Simon Willison’s Weblog

python-imgcat (via) I was investigating options for displaying images in a terminal window (for multi-modal logging output of LLM) and I found this neat Python library for displaying images using iTerm 2.

It includes a CLI tool, which means you can run it without installation using uvx like this:

uvx imgcat filename.png

# 28th October 2024, 5:13 am / llm, cli, python, uv

llm-whisper-api. I wanted to run an experiment through the OpenAI Whisper API this morning so I knocked up a very quick plugin for LLM that provides the following interface:

llm install llm-whisper-api
llm whisper-api myfile.mp3 > transcript.txt

It uses the API key that you previously configured using the llm keys set openai command. If you haven't configured one you can pass it as --key XXX instead.

It's a tiny plugin: the source code is here.

# 27th October 2024, 6:19 pm / llm, projects, plugins, openai, whisper, ai, speech-to-text

Pelicans on a bicycle. I decided to roll out my own LLM benchmark: how well can different models render an SVG of a pelican riding a bicycle?

I chose that because a) I like pelicans and b) I'm pretty sure there aren't any pelican on a bicycle SVG files floating around (yet) that might have already been sucked into the training data.

My prompt:

Generate an SVG of a pelican riding a bicycle

I've run it through 16 models so far - from OpenAI, Anthropic, Google Gemini and Meta (Llama running on Cerebras), all using my LLM CLI utility. Here's my (Claude assisted) Bash script: generate-svgs.sh

Here's Claude 3.5 Sonnet (2024-06-20) and Claude 3.5 Sonnet (2024-10-22):

Gemini 1.5 Flash 001 and Gemini 1.5 Flash 002:

GPT-4o mini and GPT-4o:

o1-mini and o1-preview:

Cerebras Llama 3.1 70B and Llama 3.1 8B:

And a special mention for Gemini 1.5 Flash 8B:

The rest of them are linked from the README.

# 25th October 2024, 11:56 pm / gemini, anthropic, llama, openai, ai, llms, svg, generative-ai, llm, cerebras, pelican-riding-a-bicycle

llm-cerebras. Cerebras (previously) provides Llama LLMs hosted on custom hardware at ferociously high speeds.

GitHub user irthomasthomas built an LLM plugin that works against their API - which is currently free, albeit with a rate limit of 30 requests per minute for their two models.

llm install llm-cerebras
llm keys set cerebras
# paste key here
llm -m cerebras-llama3.1-70b 'an epic tail of a walrus pirate'

Here's a video showing the speed of that prompt:

The other model is cerebras-llama3.1-8b.

# 25th October 2024, 5:50 am / llm-performance, llm, llms, ai, generative-ai, cerebras

Running prompts against images and PDFs with Google Gemini. New TIL. I've been experimenting with the Google Gemini APIs for running prompts against images and PDFs (in preparation for finally adding multi-modal support to LLM) - here are my notes on how to send images or PDF files to their API using curl and the base64 -i macOS command.

I figured out the curl incantation first and then got Claude to build me a Bash script that I can execute like this:

prompt-gemini 'extract text' example-handwriting.jpg

Playing with this is really fun. The Gemini models charge less than 1/10th of a cent per image, so it's really inexpensive to try them out.

# 23rd October 2024, 6:25 pm / vision-llms, gemini, llm, bash, ai, llms, ai-assisted-programming, google, generative-ai, ocr, projects, llm-pricing

Un Ministral, des Ministraux (via) Two new models from Mistral: Ministral 3B and Ministral 8B - joining Mixtral, Pixtral, Codestral and Mathstral as weird naming variants on the Mistral theme.

These models set a new frontier in knowledge, commonsense, reasoning, function-calling, and efficiency in the sub-10B category, and can be used or tuned to a variety of uses, from orchestrating agentic workflows to creating specialist task workers. Both models support up to 128k context length (currently 32k on vLLM) and Ministral 8B has a special interleaved sliding-window attention pattern for faster and memory-efficient inference.

Mistral's own benchmarks look impressive, but it's hard to get excited about small on-device models with a non-commercial Mistral Research License (for the 8B) and a contact-us-for-pricing Mistral Commercial License (for the 8B and 3B), given the existence of the extremely high quality Llama 3.1 and 3.2 series of models.

