#531: Talk Python in Production

Have you ever thought about getting your small product into production, but are worried about the cost of the big cloud providers? Or maybe you think your current cloud service is over-architected and costing you too much? Well, in this episode, we interview Michael Kennedy, author of "Talk Python in Production," a new book that guides you through deploying web apps at scale with right-sized engineering. Episode sponsors Seer: AI Debugging, Code TALKPYTHON Agntcy Talk Python Courses Links from the show Christopher Trudeau - guest host: www.linkedin.com Michael's personal site: mkennedy.codes Talk Python in Production Book: talkpython.fm glances: github.com btop: github.com Uptimekuma: uptimekuma.org Coolify: coolify.io Talk Python Blog: talkpython.fm Hetzner (€20 credit with link): hetzner.cloud OpalStack: www.opalstack.com Bunny.net CDN: bunny.net Galleries from the book: github.com Pandoc: pandoc.org Docker: www.docker.com Watch this episode on YouTube: youtube.com Episode #531 deep-dive: talkpython.fm/531 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

For years, building interactive widgets in Python notebooks meant wrestling with toolchains, platform quirks, and a mountain of JavaScript machinery. Most developers took one look and backed away slowly. Trevor Manz decided that barrier did not need to exist. His idea was simple: give Python users just enough JavaScript to unlock the web’s interactivity, without dragging along the rest of the web ecosystem. That idea became anywidget, and it is quickly becoming the quiet connective tissue of modern interactive computing. Today we dig into how it works, why it has taken off, and how it might change the way we explore data. Episode sponsors Seer: AI Debugging, Code TALKPYTHON PyCharm, code STRONGER PYTHON Talk Python Courses Links from the show Trevor on GitHub: github.com anywidget GitHub: github.com Trevor's SciPy 2024 Talk: www.youtube.com Marimo GitHub: github.com Myst (Markdown docs): mystmd.org Altair: altair-viz.github.io DuckDB: duckdb.org Mosaic: uwdata.github.io ipywidgets: ipywidgets.readthedocs.io Tension between Web and Data Sci Graphic: blobs.talkpython.fm Quak: github.com Walk through building a widget: anywidget.dev Widget Gallery: anywidget.dev Video: How do I anywidget?: www.youtube.com PyCharm + PSF Fundraiser: pycharm-psf-2025 code STRONGER PYTHON Watch this episode on YouTube: youtube.com Episode #530 deep-dive: talkpython.fm/530 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

A lot of people building software today never took the traditional CS path. They arrived through curiosity, a job that needed automating, or a late-night itch to make something work. This week, David Kopec joins me to talk about rebuilding computer science for exactly those folks, the ones who learned to program first and are now ready to understand the deeper ideas that power the tools they use every day. Episode sponsors Sentry Error Monitoring, Code TALKPYTHON NordStellar Talk Python Courses Links from the show David Kopec: davekopec.com Classic Computer Science Book: amazon.com Computer Science from Scratch Book: computersciencefromscratch.com Computer Science from Scratch at NoStartch (CSFS30 for 30% off): nostarch.com Watch this episode on YouTube: youtube.com Episode #529 deep-dive: talkpython.fm/529 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

In this episode, I’m talking with Vincent Warmerdam about treating LLMs as just another API in your Python app, with clear boundaries, small focused endpoints, and good monitoring. We’ll dig into patterns for wrapping these calls, caching and inspecting responses, and deciding where an LLM API actually earns its keep in your architecture. Episode sponsors Seer: AI Debugging, Code TALKPYTHON NordStellar Talk Python Courses Links from the show Vincent on X: @fishnets88 Vincent on Mastodon: @koaning LLM Building Blocks for Python Co-urse: training.talkpython.fm Top Talk Python Episodes of 2024: talkpython.fm LLM Usage - Datasette: llm.datasette.io DiskCache - Disk Backed Cache (Documentation): grantjenks.com smartfunc - Turn docstrings into LLM-functions: github.com Ollama: ollama.com LM Studio - Local AI: lmstudio.ai marimo - A Next-Generation Python Notebook: marimo.io Pydantic: pydantic.dev Instructor - Complex Schemas & Validation (Python): python.useinstructor.com Diving into PydanticAI with marimo: youtube.com Cline - AI Coding Agent: cline.bot OpenRouter - The Unified Interface For LLMs: openrouter.ai Leafcloud: leaf.cloud OpenAI looks for its "Google Chrome" moment with new Atlas web browser: arstechnica.com Watch this episode on YouTube: youtube.com Episode #528 deep-dive: talkpython.fm/528 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

