How streaming LLM APIs work
I decided to have a poke around and see if I could figure out how the HTTP streaming APIs from the various hosted LLM providers actually worked. He...
1210 words
|
6 minutes
A simple Python implementation of the ReAct pattern for LLMs
A popular nightmare scenario for AI is giving it access to tools, so it can make API calls and execute its own code and generally break free of the...
1111 words
|
6 minutes
Using llama-cpp-python grammars to generate JSON
[llama.cpp](https://github.com/ggerganov/llama.cpp) recently added the ability to control the output of any model using a grammar.
851 words
|
4 minutes
Piping from rg to llm to answer questions about code
Here's a trick I've used a couple of times in the past few days.
1105 words
|
6 minutes
Display EC2 instance costs per month
The [EC2 pricing page](https://aws.amazon.com/ec2/pricing/on-demand/) shows cost per hour, which is pretty much useless. I want cost per month. The...
69 words
|
1 minute
eBPF-Based ADR: Real-time Application Defense
Comprehensive guide to implementing Application Detection and Response (ADR) using eBPF for real-time threat detection and prevention in modern web applications.
5316 words
|
27 minutes
How to scp files to and from Fly
I have a Fly instance with a 20GB volume, and I wanted to copy files to and from the instance from my computer using `scp`.
256 words
|
1 minute
How to deploy a folder with a Dockerfile to Cloud Run
I deployed https://metmusem.datasettes.com/ by creating a folder on my computer containing a Dockerfile and then shipping that folder up to Google ...
319 words
|
2 minutes
Using heroku pg:pull to restore a backup to a macOS laptop
Today I worked out how to use the Heroku `pg:pull` command and [Postgres.app](https://postgresapp.com/) to pull a Heroku backup to my laptop.
248 words
|
1 minute
Storing files in an S3 bucket between GitHub Actions runs
For my [git-history live demos](https://github.com/simonw/git-history/issues/30) I needed to store quite large files (~200MB SQLite databases) in b...
323 words
|
2 minutes
Using Prettier to check JavaScript code style in GitHub Actions
I [decided](https://github.com/simonw/datasette/issues/1166) to adopt [Prettier](https://prettier.io/) as the JavaScript code style for Datasette, ...
235 words
|
1 minute
Using build-arg variables with Cloud Run deployments
For [datasette/issues/1522](https://github.com/simonw/datasette/issues/1522) I wanted to use a Docker build argument in a `Dockerfile` that would t...
295 words
|
1 minute
Whisky sour
I picked up the recipe for this one from [this video](https://www.tiktok.com/t/ZTRaxyxQP/) by [@notjustabartender](https://www.tiktok.com/@notjusta...
325 words
|
2 minutes
Upgrading a Heroku PostgreSQL database with pg:copy
Figured this out in https://github.com/simonw/simonwillisonblog/issues/132 - I was running PostgreSQL 9.x and I wanted 11.x in order to use the new...
367 words
|
2 minutes
Only run GitHub Action on push to master / main
Spotted in [this Cloud Run example](https://github.com/GoogleCloudPlatform/github-actions/blob/20c294aabd5331f9f7b8a26e6075d41c31ce5e0d/example-wor...
118 words
|
1 minute
Wildcard DNS and SSL on Fly
[Fly](https://fly.io/) makes it surprisingly easy to configure wildcard DNS, such that `anything.your-new-domain.dev` is served by a single Fly app...
552 words
|
3 minutes
Running OpenAI's large context models using llm
OpenAI [announced new models](https://openai.com/blog/function-calling-and-other-api-updates) today. Of particular interest to me is the new `gpt-3...
560 words
|
3 minutes
Complete Guide to AWS IAM Roles: Secure Access Management
Complete guide to AWS IAM Roles - understanding trust policies, permissions, and common use cases for secure AWS resource access management.
409 words
|
2 minutes
Guessing Amazon image URLs using GitHub Copilot
I was experimenting with the new [Readwise export API](https://readwise.io/api_deets#export) and it gave me back the following JSON:
248 words
|
1 minute
Expanding ChatGPT Code Interpreter with Python packages, Deno and Lua
The ChatGPT Code Interpreter alpha remains incredibly interesting. I wrote about how I was using it [for Python and SQLite benchmarking](https://si...
1221 words
|
6 minutes
Testing against Python 3.11 preview using GitHub Actions
I decided to run my CI tests against the Python 3.11 preview, to avoid the problem I had when Python 3.10 came out with [a bug that affected Datase...
133 words
|
1 minute
Integrating HashiCorp Vault with CoreDNS: Secure DNS and Secrets Management
A comprehensive guide to integrating HashiCorp Vault with CoreDNS for secure DNS resolution, dynamic secrets management, and certificate automation in modern infrastructure.
4366 words
|
22 minutes
Creating a Comprehensive API Inventory: Discovery, Documentation, and Management
A complete guide to building an automated API inventory system that discovers, documents, and manages all APIs across your organization's infrastructure.
4371 words
|
22 minutes
Mastering Container Management with Podman Quadlet: Complete Guide
A comprehensive guide to using Podman Quadlet for container management, enabling systemd-native container deployment with automatic updates, dependencies, and lifecycle management.
1402 words
|
7 minutes