Simon Willison’s Weblog

Datasette 1.0a22. New Datasette 1.0 alpha, adding some small features we needed to properly integrate the new permissions system with Datasette Cloud:

• datasette serve --default-deny option for running Datasette configured to deny all permissions by default. (#2592)
• datasette.is_client() method for detecting if code is executing inside a datasette.client request. (#2594)

Plus a developer experience improvement for plugin authors:

• datasette.pm property can now be used to register and unregister plugins in tests. (#2595)

# 13th November 2025, 11:04 pm / projects, datasette-cloud, annotated-release-notes, datasette

Open redirect endpoint in Datasette prior to 0.65.2 and 1.0a21. This GitHub security advisory covers two new releases of Datasette that I shipped today, both addressing the same open redirect issue with a fix by James Jefferies.

Datasette 0.65.2 fixes the bug and also adds Python 3.14 support and a datasette publish cloudrun fix.

Datasette 1.0a21 also has that Cloud Run fix and two other small new features:

• New datasette --get /path --headers option for inspecting the headers returned by a path. (#2578)
• New datasette.client.get(..., skip_permission_checks=True) parameter to bypass permission checks when making requests using the internal client. (#2583)

I decided to include the Cloud Run deployment fix so anyone with Datasette instances deployed to Cloud Run can update them with the new patched versions.

# 5th November 2025, 11:11 pm / annotated-release-notes, security, datasette, cloudrun

llm-openrouter 0.5. New release of my LLM plugin for accessing models made available via OpenRouter. The release notes in full:

• Support for tool calling. Thanks, James Sanford. #43
• Support for reasoning options, for example llm -m openrouter/openai/gpt-5 'prove dogs exist' -o reasoning_effort medium. #45

Tool calling is a really big deal, as it means you can now use the plugin to try out tools (and build agents, if you like) against any of the 179 tool-enabled models on that platform:

llm install llm-openrouter
llm keys set openrouter
# Paste key here
llm models --tools | grep 'OpenRouter:' | wc -l
# Outputs 179

Quite a few of the models hosted on OpenRouter can be accessed for free. Here's a tool-usage example using the llm-tools-datasette plugin against the new Grok 4 Fast model:

llm install llm-tools-datasette
llm -m openrouter/x-ai/grok-4-fast:free -T 'Datasette("https://datasette.io/content")' 'Count available plugins'

Outputs:

There are 154 available plugins.

The output of llm logs -cu shows the tool calls and SQL queries it executed to get that result.

# 21st September 2025, 12:24 am / llm, llm-reasoning, llm-tool-use, ai, llms, generative-ai, projects, openrouter, datasette

Saying Bye to Glitch (via) Pirijan, co-creator of Glitch - who stopped working on it six years ago, so has the benefit of distance:

Here lies Glitch, a place on the web you could go to write up a website or a node.js server that would be hosted and updated as you type. 🥀 RIP 2015 – 2025.

Pirijan continues with a poignant retrospective about Glitch's early origins at Fog Greek with the vision of providing "web development with real code that was as easy as editing a Google Doc". Their conclusion:

I still believe there’s a market for easy and fun web development and hosting, but a product like this needs power-users and enthusiasts willing to pay for it. To build any kind of prosumer software, you do have to be an optimist and believe that enough of the world still cares about quality and craft.

Glitch will be shutting down project hosting and user profiles on July 8th.

Code will be available to download until the end of the year. Glitch have an official Python export script that can download all of your projects and assets.

Jenn Schiffer, formerly Director of Community at Glitch and then Fastly, is a little more salty:

all that being said, i do sincerely want to thank fastly for giving glitch the opportunity to live to its 3-year acqui-versary this week. they generously took in a beautiful flower and placed it upon their sunny window sill with hopes to grow it more. the problem is they chose to never water it, and anyone with an elementary school education know what happens then. i wish us all a merry august earnings call season.

I'm very sad to see Glitch go. I've been pointing people to my tutorial on Running Datasette on Glitch for 5 years now, it was a fantastic way to help people quickly get started hosting their own projects.