These new models are also available through Mistral's la Plateforme API, priced at $0.1/million tokens (input and output) for the 8B and $0.04/million tokens for the 3B.

The latest release of my llm-mistral plugin for LLM adds aliases for the new models. Previously you could access them like this:

llm mistral refresh # To fetch new models
llm -m mistral/ministral-3b-latest "a poem about pelicans at the park"
llm -m mistral/ministral-8b-latest "a poem about a pelican in french"

With the latest plugin version you can do this:

llm install -U llm-mistral
llm -m ministral-8b "a poem about a pelican in french"

# 16th October 2024, 3:40 pm / mistral, llms, ai, generative-ai, llm, llm-release, local-llms

An LLM TDD loop (via) Super neat demo by David Winterbottom, who wrapped my LLM and files-to-prompt tools in a short Bash script that can be fed a file full of Python unit tests and an empty implementation file and will then iterate on that file in a loop until the tests pass.

# 13th October 2024, 7:37 pm / llm, ai-assisted-programming, python, generative-ai, pytest, ai, llms, files-to-prompt, testing

lm.rs: run inference on Language Models locally on the CPU with Rust (via) Impressive new LLM inference implementation in Rust by Samuel Vitorino. I tried it just now on an M2 Mac with 64GB of RAM and got very snappy performance for this Q8 Llama 3.2 1B, with Activity Monitor reporting 980% CPU usage over 13 threads.

Here's how I compiled the library and ran the model:

cd /tmp
git clone https://github.com/samuel-vitorino/lm.rs
cd lm.rs
RUSTFLAGS="-C target-cpu=native" cargo build --release --bin chat
curl -LO 'https://huggingface.co/samuel-vitorino/Llama-3.2-1B-Instruct-Q8_0-LMRS/resolve/main/tokenizer.bin?download=true'
curl -LO 'https://huggingface.co/samuel-vitorino/Llama-3.2-1B-Instruct-Q8_0-LMRS/resolve/main/llama3.2-1b-it-q80.lmrs?download=true'
./target/release/chat --model llama3.2-1b-it-q80.lmrs --show-metrics

That --show-metrics option added this at the end of a response:

Speed: 26.41 tok/s

It looks like the performance is helped by two key dependencies: wide, which provides data types optimized for SIMD operations and rayon for running parallel iterators across multiple cores (used for matrix multiplication).

(I used LLM and files-to-prompt to help figure this out.)

# 11th October 2024, 7:33 pm / llm, rust, ai-assisted-programming, generative-ai, ai, llms, files-to-prompt

If we had $1,000,000…. Jacob Kaplan-Moss gave my favorite talk at DjangoCon this year, imagining what the Django Software Foundation could do if it quadrupled its annual income to $1 million and laying out a realistic path for getting there. Jacob suggests leaning more into large donors than increasing our small donor base:

It’s far easier for me to picture convincing eight or ten or fifteen large companies to make large donations than it is to picture increasing our small donor base tenfold. So I think a major donor strategy is probably the most realistic one for us.

So when I talk about major donors, who am I talking about? I’m talking about four major categories: large corporations, high net worth individuals (very wealthy people), grants from governments (e.g. the Sovereign Tech Fund run out of Germany), and private foundations (e.g. the Chan Zuckerberg Initiative, who’s given grants to the PSF in the past).

Also included: a TIL on Turning a conference talk into an annotated presentation. Jacob used my annotated presentation tool to OCR text from images of keynote slides, extracted a Whisper transcript from the YouTube livestream audio and then cleaned that up a little with LLM and Claude 3.5 Sonnet ("Split the content of this transcript up into paragraphs with logical breaks. Add newlines between each paragraph.") before editing and re-writing it all into the final post.

# 8th October 2024, 7:59 pm / jacob-kaplan-moss, django, dsf, claude-3-5-sonnet, llm, whisper

marimo v0.9.0 with mo.ui.chat. The latest release of the Marimo Python reactive notebook project includes a neat new feature: you can now easily embed a custom chat interface directly inside of your notebook.

