Talk Python To Me

When you type a question into ChatGPT, the model only has what you typed to work with. But tools like Claude Code can plan, iterate, test, and recover from mistakes. They work more like we do. The difference is the agent harness: Planning tools, file system access, sub-agents, and carefully crafted system prompts that turn a raw LLM into something genuinely capable. Sydney Runkle is back on Talk Python representing LangChain and their new open source library, Deep Agents: A framework for building your own deep agents with plain Python functions, middleware hooks, and MCP support. This is how the magic works under the hood. Episode sponsors Sentry Error Monitoring, Code talkpython26 Temporal Talk Python Courses Links from the show Guest Sydney Runkle: github.com Claude Code uses: x.com Deep Research: openai.com Manus: manus.im Blog post announcement: blog.langchain.com Claudes system prompt: github.com sub agents: docs.anthropic.com the quick start: docs.langchain.com CLIs: github.com Talk Python's CLI: talkpython.fm custom tools: docs.langchain.com DeepAgents Examples: github.com Custom Middleware: docs.langchain.com Built in middleware: docs.langchain.com Improving Deep Agents with harness engineering: blog.langchain.com Prebuilt middleware: docs.langchain.com Watch this episode on YouTube: youtube.com Episode #543 deep-dive: talkpython.fm/543 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

If you've built documentation in the Python ecosystem, chances are you've used Martin Donath's work. His Material for MKDocs powers docs for FastAPI, uv, AWS, OpenAI, and tens of thousands of other projects. But when MKDocs 2.0 took a direction that would break Material and 300 ecosystem plugins, Martin went back to the drawing board. The result is Zensical: A new static site generator with a Rust core, differential builds in milliseconds instead of minutes, and a migration path designed to bring the whole community along. Episode sponsors Sentry Error Monitoring, Code talkpython26 Talk Python Courses Links from the show Guest Martin Donath: github.com Zensical: zensical.org Material for MkDocs: squidfunk.github.io Getting Started: zensical.org Github pages: docs.github.com Cloudflare pages: pages.cloudflare.com Michaels Example: gist.github.com Material for MkDocs: zensical.org gohugo.io/content-management/shortcodes: gohugo.io a sense of size of the project: blobs.talkpython.fm Zensical Spark: zensical.org Watch this episode on YouTube: youtube.com Episode #542 deep-dive: talkpython.fm/542 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

When LLMs write code to accomplish a task, that code has to actually run somewhere. And right now, the options aren't great. Spin up a sandboxed container and you're paying a full second of cold start overhead plus the complexity of another service. Let the LLM loose on your actual machine and... well, you'd better be watching. On this episode, I sit down with Samuel Colvin, creator of Pydantic, now at 10 billion downloads, to explore Monty, a Python interpreter written from scratch in Rust, purpose-built to run LLM-generated code. It starts in microseconds, is completely sandboxed by design, and can even serialize its entire state to a database and resume later. We dig into why this deliberately limited interpreter might be exactly what the AI agent era needs. Episode sponsors Talk Python Courses Python in Production Links from the show Guest Samuel Colvin: github.com CPython: github.com IronPython: ironpython.net Jython: www.jython.org Pyodide: pyodide.com monty: github.com Pydantic AI: pydantic.dev Python AI conference: pyai.events bashkit: github.com just-bash: github.com Narwhals: narwhals-dev.github.io Polars: pola.rs Strands Agents: aws.amazon.com Subscribe Running Pydantic’s Monty Rust sandboxed Python subset in WebAssembly: simonwillison.net Rust Python: github.com Valgrind: valgrind.org Cod Speed: codspeed.io Watch this episode on YouTube: youtube.com Episode #541 deep-dive: talkpython.fm/541 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

