Talk Python To Me

#529: Computer Science from Scratch

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 [https://talkpython.fm/sentry] NordStellar [https://talkpython.fm/nordstellar] Talk Python Courses [https://talkpython.fm/training] LINKS FROM THE SHOW David Kopec: davekopec.com [https://davekopec.com?featured_on=talkpython] Classic Computer Science Book: amazon.com [https://www.amazon.com/Classic-Computer-Science-Problems-Python/dp/1617295981?featured_on=talkpython] Computer Science from Scratch Book: computersciencefromscratch.com [https://computersciencefromscratch.com?featured_on=talkpython] Computer Science from Scratch at NoStartch (CSFS30 for 30% off): nostarch.com [https://nostarch.com/computer-science-from-scratch?featured_on=talkpython] Watch this episode on YouTube: youtube.com [https://www.youtube.com/watch?v=EVQOoD6cZmg] Episode #529 deep-dive: talkpython.fm/529 [https://talkpython.fm/episodes/show/529/computer-science-from-scratch#takeaways-anchor] Episode transcripts: talkpython.fm [https://talkpython.fm/episodes/transcript/529/computer-science-from-scratch] Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong [https://talkpython.fm/flasksong] ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython [https://talkpython.fm/youtube] Bluesky: @talkpython.fm [https://bsky.app/profile/talkpython.fm] Mastodon: @talkpython@fosstodon.org [https://fosstodon.org/web/@talkpython] X.com: @talkpython [https://x.com/talkpython] Michael on Bluesky: @mkennedy.codes [https://bsky.app/profile/mkennedy.codes?featured_on=talkpython] Michael on Mastodon: @mkennedy@fosstodon.org [https://fosstodon.org/web/@mkennedy] Michael on X.com: @mkennedy [https://x.com/mkennedy?featured_on=talkpython]

#528: Python apps with LLM building blocks

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 [https://talkpython.fm/seer] NordStellar [https://talkpython.fm/nordstellar] Talk Python Courses [https://talkpython.fm/training] LINKS FROM THE SHOW Vincent on X: @fishnets88 [https://x.com/fishnets88?featured_on=talkpython] Vincent on Mastodon: @koaning [https://fosstodon.org/@koaning] LLM Building Blocks for Python Co-urse: training.talkpython.fm [https://training.talkpython.fm/courses/llm-building-blocks-for-python] Top Talk Python Episodes of 2024: talkpython.fm [https://talkpython.fm/blog/posts/top-talk-python-podcast-episodes-of-2024/] LLM Usage - Datasette: llm.datasette.io [https://llm.datasette.io/en/stable/usage.html?featured_on=talkpython] DiskCache - Disk Backed Cache (Documentation): grantjenks.com [https://grantjenks.com/docs/diskcache?featured_on=talkpython] smartfunc - Turn docstrings into LLM-functions: github.com [https://github.com/koaning/smartfunc?featured_on=talkpython] Ollama: ollama.com [https://ollama.com?featured_on=talkpython] LM Studio - Local AI: lmstudio.ai [https://lmstudio.ai?featured_on=talkpython] marimo - A Next-Generation Python Notebook: marimo.io [https://marimo.io?featured_on=talkpython] Pydantic: pydantic.dev [https://pydantic.dev?featured_on=talkpython] Instructor - Complex Schemas & Validation (Python): python.useinstructor.com [https://python.useinstructor.com/#complex-schemas-validation] Diving into PydanticAI with marimo: youtube.com [https://www.youtube.com/watch?v=ujQjqqBka-8] Cline - AI Coding Agent: cline.bot [https://cline.bot?featured_on=talkpython] OpenRouter - The Unified Interface For LLMs: openrouter.ai [https://openrouter.ai?featured_on=talkpython] Leafcloud: leaf.cloud [https://leaf.cloud?featured_on=talkpython] OpenAI looks for its "Google Chrome" moment with new Atlas web browser: arstechnica.com [https://arstechnica.com/ai/2025/10/openais-new-atlas-web-browser-wants-to-let-you-chat-with-a-page/?featured_on=talkpython] Watch this episode on YouTube: youtube.com [https://www.youtube.com/watch?v=t-ReN9jS9sQ] Episode #528 deep-dive: talkpython.fm/528 [https://talkpython.fm/episodes/show/528/python-apps-with-llm-building-blocks#takeaways-anchor] Episode transcripts: talkpython.fm [https://talkpython.fm/episodes/transcript/528/python-apps-with-llm-building-blocks] Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong [https://talkpython.fm/flasksong] ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython [https://talkpython.fm/youtube] Bluesky: @talkpython.fm [https://bsky.app/profile/talkpython.fm] Mastodon: @talkpython@fosstodon.org [https://fosstodon.org/web/@talkpython] X.com: @talkpython [https://x.com/talkpython] Michael on Bluesky: @mkennedy.codes [https://bsky.app/profile/mkennedy.codes?featured_on=talkpython] Michael on Mastodon: @mkennedy@fosstodon.org [https://fosstodon.org/web/@mkennedy] Michael on X.com: @mkennedy [https://x.com/mkennedy?featured_on=talkpython]

