and Codex, LLMs evolved from basic chat to tab completion to active digital workers. The secret isn't bigger models: it's the harness. We will build a complete harness live from scratch in Python, demonstrating how it bridges next-token prediction with managed state, action execution, and error handling. Plus, we'll peek at how these execution loops generate training data for future models.
Python
When an AI agents goes wrong, it doesn't fail in one log line. It's across a chain of model decisions, retrieval, retries, and tool calls that jump between services. So, how do we tell what happened with each request, and perhaps why the response wasn't what we wanted? This session is a demo of tracing AI agents using OpenTelemetry and MLflow to understand requests from user -> agent -> tools -> and back, to better understand agent behavior.
Python
Data engineering involves repeating patterns: ingesting, transforming, storing, and serving data all follow the same recipe. Many teams have opted to create an in-house framework, with mixed results. Now, with AI coding assistants, some may see these as obsolete, since ETLs can now be built in minutes. Or should we instead write better, more robust, and agile frameworks? This talk will explore the "why" and the "how" of building your own.
Python
Python is loved for its developer ergonomics but often struggles with CPU-bound performance. Enter PyO3: the bridge between Python and Rust. In this session, we will explore how to build blazing-fast, memory-safe Python extensions without the pain of C or Cython. We will walk through compiling Rust modules with PyO3 and Maturin to help you crush bottlenecks and unlock native performance while keeping your Python code clean.
Python
Let's look at what things are new in Python. We get a new release every year now, so let's take a look at what's come out in 3.14, as well as some features that you might have missed in the last few years.
© 2010-2026 ConFoo. All rights reserved. Code of Conduct
Cookie Consent
To provide the best experiences, the usage of cookies are necessary. Some are essential for the proper functioning of the site, while others help us better cater to your interests.