Monorepos -- you've heard the talks, you've read the blog posts, maybe you've seen a few tantalizing glimpses into how Google or Meta organize their massive codebases. But it's often in the abstract and behind closed doors. What if you could crack open a real, production monorepo, one with over a million lines of Python and over 100 of sub-packages, and actually see how it's built, step by step, using modern tools and standards? That's exactly what Apache Airflow gives us. On this episode, I sit down with Jarek Potiuk and Amogh Desai, two of Airflow's top contributors, to go inside one of the largest open-source Python monorepos in the world and learn how they manage it with uv, pyproject.toml, and the latest packaging standards, so you can apply those same patterns to your own projects. Episode sponsors Agentic AI Course Python in Production Talk Python Courses Links from the show Guests Amogh Desai: github.com Jarek's GitHub: github.com definition of a monorepo: monorepo.tools airflow: airflow.apache.org Activity: github.com OpenAI: airflowsummit.org Part 1. Pains of big modular Python projects: medium.com Part 2. Modern Python packaging standards and tools for monorepos: medium.com Part 3. Monorepo on steroids - modular prek hooks: medium.com Part 4. Shared “static” libraries in Airflow monorepo: medium.com PEP-440: peps.python.org PEP-517: peps.python.org PEP-518: peps.python.org PEP-566: peps.python.org PEP-561: peps.python.org PEP-660: peps.python.org PEP-621: peps.python.org PEP-685: peps.python.org PEP-723: peps.python.org PEP-735: peps.python.org uv: docs.astral.sh uv workspaces: blobs.talkpython.fm prek.j178.dev: prek.j178.dev your presentation at FOSDEM26: fosdem.org Tallyman: github.com Watch this episode on YouTube: youtube.com Episode #540 deep-dive: talkpython.fm/540 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

You're adding type hints to your Python code, your editor is happy, autocomplete is working great. But then you switch tools and suddenly there are red squiggles everywhere. Who decides what a float annotation actually means? Or whether passing None where an int is expected should be an error? It turns out there's a five-person council dedicated to exactly these questions -- and two brand-new Rust-based type checkers are raising the bar. On this episode, I sit down with three members of the Python Typing Council -- Jelle Zijlstra, Rebecca Chen, and Carl Meyer -- to learn how the type system is governed, where the spec and the type checkers agree and disagree, and get the council's official advice on how much typing is just enough. Episode sponsors Sentry Error Monitoring, Code talkpython26 Agentic AI Course Talk Python Courses Links from the show Guests Carl Meyer: github.com Jelle Zijlstra: jellezijlstra.github.io Rebecca Chen: github.com Typing Council: github.com typing.python.org: typing.python.org details here: github.com ty: docs.astral.sh pyrefly: pyrefly.org conformance test suite project: github.com typeshed: github.com Stub files: mypy.readthedocs.io Pydantic: pydantic.dev Beartype: github.com TOAD AI: github.com PEP 747 – Annotating Type Forms: peps.python.org PEP 724 – Stricter Type Guards: peps.python.org Python Typing Repo (PRs and Issues): github.com Watch this episode on YouTube: youtube.com Episode #539 deep-dive: talkpython.fm/539 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

Digital humanities sounds niche, until you realize it can mean a searchable archive of U.S. amendment proposals, Irish folklore, or pigment science in ancient art. Today I’m talking with David Flood from Harvard’s DARTH team about an unglamorous problem: What happens when the grant ends but the website can’t. His answer, static sites, client-side search, and sneaky Python. Let’s dive in. Episode sponsors Sentry Error Monitoring, Code talkpython26 Command Book Talk Python Courses Links from the show Guest David Flood: davidaflood.com DARTH: digitalhumanities.fas.harvard.edu Amendments Project: digitalhumanities.fas.harvard.edu Fionn Folklore Database: fionnfolklore.org Mapping Color in History: iiif.harvard.edu Apatosaurus: apatosaurus.io Criticus: github.com github.com/palewire/django-bakery: github.com sigsim.acm.org/conf/pads/2026/blog/artifact-evaluation: sigsim.acm.org Hugo: gohugo.io Water Stories: waterstories.fas.harvard.edu Tsumeb Mine Notebook: tmn.fas.harvard.edu Dharma and Punya: dharmapunya2019.org Pagefind library: pagefind.app django_webassembly: github.com Astro Static Site Generator: astro.build PageFind Python Lib: pypi.org Frozen-Flask: frozen-flask.readthedocs.io Watch this episode on YouTube: youtube.com Episode #538 deep-dive: talkpython.fm/538 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

