Simon Willison’s Weblog

Blogmarks that use markdown. I needed to attach a correction to an older blogmark (my 20-year old name for short-form links with commentary on my blog) today - but the commentary field has always been text, not HTML, so I didn't have a way to add the necessary link.

This motivated me to finally add optional Markdown support for blogmarks to my blog's custom Django CMS. I then went through and added inline code markup to a bunch of different older posts, and built this Django SQL Dashboard to keep track of which posts I had updated. # 25th April 2024, 4:34 am

llm-gpt4all. New release of my LLM plugin which builds on Nomic's excellent gpt4all Python library. I've upgraded to their latest version which adds support for Llama 3 8B Instruct, so after a 4.4GB model download this works:

llm -m Meta-Llama-3-8B-Instruct "say hi in Spanish" # 20th April 2024, 5:58 pm

llm-reka. My new plugin for running LLM prompts against the Reka family of API hosted LLM models: reka-core ($10 per million input), reka-flash (80c per million) and reka-edge (40c per million).

All three of those models are trained from scratch by a team that includes several Google Brain alumni.

Reka Core is their most powerful model, released on Monday 15th April and claiming benchmark scores competitive with GPT-4 and Claude 3 Opus. # 18th April 2024, 3:17 am

Extracting data from unstructured text and images with Datasette and GPT-4 Turbo. Datasette Extract is a new Datasette plugin that uses GPT-4 Turbo (released to general availability today) and GPT-4 Vision to extract structured data from unstructured text and images.

I put together a video demo of the plugin in action today, and posted it to the Datasette Cloud blog along with screenshots and a tutorial describing how to use it. # 9th April 2024, 11:03 pm

datasette-import. A new plugin for importing data into Datasette. This is a replacement for datasette-paste, duplicating and extending its functionality. datasette-paste had grown beyond just dealing with pasted CSV/TSV/JSON data—it handles file uploads as well now—which inspired the new name. # 6th April 2024, 10:40 pm

s3-credentials 0.16. I spent entirely too long this evening trying to figure out why files in my new supposedly public S3 bucket were unavailable to view. It turns out these days you need to set a PublicAccessBlockConfiguration of {"BlockPublicAcls": false, "IgnorePublicAcls": false, "BlockPublicPolicy": false, "RestrictPublicBuckets": false}.

The s3-credentials --create-bucket --public option now does that for you. I also added a s3-credentials debug-bucket name-of-bucket command to help figure out why a bucket isn't working as expected. # 5th April 2024, 5:35 am

llm-command-r. Cohere released Command R Plus today—an open weights (non commercial/research only) 104 billion parameter LLM, a big step up from their previous 35 billion Command R model.

Both models are fine-tuned for both tool use and RAG. The commercial API has features to expose this functionality, including a web-search connector which lets the model run web searches as part of answering the prompt and return documents and citations as part of the JSON response.

I released a new plugin for my LLM command line tool this morning adding support for the Command R models.

In addition to the two models it also adds a custom command for running prompts with web search enabled and listing the referenced documents. # 4th April 2024, 5:38 pm

llm-nomic-api-embed. My new plugin for LLM which adds API access to the Nomic series of embedding models. Nomic models can be run locally too, which makes them a great long-term commitment as there’s no risk of the models being retired in a way that damages the value of your previously calculated embedding vectors. # 31st March 2024, 3:17 pm

textract-cli. This is my other OCR project from yesterday: I built the thinnest possible CLI wrapper around Amazon Textract, out of frustration at how hard that tool is to use on an ad-hoc basis.

It only works with JPEGs and PNGs (not PDFs) up to 5MB in size, reflecting limitations in Textract’s synchronous API: it can handle PDFs amazingly well but you have to upload them to an S3 bucket yet and I decided to keep the scope tight for the first version of this tool.

