Simon Willison’s Weblog

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 / bash, google, ocr, projects, ai, generative-ai, llms, ai-assisted-programming, llm, gemini, vision-llms, llm-pricing

lsix (via) This is pretty magic: an ls style tool which shows actual thumbnails of every image in the current folder, implemented as a Bash script.

To get this working on macOS I had to update to a more recent Bash (brew install bash) and switch to iTerm2 due to the need for a Sixel compatible terminal.

# 6th June 2024, 10:07 pm / bash

A tiny CI system (via) Christian Ştefănescu shares a recipe for building a tiny self-hosted CI system using Git and Redis. A post-receive hook runs when a commit is pushed to the repo and uses redis-cli to push jobs to a list. Then a separate bash script runs a loop with a blocking “redis-cli blpop jobs” operation which waits for new jobs and then executes the CI job as a shell script.

# 26th April 2022, 3:39 pm / bash, continuous-integration, git, redis

flk: A LISP that runs wherever Bash is (via) This is a heck of a project: an implementation of LISP written entirely in Bash, meaning you can run it as a script on any machine that has a Bash installation.

# 4th December 2019, 5:19 am / bash, lisp

direnv (via) A shell extension (for bash, zsh and others) which can automatically set and unset environment variables when you cd into specific directories. Useful for managing things like a project’s GOPATH or automatically activating Python virtual environments.

# 5th November 2017, 7:59 pm / bash, shell, zsh

Using Bash’s History Effectively. The HISTIGNORE environment variable is particularly useful, allowing you to suppress certain commands by specifying a pattern. This article has a tip for causing a command to be omitted from the history if you prefix it with a space.

# 25th February 2010, 12:21 pm / bash, commandline

shunit2 (via) xUnit style testing for shell scripts.

# 27th September 2009, 7:34 pm / bash, shell, shunit2, testing, unittesting, unix, xunit

BashReduce. Map/Reduce in Bash is no longer a joke project (if it ever was)—Richard Crowley is extending it and using it for analysis at OpenDNS.

# 28th June 2009, 3:03 pm / bash, bashreduce, mapreduce, opendns, richard-crowley

resty. 58 lines of bash provides a better command-line interface to RESTful APIs, using curl under the hood. This should save me from running “man curl” several times a week.

# 18th May 2009, 1:07 pm / apis, bash, commandline, curl, rest, resty