Today we’re digging into the Model Context Protocol, or MCP. Think LSP for AI: build a small Python service once and your tools and data show up across editors and agents like VS Code, Claude Code, and more. My guest, Den Delimarsky from Microsoft, helps build this space and will keep us honest about what’s solid versus what's just shiny. We’ll keep it practical: transports that actually work, guardrails you can trust, and a tiny server you could ship this week. By the end, you’ll have a clear mental model and a path to plug Python into the internet of agents. Episode sponsors Sentry AI Monitoring, Code TALKPYTHON NordStellar Talk Python Courses Links from the show Den Delimarsky: den.dev Agentic AI Programming for Python Course: training.talkpython.fm Model Context Protocol: modelcontextprotocol.io Model Context Protocol Specification (2025-03-26): modelcontextprotocol.io MCP Python Package (PyPI): pypi.org Awesome MCP Servers (punkpeye) GitHub Repo: github.com Visual Studio Code Docs: Copilot MCP Servers: code.visualstudio.com GitHub MCP Server (GitHub repo): github.com GitHub Blog: Meet the GitHub MCP Registry: github.blog MultiViewer App: multiviewer.app GitHub Blog: Spec-driven development with AI (open source toolkit): github.blog Model Context Protocol Registry (GitHub): github.com mcp (GitHub organization): github.com Tailscale: tailscale.com Watch this episode on YouTube: youtube.com Episode #527 deep-dive: talkpython.fm/527 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

Today, we’re talking about building real AI products with foundation models. Not toy demos, not vibes. We’ll get into the boring dashboards that save launches, evals that change your mind, and the shift from analyst to AI app builder. Our guide is Hugo Bowne-Anderson, educator, podcaster, and data scientist, who’s been in the trenches from scalable Python to LLM apps. If you care about shipping LLM features without burning the house down, stick around. Episode sponsors Posit NordStellar Talk Python Courses Links from the show Hugo Bowne-Anderson: x.com Vanishing Gradients Podcast: vanishinggradients.fireside.fm Fundamentals of Dask: High Performance Data Science Course: training.talkpython.fm Building LLM Applications for Data Scientists and Software Engineers: maven.com marimo: a next-generation Python notebook: marimo.io DevDocs (Offline aggregated docs): devdocs.io Elgato Stream Deck: elgato.com Sentry's Seer: talkpython.fm The End of Programming as We Know It: oreilly.com LorikeetCX AI Concierge: lorikeetcx.ai Text to SQL & AI Query Generator: text2sql.ai Inverse relationship enthusiasm for AI and traditional projects: oreilly.com Watch this episode on YouTube: youtube.com Episode #526 deep-dive: talkpython.fm/526 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

Building a UI in Python usually means choosing between "quick and limited" or "powerful and painful." What if you could write modern, component-based web apps in pure Python and still keep full control? NiceGUI, pronounced "Nice Guy" sits on FastAPI with a Vue/Quasar front end, gives you real components, live updates over websockets, and it’s running in production at Zauberzeug, a German robotic company. On this episode, I’m talking with NiceGUI’s creators, Rodja Trappe and Falko Schindler, about how it works, where it shines, and what’s coming next. With version 3.0 releasing around the same time this episode comes out, we spend the end of the episode celebrating the 3.0 release. Episode sponsors Posit Agntcy Talk Python Courses Links from the show Rodja Trappe: github.com Falko Schindler: github.com NiceGUI 3.0.0 release: github.com Full LLM/Agentic AI docs instructions for NiceGUI: github.com Zauberzeug: zauberzeug.com NiceGUI: nicegui.io NiceGUI GitHub Repository: github.com NiceGUI Authentication Examples: github.com NiceGUI v3.0.0rc1 Release: github.com Valkey: valkey.io Caddy Web Server: caddyserver.com JustPy: justpy.io Tailwind CSS: tailwindcss.com Quasar ECharts v5 Demo: quasar-echarts-v5.netlify.app AG Grid: ag-grid.com Quasar Framework: quasar.dev NiceGUI Interactive Image Documentation: nicegui.io NiceGUI 3D Scene Documentation: nicegui.io Watch this episode on YouTube: youtube.com Episode #525 deep-dive: talkpython.fm/525 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