#527: MCP Servers for Python Devs

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 [https://talkpython.fm/sentryagents] NordStellar [https://talkpython.fm/nordstellar] Talk Python Courses [https://talkpython.fm/training] LINKS FROM THE SHOW Den Delimarsky: den.dev [https://den.dev?featured_on=talkpython] Agentic AI Programming for Python Course: training.talkpython.fm [https://training.talkpython.fm/courses/agentic-ai-programming-for-python] Model Context Protocol: modelcontextprotocol.io [https://modelcontextprotocol.io?featured_on=talkpython] Model Context Protocol Specification (2025-03-26): modelcontextprotocol.io [https://modelcontextprotocol.io/specification/2025-03-26?featured_on=talkpython] MCP Python Package (PyPI): pypi.org [https://pypi.org/project/mcp?featured_on=talkpython] Awesome MCP Servers (punkpeye) GitHub Repo: github.com [https://github.com/punkpeye/awesome-mcp-servers?featured_on=talkpython] Visual Studio Code Docs: Copilot MCP Servers: code.visualstudio.com [https://code.visualstudio.com/docs/copilot/customization/mcp-servers?featured_on=talkpython] GitHub MCP Server (GitHub repo): github.com [https://github.com/github/github-mcp-server?featured_on=talkpython] GitHub Blog: Meet the GitHub MCP Registry: github.blog [https://github.blog/ai-and-ml/github-copilot/meet-the-github-mcp-registry-the-fastest-way-to-discover-mcp-servers?featured_on=talkpython] MultiViewer App: multiviewer.app [https://multiviewer.app?featured_on=talkpython] GitHub Blog: Spec-driven development with AI (open source toolkit): github.blog [https://github.blog/ai-and-ml/generative-ai/spec-driven-development-with-ai-get-started-with-a-new-open-source-toolkit/?featured_on=talkpython] Model Context Protocol Registry (GitHub): github.com [https://github.com/modelcontextprotocol/registry?featured_on=talkpython] mcp (GitHub organization): github.com [https://github.com/mcp?featured_on=talkpython] Tailscale: tailscale.com [https://tailscale.com?featured_on=talkpython] Watch this episode on YouTube: youtube.com [https://www.youtube.com/watch?v=0V3Tah-BDy4] Episode #527 deep-dive: talkpython.fm/527 [https://talkpython.fm/episodes/show/527/mcp-servers-for-python-devs#takeaways-anchor] Episode transcripts: talkpython.fm [https://talkpython.fm/episodes/transcript/527/mcp-servers-for-python-devs] Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong [https://talkpython.fm/flasksong] ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython [https://talkpython.fm/youtube] Bluesky: @talkpython.fm [https://bsky.app/profile/talkpython.fm] Mastodon: @talkpython@fosstodon.org [https://fosstodon.org/web/@talkpython] X.com: @talkpython [https://x.com/talkpython] Michael on Bluesky: @mkennedy.codes [https://bsky.app/profile/mkennedy.codes?featured_on=talkpython] Michael on Mastodon: @mkennedy@fosstodon.org [https://fosstodon.org/web/@mkennedy] Michael on X.com: @mkennedy [https://x.com/mkennedy?featured_on=talkpython]