Assuming you’ve configured AWS credentials already, this is all you need to know:

pipx install textract-cli
textract-cli image.jpeg > output.txt # 30th March 2024, 7:01 pm

Wrap text at specified width. New Observable notebook. I built this with the help of Claude 3 Opus—it’s a text wrapping tool which lets you set the width and also lets you optionally add a four space indent.

The four space indent is handy for posting on forums such as Hacker News that treat a four space indent as a code block. # 28th March 2024, 3:36 am

llm-gemini 0.1a1. I upgraded my llm-gemini plugin to add support for the new Google Gemini Pro 1.5 model, which is beginning to roll out in early access.

The 1.5 model supports 1,048,576 input tokens and generates up to 8,192 output tokens—a big step up from Gemini 1.0 Pro which handled 30,720 and 2,048 respectively.

The big missing feature from my LLM tool at the moment is image input—a fantastic way to take advantage of that huge context window. I have a branch for this which I really need to get into a useful state. # 28th March 2024, 3:32 am

GitHub Public repo history tool (via) I built this Observable Notebook to run queries against the GH Archive (via ClickHouse) to try to answer questions about repository history—in particular, were they ever made public as opposed to private in the past.

It works by combining together PublicEvent event (moments when a private repo was made public) with the most recent PushEvent event for each of a user’s repositories. # 20th March 2024, 9:56 pm

llm-claude-3 0.3. Anthropic released Claude 3 Haiku today, their least expensive model: $0.25/million tokens of input, $1.25/million of output (GPT-3.5 Turbo is $0.50/$1.50). Unlike GPT-3.5 Haiku also supports image inputs.

I just released a minor update to my llm-claude-3 LLM plugin adding support for the new model. # 13th March 2024, 9:18 pm

datasette/studio. I’m trying a new way to make Datasette available for small personal data manipulation projects, using GitHub Codespaces.

This repository is designed to be opened directly in Codespaces—detailed instructions in the README.

When the container starts it installs the datasette-studio family of plugins—including CSV upload, some enrichments and a few other useful feature—then starts the server running and provides a big green button to click to access the server via GitHub’s port forwarding mechanism. # 10th March 2024, 3:03 am

llm-claude-3. I built a new plugin for LLM—my command-line tool and Python library for interacting with Large Language Models—which adds support for the new Claude 3 models from Anthropic. # 4th March 2024, 6:46 pm

Datasette 1.0a12. Another alpha release, this time with a new query_actions() plugin hook, a new design for the table, database and query actions menus, a “does not contain” table filter and a fix for a minor bug with the JavaScript makeColumnActions() plugin mechanism. # 29th February 2024, 11:56 pm

dclient 0.3. dclient is my CLI utility for working with remote Datasette instances—in particular for authenticating with them and then running both read-only SQL queries and inserting data using the new Datasette write JSON API. I just picked up work on the project again after a six month gap—the insert command can now be used to constantly stream data directly to hosted Datasette instances such as Datasette Cloud. # 25th February 2024, 8:06 pm

datasette-studio. I’ve been thinking for a while that it might be interesting to have a version of Datasette that comes bundled with a set of useful plugins, aimed at expanding Datasette’s default functionality to cover things like importing data and editing schemas.

This morning I built the very first experimental preview of what that could look like. Install it using pipx:

pipx install datasette-studio

I recommend pipx because it will ensure datasette-studio gets its own isolated environment, independent of any other Datasette installations you might have.

Now running “datasette-studio” instead of “datasette” will get you the version with the bundled plugins.

The implementation of this is fun—it’s a single pyproject.toml file defining the dependencies and setting up the datasette-studio CLI hook, which is enough to provide the full set of functionality.

Is this a good idea? I don’t know yet, but it’s certainly an interesting initial experiment. # 18th February 2024, 8:38 pm

Datasette 1.0a10. The only changes in this alpha release concern the way Datasette handles database transactions. The database.execute_write_fn() internal method used to leave functions to implement transactions on their own—it now defaults to wrapping them in a transaction unless they opt out with the new transaction=False parameter.