Marimo co-founder Myles Scolnick posted this intriguing demo on Twitter, demonstrating a chat interface to my LLM library “in only 3 lines of code”:

import marimo as mo
import llm

model = llm.get_model()
conversation = model.conversation()
mo.ui.chat(lambda messages: conversation.prompt(messages[-1].content))

I tried that out today - here’s the result:

marimo.ui.chat() takes a function which is passed a list of Marimo chat messages (representing the current state of that widget) and returns a string - or other type of renderable object - to add as the next message in the chat. This makes it trivial to hook in any custom chat mechanism you like.

Marimo also ship their own built-in chat handlers for OpenAI, Anthropic and Google Gemini which you can use like this:

mo.ui.chat(
    mo.ai.llm.anthropic(
        "claude-3-5-sonnet-20240620",
        system_message="You are a helpful assistant.",
        api_key="sk-ant-...",
    ),
    show_configuration_controls=True
)

# 5th October 2024, 10:59 pm / llm, marimo, python, llms, ai, generative-ai

Gemini 1.5 Flash-8B is now production ready (via) Gemini 1.5 Flash-8B is "a smaller and faster variant of 1.5 Flash" - and is now released to production, at half the price of the 1.5 Flash model.

It's really, really cheap:

• $0.0375 per 1 million input tokens on prompts <128K
• $0.15 per 1 million output tokens on prompts <128K
• $0.01 per 1 million input tokens on cached prompts <128K

Prices are doubled for prompts longer than 128K.

I believe images are still charged at a flat rate of 258 tokens, which I think means a single non-cached image with Flash should cost 0.00097 cents - a number so tiny I'm doubting if I got the calculation right.

OpenAI's cheapest model remains GPT-4o mini, at $0.15/1M input - though that drops to half of that for reused prompt prefixes thanks to their new prompt caching feature (or by half if you use batches, though those can’t be combined with OpenAI prompt caching. Gemini also offer half-off for batched requests).

Anthropic's cheapest model is still Claude 3 Haiku at $0.25/M, though that drops to $0.03/M for cached tokens (if you configure them correctly).

I've released llm-gemini 0.2 with support for the new model:

llm install -U llm-gemini
llm keys set gemini
# Paste API key here
llm -m gemini-1.5-flash-8b-latest "say hi"

# 3rd October 2024, 8:16 pm / vision-llms, gemini, anthropic, openai, ai, llms, google, generative-ai, llm, llm-pricing, prompt-caching, llm-release

Solving a bug with o1-preview, files-to-prompt and LLM. I added a new feature to DJP this morning: you can now have plugins specify their middleware in terms of how it should be positioned relative to other middleware - inserted directly before or directly after django.middleware.common.CommonMiddleware for example.

At one point I got stuck with a weird test failure, and after ten minutes of head scratching I decided to pipe the entire thing into OpenAI's o1-preview to see if it could spot the problem. I used files-to-prompt to gather the code and LLM to run the prompt:

files-to-prompt **/*.py -c | llm -m o1-preview "
The middleware test is failing showing all of these - why is MiddlewareAfter repeated so many times?

['MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware5', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware2', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware5', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware4', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware5', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware2', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware5', 'MiddlewareAfter', 'Middleware3', 'MiddlewareAfter', 'Middleware', 'MiddlewareBefore']"

The model whirled away for a few seconds and spat out an explanation of the problem - one of my middleware classes was accidentally calling self.get_response(request) in two different places.

I did enjoy how o1 attempted to reference the relevant Django documentation and then half-repeated, half-hallucinated a quote from it:

This took 2,538 input tokens and 4,354 output tokens - by my calculations at $15/million input and $60/million output that prompt cost just under 30 cents.

# 25th September 2024, 6:41 pm / o1, llm, djp, openai, ai, llms, ai-assisted-programming, generative-ai, llm-reasoning, files-to-prompt

LLM 0.16. New release of LLM adding support for the o1-preview and o1-mini OpenAI models that were released today.

# 12th September 2024, 11:20 pm / llm, projects, generative-ai, openai, ai, llms, o1