You love building web apps with Python, and HTMX got you excited about the hypermedia approach -- let the server drive the HTML, skip the JavaScript build step, keep things simple. But then you hit that last 10%: You need Alpine.js for interactivity, your state gets out of sync, and suddenly you're juggling two unrelated libraries that weren't designed to work together. What if there was a single 11-kilobyte framework that gave you everything HTMX and Alpine do, and more, with real-time updates, multiplayer collaboration out of the box, and performance so fast you're actually bottlenecked by the monitor's refresh rate? That's Datastar. On this episode, I sit down with its creator Delaney Gillilan, core maintainer Ben Croker, and Datastar convert Chris May to explore how this backend-driven, server-sent-events-first framework is changing the way full-stack developers think about the modern web. Episode sponsors Sentry Error Monitoring, Code talkpython26 Command Book Talk Python Courses Links from the show Guests Delaney Gillilan: linkedin.com Ben Croker: x.com Chris May: everydaysuperpowers.dev Datastar: data-star.dev HTMX: htmx.org AlpineJS: alpinejs.dev Core Attribute Tour: data-star.dev data-star.dev/examples: data-star.dev github.com/starfederation/datastar-python: github.com VSCode: marketplace.visualstudio.com OpenVSX: open-vsx.org PyCharm/Intellij plugin: plugins.jetbrains.com data-star.dev/datastar_pro: data-star.dev gg: discord.gg HTML-ivating your Django web app's experience with HTMX, AlpineJS, and streaming HTML - Chris May: www.youtube.com Senior Engineer tries Vibe Coding: www.youtube.com 1 Billion Checkboxes: checkboxes.andersmurphy.com Game of life example: example.andersmurphy.com Watch this episode on YouTube: youtube.com Episode #537 deep-dive: talkpython.fm/537 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

You've built your FastAPI app, it's running great locally, and now you want to share it with the world. But then reality hits -- containers, load balancers, HTTPS certificates, cloud consoles with 200 options. What if deploying was just one command? That's exactly what Sebastian Ramirez and the FastAPI Cloud team are building. On this episode, I sit down with Sebastian, Patrick Arminio, Savannah Ostrowski, and Jonathan Ehwald to go inside FastAPI Cloud, explore what it means to build a "Pythonic" cloud, and dig into how this commercial venture is actually making FastAPI the open-source project stronger than ever. Episode sponsors Command Book Python in Production Talk Python Courses Links from the show Guests Sebastián Ramírez: github.com Savannah Ostrowski: github.com Patrick Arminio: github.com Jonathan Ehwald: github.com FastAPI labs: fastapilabs.com quickstart: fastapicloud.com an episode on diskcache: talkpython.fm Fastar: github.com FastAPI: The Documentary: www.youtube.com Tailwind CSS Situation: adams-morning-walk.transistor.fm FastAPI Job Meme: fastapi.meme Migrate an Existing Project: fastapicloud.com Join the waitlist: fastapicloud.com Talk Python CLI Talk Python CLI Announcement: talkpython.fm Talk Python CLI GitHub: github.com Command Book Download Command Book: commandbookapp.com Announcement post: mkennedy.codes Watch this episode on YouTube: youtube.com Episode #536 deep-dive: talkpython.fm/536 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

Building on the web is like working with the perfect clay. It’s malleable and can become almost anything. But too often, frameworks try to hide the web’s best parts away from us. Today, we’re looking at PyView, a project that brings the real-time power of Phoenix LiveView directly into the Python world. I'm joined by Larry Ogrodnek to dive into PyView. Episode sponsors Talk Python Courses Python in Production Links from the show Guest Larry Ogrodnek: hachyderm.io pyview.rocks: pyview.rocks Phoenix LiveView: github.com this section: pyview.rocks Core Concepts: pyview.rocks Socket and Context: pyview.rocks Event Handling: pyview.rocks LiveComponents: pyview.rocks Routing: pyview.rocks Templating: pyview.rocks HTML Templates: pyview.rocks T-String Templates: pyview.rocks File Uploads: pyview.rocks Streams: pyview.rocks Sessions & Authentication: pyview.rocks Single-File Apps: pyview.rocks starlette: starlette.dev wsproto: github.com apscheduler: github.com t-dom project: github.com Watch this episode on YouTube: youtube.com Episode #535 deep-dive: talkpython.fm/535 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

Your cloud SSD is sitting there, bored, and it would like a job. Today we’re putting it to work with DiskCache, a simple, practical cache built on SQLite that can speed things up without spinning up Redis or extra services. Once you start to see what it can do, a universe of possibilities opens up. We're joined by Vincent Warmerdam to dive into DiskCache. Episode sponsors Talk Python Courses Python in Production Links from the show diskcache docs: grantjenks.com LLM Building Blocks for Python course: training.talkpython.fm JSONDisk: grantjenks.com Git Code Archaeology Charts: koaning.github.io Talk Python Cache Admin UI: blobs.talkpython.fm Litestream SQLite streaming: litestream.io Plash hosting: pla.sh Watch this episode on YouTube: youtube.com Episode #534 deep-dive: talkpython.fm/534 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

