Simon Willison’s Weblog

Newsletter

17th May 2025

In addition to my workshop the other day I'm also participating in the poster session at PyCon US this year.

This means that tomorrow (Sunday 18th May) I'll be hanging out next to my poster from 10am to 1pm in Hall A talking to people about my various projects.

I'll confess: I didn't pay close enough attention to the poster information, so when I first put my poster up it looked a little small:

My Datasette poster on a huge black poster board. It looks a bit lonely in the middle surrounded by empty space.

... so I headed to the nearest CVS and printed out some photos to better represent my interests and personality. I'm going for a "teenage bedroom" aesthetic here, I'm very happy with the result:

My Datasette poster is now surrounded by nearly 100 photos - mostly of pelicans, SVGs of pelicans and niche museums I've been to.

Here's the poster in the middle (also available as a PDF). It has columns for Datasette, sqlite-utils and LLM.

Datasette: An ecosystem of tools for finding stories in data. Three projects: Datasette is a tool for exploring and publishing data. It helps data journalists (and everyone else) take data of any shape, analyze and explore it, and publish it as an interactive website and accompanying API. There's a screenshot of the table interface against a legislators table. Datasette has over 180 plugins adding features for visualizing, editing and transforming data. datasette-cluster-map, datasette-graphql, datasette-publish-cloudrun, datasette-comments, datasette-query-assistant, datasette-extract. datasette.io. sqlite-utils is a Python library and CLI tool for manipulating SQLite databases. It aims to make the gap from “I have data” to “that data is in SQLite” as small as possible. There's a code example showing inserting three chickens into a database and configuring full-text search. And in the terminal: sqlite-utils transform places.db roadside_attractions --rename pk id --default name Untitled --drop address. sqlite-utils.datasette.io. LLM is a Python library and CLI tool for interacting with Large Language Models. It provides a plugin-based abstraction over hundreds of different models, both local and hosted, and logs every interaction with them to SQLite. LLMs are proficient at SQL and extremely good at extracting structured data from unstructured text, images and documents. LLM’s asyncio Python library powers several Datasette plugins, including datasette-query-assistant, datasette-enrichments and datasette-extract. llm.datasette.io

If you're at PyCon I'd love to talk to you about things I'm working on!

Update: Thanks to everyone who came along. Here's a 6MB photo of the poster setup. The museums were all from my www.niche-museums.com site and the pelicans riding a bicycle SVGs came from my pelican-riding-a-bicycle tag.

Posted 17th May 2025 at 8:34 pm

Recent articles

This is a note by Simon Willison, posted on 17th May 2025.

Monthly briefing

Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.

Pay me to send you less!

Sponsor & subscribe