# 29th May 2025, 8:36 pm / glitch, fastly, datasette

django-simple-deploy. Eric Matthes presented a lightning talk about this project at PyCon US this morning. "Django has a deploy command now". You can run it like this:

pip install django-simple-deploy[fly_io]
# Add django_simple_deploy to INSTALLED_APPS.
python manage.py deploy --automate-all

It's plugin-based (inspired by Datasette!) and the project has stable plugins for three hosting platforms: dsd-flyio, dsd-heroku and dsd-platformsh.

Currently in development: dsd-vps - a plugin that should work with any VPS provider, using Paramiko to connect to a newly created instance and run all of the commands needed to start serving a Django application.

# 17th May 2025, 12:49 pm / fly, heroku, datasette, plugins, django, paramiko, python

Introducing Datasette for Newsrooms. We're introducing a new product suite today called Datasette for Newsrooms - a bundled collection of Datasette Cloud features built specifically for investigative journalists and data teams. We're describing it as an all-in-one data store, search engine, and collaboration platform designed to make working with data in a newsroom easier, faster, and more transparent.

If your newsroom could benefit from a managed version of Datasette we would love to hear from you. We're offering it to nonprofit newsrooms for free for the first year (they can pay us in feedback), and we have a two month trial for everyone else.

Get in touch at hello@datasette.cloud if you'd like to try it out.

One crucial detail: we will help you get started - we'll load data into your instance for you (you get some free data engineering!) and walk you through how to use it, and we will eagerly consume any feedback you have for us and prioritize shipping anything that helps you use the tool. Our unofficial goal: we want someone to win a Pulitzer for investigative reporting where our tool played a tiny part in their reporting process.

Here's an animated GIF demo (taken from our new Newsrooms landing page) of my favorite recent feature: the ability to extract structured data into a table starting with an unstructured PDF, using the latest version of the datasette-extract plugin.

# 24th April 2025, 9:51 pm / datasette-cloud, structured-extraction, datasette, projects, data-journalism, journalism

files-to-prompt 0.5. My files-to-prompt tool (originally built using Claude 3 Opus back in April) had been accumulating a bunch of issues and PRs - I finally got around to spending some time with it and pushed a fresh release:

• New -n/--line-numbers flag for including line numbers in the output. Thanks, Dan Clayton. #38
• Fix for utf-8 handling on Windows. Thanks, David Jarman. #36
• --ignore patterns are now matched against directory names as well as file names, unless you pass the new --ignore-files-only flag. Thanks, Nick Powell. #30

I use this tool myself on an almost daily basis - it's fantastic for quickly answering questions about code. Recently I've been plugging it into Gemini 2.0 with its 2 million token context length, running recipes like this one:

git clone https://github.com/bytecodealliance/componentize-py
cd componentize-py
files-to-prompt . -c | llm -m gemini-2.0-pro-exp-02-05 \
  -s 'How does this work? Does it include a python compiler or AST trick of some sort?'

I ran that question against the bytecodealliance/componentize-py repo - which provides a tool for turning Python code into compiled WASM - and got this really useful answer.

Here's another example. I decided to have o3-mini review how Datasette handles concurrent SQLite connections from async Python code - so I ran this:

git clone https://github.com/simonw/datasette
cd datasette/datasette
files-to-prompt database.py utils/__init__.py -c | \
  llm -m o3-mini -o reasoning_effort high \
  -s 'Output in markdown a detailed analysis of how this code handles the challenge of running SQLite queries from a Python asyncio application. Explain how it works in the first section, then explore the pros and cons of this design. In a final section propose alternative mechanisms that might work better.'

Here's the result. It did an extremely good job of explaining how my code works - despite being fed just the Python and none of the other documentation. Then it made some solid recommendations for potential alternatives.

I added a couple of follow-up questions (using llm -c) which resulted in a full working prototype of an alternative threadpool mechanism, plus some benchmarks.

One final example: I decided to see if there were any undocumented features in Litestream, so I checked out the repo and ran a prompt against just the .go files in that project:

git clone https://github.com/benbjohnson/litestream
cd litestream
files-to-prompt . -e go -c | llm -m o3-mini \
  -s 'Write extensive user documentation for this project in markdown'

Once again, o3-mini provided a really impressively detailed set of unofficial documentation derived purely from reading the source.