Today on Talk Python, the creators behind FastAPI, Flask, Django, Quart, and Litestar get practical about running apps based on their framework in production. Deployment patterns, async gotchas, servers, scaling, and the stuff you only learn at 2 a.m. when the pager goes off. For Django, we have Carlton Gibson and Jeff Triplet. For Flask, we have David Lord and Phil Jones, and on team Litestar we have Janek Nouvertné and Cody Fincher, and finally Sebastián Ramírez from FastAPI is here. Let’s jump in. Episode sponsors Talk Python Courses Python in Production Links from the show Carlton Gibson - Django: github.com Sebastian Ramirez - FastAPI: github.com David Lord - Flask: davidism.com Phil Jones - Flask and Quartz(async): pgjones.dev Yanik Nouvertne - LiteStar: github.com Cody Fincher - LiteStar: github.com Jeff Triplett - Django: jefftriplett.com Django: www.djangoproject.com Flask: flask.palletsprojects.com Quart: quart.palletsprojects.com Litestar: litestar.dev FastAPI: fastapi.tiangolo.com Coolify: coolify.io ASGI: asgi.readthedocs.io WSGI (PEP 3333): peps.python.org Granian: github.com Hypercorn: github.com uvicorn: uvicorn.dev Gunicorn: gunicorn.org Hypercorn: hypercorn.readthedocs.io Daphne: github.com Nginx: nginx.org Docker: www.docker.com Kubernetes: kubernetes.io PostgreSQL: www.postgresql.org SQLite: www.sqlite.org Celery: docs.celeryq.dev SQLAlchemy: www.sqlalchemy.org Django REST framework: www.django-rest-framework.org Jinja: jinja.palletsprojects.com Click: click.palletsprojects.com HTMX: htmx.org Server-Sent Events (SSE): developer.mozilla.org WebSockets (RFC 6455): www.rfc-editor.org HTTP/2 (RFC 9113): www.rfc-editor.org HTTP/3 (RFC 9114): www.rfc-editor.org uv: docs.astral.sh Amazon Web Services (AWS): aws.amazon.com Microsoft Azure: azure.microsoft.com Google Cloud Run: cloud.google.com Amazon ECS: aws.amazon.com AlloyDB for PostgreSQL: cloud.google.com Fly.io: fly.io Render: render.com Cloudflare: www.cloudflare.com Fastly: www.fastly.com Watch this episode on YouTube: youtube.com Episode #533 deep-dive: talkpython.fm/533 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

Python in 2025 is in a delightfully refreshing place: the GIL's days are numbered, packaging is getting sharper tools, and the type checkers are multiplying like gremlins snacking after midnight. On this episode, we have an amazing panel to give us a range of perspectives on what matter in 2025 in Python. We have Barry Warsaw, Brett Cannon, Gregory Kapfhammer, Jodie Burchell, Reuven Lerner, and Thomas Wouters on to give us their thoughts. Episode sponsors Seer: AI Debugging, Code TALKPYTHON Talk Python Courses Links from the show Python Software Foundation (PSF): www.python.org PEP 810: Explicit lazy imports: peps.python.org PEP 779: Free-threaded Python is officially supported: peps.python.org PEP 723: Inline script metadata: peps.python.org PyCharm: www.jetbrains.com JetBrains: www.jetbrains.com Visual Studio Code: code.visualstudio.com pandas: pandas.pydata.org PydanticAI: ai.pydantic.dev OpenAI API docs: platform.openai.com uv: docs.astral.sh Hatch: github.com PDM: pdm-project.org Poetry: python-poetry.org Project Jupyter: jupyter.org JupyterLite: jupyterlite.readthedocs.io PEP 690: Lazy Imports: peps.python.org PyTorch: pytorch.org Python concurrent.futures: docs.python.org Python Package Index (PyPI): pypi.org EuroPython: tickets.europython.eu TensorFlow: www.tensorflow.org Keras: keras.io PyCon US: us.pycon.org NumFOCUS: numfocus.org Python discussion forum (discuss.python.org): discuss.python.org Language Server Protocol: microsoft.github.io mypy: mypy-lang.org Pyright: github.com Pylance: marketplace.visualstudio.com Pyrefly: github.com ty: github.com Zuban: docs.zubanls.com Jedi: jedi.readthedocs.io GitHub: github.com PyOhio: www.pyohio.org Watch this episode on YouTube: youtube.com Episode #532 deep-dive: talkpython.fm/532 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy

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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org 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: @talkpython@fosstodon.org X.com: @talkpython Michael on Bluesky: @mkennedy.codes Michael on Mastodon: @mkennedy@fosstodon.org Michael on X.com: @mkennedy