#526: Building Data Science with Foundation LLM Models

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 [https://talkpython.fm/ppm] NordStellar [https://talkpython.fm/nordstellar] Talk Python Courses [https://talkpython.fm/training] LINKS FROM THE SHOW Hugo Bowne-Anderson: x.com [https://x.com/hugobowne?featured_on=talkpython] Vanishing Gradients Podcast: vanishinggradients.fireside.fm [https://vanishinggradients.fireside.fm?featured_on=talkpython] Fundamentals of Dask: High Performance Data Science Course: training.talkpython.fm [https://training.talkpython.fm/courses/fundamentals-of-dask-getting-up-to-speed] Building LLM Applications for Data Scientists and Software Engineers: maven.com [https://maven.com/hugo-stefan/building-llm-apps-ds-and-swe-from-first-principles?promoCode=friendsoftalkpython] marimo: a next-generation Python notebook: marimo.io [https://marimo.io?featured_on=talkpython] DevDocs (Offline aggregated docs): devdocs.io [https://devdocs.io?featured_on=talkpython] Elgato Stream Deck: elgato.com [https://www.elgato.com/us/en/p/stream-deck?featured_on=talkpython] Sentry's Seer: talkpython.fm [https://talkpython.fm/seer] The End of Programming as We Know It: oreilly.com [https://www.oreilly.com/radar/the-end-of-programming-as-we-know-it/?featured_on=talkpython] LorikeetCX AI Concierge: lorikeetcx.ai [https://www.lorikeetcx.ai?featured_on=talkpython] Text to SQL & AI Query Generator: text2sql.ai [https://www.text2sql.ai?featured_on=talkpython] Inverse relationship enthusiasm for AI and traditional projects: oreilly.com [https://www.oreilly.com/radar/wp-content/uploads/sites/3/2025/04/LLM-SDLC_Fig1_edit3-1.png?featured_on=talkpython] Watch this episode on YouTube: youtube.com [https://www.youtube.com/watch?v=_LFdKjsKdPE] Episode #526 deep-dive: talkpython.fm/526 [https://talkpython.fm/episodes/show/526/building-data-science-with-foundation-llm-models#takeaways-anchor] Episode transcripts: talkpython.fm [https://talkpython.fm/episodes/transcript/526/building-data-science-with-foundation-llm-models] Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong [https://talkpython.fm/flasksong] ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython [https://talkpython.fm/youtube] Bluesky: @talkpython.fm [https://bsky.app/profile/talkpython.fm] Mastodon: @talkpython@fosstodon.org [https://fosstodon.org/web/@talkpython] X.com: @talkpython [https://x.com/talkpython] Michael on Bluesky: @mkennedy.codes [https://bsky.app/profile/mkennedy.codes?featured_on=talkpython] Michael on Mastodon: @mkennedy@fosstodon.org [https://fosstodon.org/web/@mkennedy] Michael on X.com: @mkennedy [https://x.com/mkennedy?featured_on=talkpython]

#525: NiceGUI Goes 3.0

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 [https://talkpython.fm/connect] Agntcy [https://talkpython.fm/agntcy] Talk Python Courses [https://talkpython.fm/training] LINKS FROM THE SHOW Rodja Trappe: github.com [https://github.com/rodja?featured_on=talkpython] Falko Schindler: github.com [https://github.com/falkoschindler?featured_on=talkpython] NiceGUI 3.0.0 release: github.com [https://github.com/zauberzeug/nicegui/releases/tag/v3.0.0?featured_on=talkpython] Full LLM/Agentic AI docs instructions for NiceGUI: github.com [https://github.com/zauberzeug/nicegui/wiki#chatgpt-and-other-llms] Zauberzeug: zauberzeug.com [https://zauberzeug.com?featured_on=talkpython] NiceGUI: nicegui.io [https://nicegui.io?featured_on=talkpython] NiceGUI GitHub Repository: github.com [https://github.com/zauberzeug/nicegui/?featured_on=talkpython] NiceGUI Authentication Examples: github.com [https://github.com/zauberzeug/nicegui/blob/main/examples/authentication?featured_on=talkpython] NiceGUI v3.0.0rc1 Release: github.com [https://github.com/zauberzeug/nicegui/releases/tag/v3.0.0rc1?featured_on=talkpython] Valkey: valkey.io [https://valkey.io?featured_on=talkpython] Caddy Web Server: caddyserver.com [https://caddyserver.com?featured_on=talkpython] JustPy: justpy.io [https://justpy.io?featured_on=talkpython] Tailwind CSS: tailwindcss.com [https://tailwindcss.com?featured_on=talkpython] Quasar ECharts v5 Demo: quasar-echarts-v5.netlify.app [https://quasar-echarts-v5.netlify.app?featured_on=talkpython] AG Grid: ag-grid.com [https://www.ag-grid.com?featured_on=talkpython] Quasar Framework: quasar.dev [https://quasar.dev?featured_on=talkpython] NiceGUI Interactive Image Documentation: nicegui.io [https://nicegui.io/documentation/interactive_image?featured_on=talkpython] NiceGUI 3D Scene Documentation: nicegui.io [https://nicegui.io/documentation/scene#3d_scene] Watch this episode on YouTube: youtube.com [https://www.youtube.com/watch?v=74UXonJfl6o] Episode #525 deep-dive: talkpython.fm/525 [https://talkpython.fm/episodes/show/525/nicegui-goes-3.0#takeaways-anchor] Episode transcripts: talkpython.fm [https://talkpython.fm/episodes/transcript/525/nicegui-goes-3.0] Theme Song: Developer Rap 🥁 Served in a Flask 🎸: talkpython.fm/flasksong [https://talkpython.fm/flasksong] ---== Don't be a stranger ==--- YouTube: youtube.com/@talkpython [https://talkpython.fm/youtube] Bluesky: @talkpython.fm [https://bsky.app/profile/talkpython.fm] Mastodon: @talkpython@fosstodon.org [https://fosstodon.org/web/@talkpython] X.com: @talkpython [https://x.com/talkpython] Michael on Bluesky: @mkennedy.codes [https://bsky.app/profile/mkennedy.codes?featured_on=talkpython] Michael on Mastodon: @mkennedy@fosstodon.org [https://fosstodon.org/web/@mkennedy] Michael on X.com: @mkennedy [https://x.com/mkennedy?featured_on=talkpython]