# 14th February 2025, 4:14 am / projects, llms, gemini, llm, ai-assisted-programming, generative-ai, ai, webassembly, python, async, datasette, sqlite, litestream, files-to-prompt, llm-reasoning

Datasette 1.0a17. New Datasette alpha, with a bunch of small changes and bug fixes accumulated over the past few months. Some (minor) highlights:

• The register_magic_parameters(datasette) plugin hook can now register async functions. (#2441)
• Breadcrumbs on database and table pages now include a consistent self-link for resetting query string parameters. (#2454)
• New internal methods datasette.set_actor_cookie() and datasette.delete_actor_cookie(), described here. (#1690)
• /-/permissions page now shows a list of all permissions registered by plugins. (#1943)
• If a table has a single unique text column Datasette now detects that as the foreign key label for that table. (#2458)
• The /-/permissions page now includes options for filtering or exclude permission checks recorded against the current user. (#2460)

I was incentivized to push this release by an issue I ran into in my new datasette-load plugin, which resulted in this fix:

• Fixed a bug where replacing a database with a new one with the same name did not pick up the new database correctly. (#2465)

# 6th February 2025, 8:56 pm / projects, annotated-release-notes, datasette

S1: The $6 R1 Competitor? Tim Kellogg shares his notes on a new paper, s1: Simple test-time scaling, which describes an inference-scaling model fine-tuned on top of Qwen2.5-32B-Instruct for just $6 - the cost for 26 minutes on 16 NVIDIA H100 GPUs.

Tim highlight the most exciting result:

After sifting their dataset of 56K examples down to just the best 1K, they found that the core 1K is all that's needed to achieve o1-preview performance on a 32B model.

The paper describes a technique called "Budget forcing":

To enforce a minimum, we suppress the generation of the end-of-thinking token delimiter and optionally append the string “Wait” to the model’s current reasoning trace to encourage the model to reflect on its current generation

That's the same trick Theia Vogel described a few weeks ago.

Here's the s1-32B model on Hugging Face. I found a GGUF version of it at brittlewis12/s1-32B-GGUF, which I ran using Ollama like so:

ollama run hf.co/brittlewis12/s1-32B-GGUF:Q4_0

I also found those 1,000 samples on Hugging Face in the simplescaling/s1K data repository there.

I used DuckDB to convert the parquet file to CSV (and turn one VARCHAR[] column into JSON):

COPY (
    SELECT 
      solution,
      question,
      cot_type,
      source_type,
      metadata,
      cot,
      json_array(thinking_trajectories) as thinking_trajectories,
      attempt
    FROM 's1k-00001.parquet'
) TO 'output.csv' (HEADER, DELIMITER ',');

Then I loaded that CSV into sqlite-utils so I could use the convert command to turn a Python data structure into JSON using json.dumps() and eval():

# Load into SQLite
sqlite-utils insert s1k.db s1k output.csv --csv
# Fix that column
sqlite-utils convert s1k.db s1u metadata 'json.dumps(eval(value))' --import json
# Dump that back out to CSV
sqlite-utils rows s1k.db s1k --csv > s1k.csv

Here's that CSV in a Gist, which means I can load it into Datasette Lite.

It really is a tiny amount of training data. It's mostly math and science, but there are also 15 cryptic crossword examples.

# 5th February 2025, 8 pm / duckdb, datasette-lite, llm-reasoning, ai, ollama, llms, datasette, generative-ai, qwen, local-llms, ai-in-china, parquet

o3-mini is really good at writing internal documentation. I wanted to refresh my knowledge of how the Datasette permissions system works today. I already have extensive hand-written documentation for that, but I thought it would be interesting to see if I could derive any insights from running an LLM against the codebase.

o3-mini has an input limit of 200,000 tokens. I used LLM and my files-to-prompt tool to generate the documentation like this:

cd /tmp
git clone https://github.com/simonw/datasette
cd datasette
files-to-prompt datasette -e py -c | \
  llm -m o3-mini -s \
  'write extensive documentation for how the permissions system works, as markdown'

The files-to-prompt command is fed the datasette subdirectory, which contains just the source code for the application - omitting tests (in tests/) and documentation (in docs/).

The -e py option causes it to only include files with a .py extension - skipping all of the HTML and JavaScript files in that hierarchy.

The -c option causes it to output Claude's XML-ish format - a format that works great with other LLMs too.

You can see the output of that command in this Gist.