Python in 2025 is different. Threads really are about to run in parallel, installs finish before your coffee cools, and containers are the default. In this episode, we count down 38 things to learn this year: free-threaded CPython, uv for packaging, Docker and Compose, Kubernetes with Tilt, DuckDB and Arrow, PyScript at the edge, plus MCP for sane AI workflows. Expect practical wins and migration paths. No buzzword bingo, just what pays off in real apps. Join me along with Peter Wang and Calvin Hendrix-Parker for a fun, fast-moving conversation. Episode sponsors Seer: AI Debugging, Code TALKPYTHON Agntcy Talk Python Courses Links from the show Calvin Hendryx-Parker: github.com/calvinhp Peter on BSky: @wang.social Free-Threaded Wheels: hugovk.github.io Tilt: tilt.dev The Five Demons of Python Packaging That Fuel Our ...: youtube.com Talos Linux: talos.dev Docker: Accelerated Container Application Development: docker.com Scaf - Six Feet Up: sixfeetup.com BeeWare: beeware.org PyScript: pyscript.net Cursor: The best way to code with AI: cursor.com Cline - AI Coding, Open Source and Uncompromised: cline.bot Watch this episode on YouTube: youtube.com Episode #524 deep-dive: talkpython.fm/524 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

Python typing got fast enough to feel invisible. Pyrefly is a new, open source type checker and IDE language server from Meta, written in Rust, with a focus on instant feedback and real-world DX. Today, we will dig into what it is, why it exists, and how it plays with the rest of the typing ecosystem. We have Abby Mitchell, Danny Yang, and Kyle Into from Pyrefly here to dive into the project. Episode sponsors Sentry Error Monitoring, Code TALKPYTHON Agntcy Talk Python Courses Links from the show Abby Mitchell: linkedin.com Danny Yang: linkedin.com Kyle Into: linkedin.com Pyrefly: pyrefly.org Pyrefly Documentation: pyrefly.org Pyrefly Installation Guide: pyrefly.org Pyrefly IDE Guide: pyrefly.org Pyrefly GitHub Repository: github.com Pyrefly VS Code Extension: marketplace.visualstudio.com Introducing Pyrefly: A New Type Checker and IDE Experience for Python: engineering.fb.com Pyrefly on PyPI: pypi.org InfoQ Coverage: Meta Pyrefly Python Typechecker: infoq.com Pyrefly Discord Invite: discord.gg Python Typing Conformance (GitHub): github.com Typing Conformance Leaderboard (HTML Preview): htmlpreview.github.io Watch this episode on YouTube: youtube.com Episode #523 deep-dive: talkpython.fm/523 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy

Today we’re turning tiny tips into big wins. Khuyen Tran, creator of CodeCut.ai, has shipped hundreds of bite-size Python and data science snippets across four years. We dig into open-source tools you can use right now, cleaner workflows, and why notebooks and scripts don’t have to be enemies. If you want faster insights with fewer yak-shaves, this one’s packed with takeaways you can apply before lunch. Let’s get into it. Episode sponsors Sentry Error Monitoring, Code TALKPYTHON Agntcy Talk Python Courses Links from the show Khuyen Tran (LinkedIn): linkedin.com Khuyen Tran (GitHub): github.com CodeCut: codecut.ai Production-ready Data Science Book (discount code TalkPython): codecut.ai Why UV Might Be All You Need: codecut.ai How to Structure a Data Science Project for Readability and Transparency: codecut.ai Stop Hard-coding: Use Configuration Files Instead: codecut.ai Simplify Your Python Logging with Loguru: codecut.ai Git for Data Scientists: Learn Git Through Practical Examples: codecut.ai Marimo (A Modern Notebook for Reproducible Data Science): codecut.ai Text Similarity & Fuzzy Matching Guide: codecut.ai Loguru (Python logging made simple): github.com Hydra: hydra.cc Marimo: marimo.io Quarto: quarto.org Show Your Work! Book: austinkleon.com Watch this episode on YouTube: youtube.com Episode #522 deep-dive: talkpython.fm/522 Episode transcripts: talkpython.fm Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython Bluesky: @talkpython.fm Mastodon: @[email protected] X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @[email protected] Michael on X.com: @mkennedy