In implementing this I found several places inside Datasette—in particular parts of the JSON write API—which had not been handling transactions correctly. Those are all now fixed. # 18th February 2024, 5:10 am

Datasette 1.0a9. A new Datasette alpha release today. This adds basic alter table support API support, so you can request Datasette modify a table to add new columns needed for JSON objects submitted to the insert, upsert or update APIs.

It also makes some permission changes—fixing a minor bug with upsert permissions, and introducing a new rule where every permission plugin gets consulted for a permission check, with just one refusal vetoing that check. # 16th February 2024, 11:20 pm

shot-scraper 1.4. I decided to add HTTP Basic authentication support to shot-scraper today and found several excellent pull requests waiting to be merged, by Niel Thiart and mhalle.

1.4 adds support for HTTP Basic auth, custom --scale-factor shots, additional --browser-arg arguments and a fix for --interactive mode. # 5th February 2024, 11:11 pm

llm-sentence-transformers 0.2. I added a new --trust-remote-code option when registering an embedding model, which means LLM can now run embeddings through the new Nomic AI nomic-embed-text-v1 model. # 4th February 2024, 7:39 pm

llm-embed-onnx. I wrote a new plugin for LLM that acts as a thin wrapper around onnx_embedding_models by Benjamin Anderson, providing access to seven embedding models that can run on the ONNX model framework.

The actual plugin is around 50 lines of code, which makes for a nice example of how thin a plugin wrapper can be that adds new models to my LLM tool. # 28th January 2024, 10:28 pm

My blog’s year archive pages now have tag clouds (via) Inspired by the tag cloud I used in my recent 2023 AI roundup post, I decided to add a tag cloud to the top of every one of my archive-by-year pages showing what topics I had spent the most time with that year.

I already had old code for this, so I pasted it into GPT-4 along with an example of the output of my JSON endpoint from Django SQL Dashboard and had it do most of the work for me. # 4th January 2024, 9:02 pm

Annotate and explore your data with datasette-comments. New plugin for Datasette and Datasette Cloud: datasette-comments, providing tools for collaborating on data exploration with a team through posting comments on individual rows of data.

Alex Garcia built this for Datasette Cloud but as with almost all of our work there it’s also available as an open source Python package. # 30th November 2023, 9:59 pm

LLM 0.11. I released LLM 0.11 with support for the new gpt-3.5-turbo-instruct completion model from OpenAI.

The most interesting feature of completion models is the option to request “log probabilities” from them, where each token returned is accompanied by up to 5 alternatives that were considered, along with their scores. # 19th September 2023, 3:28 pm

Symbex 1.4. New release of my Symbex tool for finding symbols (functions, methods and classes) in a Python codebase. Symbex can now output matching symbols in JSON, CSV or TSV in addition to plain text.

I designed this feature for compatibility with the new “llm embed-multi” command—so you can now use Symbex to find every Python function in a nested directory and then pipe them to LLM to calculate embeddings for every one of them.

I tried it on my projects directory and embedded over 13,000 functions in just a few minutes! Next step is to figure out what kind of interesting things I can do with all of those embeddings. # 5th September 2023, 5:29 pm

Datasette Cloud and the Datasette 1.0 alphas. I sent out the Datasette Newsletter for the first time in quite a while, with updates on Datasette Cloud, the Datasette 1.0 alphas, a note about the security vulnerability in those alphas and a summary of some of my research into combining LLMs with Datasette. # 22nd August 2023, 7:56 pm

Welcome to Datasette Cloud. We launched the Datasette Cloud blog today! The SaaS hosted version of Datasette is ready to start onboarding more users—this post describes what it can do so far and hints at what’s planned to come next. # 16th August 2023, 1:46 am

llm-mlc (via) My latest plugin for LLM adds support for models that use the MLC Python library—which is the first library I’ve managed to get to run Llama 2 with GPU acceleration on my M2 Mac laptop. # 12th August 2023, 5:33 am