Then I pipe that result into LLM, requesting the o3-mini OpenAI model and passing the following system prompt:

write extensive documentation for how the permissions system works, as markdown

Specifically requesting Markdown is important.

The prompt used 99,348 input tokens and produced 3,118 output tokens (320 of those were invisible reasoning tokens). That's a cost of 12.3 cents.

Honestly, the results are fantastic. I had to double-check that I hadn't accidentally fed in the documentation by mistake.

(It's possible that the model is picking up additional information about Datasette in its training set, but I've seen similar high quality results from other, newer libraries so I don't think that's a significant factor.)

In this case I already had extensive written documentation of my own, but this was still a useful refresher to help confirm that the code matched my mental model of how everything works.

Documentation of project internals as a category is notorious for going out of date. Having tricks like this to derive usable how-it-works documentation from existing codebases in just a few seconds and at a cost of a few cents is wildly valuable.

# 5th February 2025, 6:07 am / llm, openai, o3, ai, llms, datasette, generative-ai, documentation, ai-assisted-programming, llm-reasoning, files-to-prompt

Datasette Public Office Hours 31st Jan at 2pm Pacific. We're running another Datasette Public Office Hours session on Friday 31st January at 2pm Pacific (more timezones here). We'll be featuring demos from the community again - take a look at the videos of the six demos from our last session for an idea of what to expect.

If you have something you would like to show, please drop us a line! We still have room for a few more demos.

# 30th January 2025, 9:45 pm / discord, datasette, community, datasette-public-office-hours

Datasette Public Office Hours Application. We are running another Datasette Public Office Hours event on Discord tomorrow (Friday 17th January 2025) at 2pm Pacific / 5pm Eastern / 10pm GMT / more timezones here.

The theme this time around is lightning talks - we're looking for 5-8 minute long talks from community members about projects they are working on or things they have built using the Datasette family of tools (which includes LLM and sqlite-utils as well).

If you have a demo you'd like to share, please let us know via this form.

I'm going to be demonstrating my recent work on the next generation of Datasette Enrichments.

# 16th January 2025, 6:38 pm / lightning-talks, enrichments, discord, datasette, datasette-public-office-hours

datasette-enrichments-llm. Today's new alpha release is datasette-enrichments-llm, a plugin for Datasette 1.0a+ that provides an enrichment that lets you run prompts against data from one or more column and store the result in another column.

So far it's a light re-implementation of the existing datasette-enrichments-gpt plugin, now using the new llm.get_async_models() method to allow users to select any async-enabled model that has been registered by a plugin - so currently any of the models from OpenAI, Anthropic, Gemini or Mistral via their respective plugins.

Still plenty to do on this one. Next step is to integrate it with datasette-llm-usage and use it to drive a design-complete stable version of that.

# 5th December 2024, 11:46 pm / llm, plugins, ai, llms, enrichments, releases, datasette, generative-ai, projects

datasette-queries. I released the first alpha of a new plugin to replace the crusty old datasette-saved-queries. This one adds a new UI element to the top of the query results page with an expandable form for saving the query as a new canned query:

It's my first plugin to depend on LLM and datasette-llm-usage - it uses GPT-4o mini to power an optional "Suggest title and description" button, labeled with the becoming-standard ✨ sparkles emoji to indicate an LLM-powered feature.

I intend to expand this to work across multiple models as I continue to iterate on llm-datasette-usage to better support those kinds of patterns.

For the moment though each suggested title and description call costs about 250 input tokens and 50 output tokens, which against GPT-4o mini adds up to 0.0067 cents.

# 3rd December 2024, 11:59 pm / projects, releases, datasette, plugins, llm, generative-ai, openai, ai, llms

datasette-llm-usage. I released the first alpha of a Datasette plugin to help track LLM usage by other plugins, with the goal of supporting token allowances - both for things like free public apps that stop working after a daily allowance, plus free previews of AI features for paid-account-based projects such as Datasette Cloud.

It's using the usage features I added in LLM 0.19.

The alpha doesn't do much yet - it will start getting interesting once I upgrade other plugins to depend on it.

Design notes so far in issue #1.

# 2nd December 2024, 9:33 pm / llm, datasette-cloud, plugins, ai, llms, datasette, generative-ai, projects, releases