440 items tagged “projects”
Posts about projects I have worked on.
2023
I built a ChatGPT plugin to answer questions about data hosted in Datasette
Yesterday OpenAI announced support for ChatGPT plugins. It’s now possible to teach ChatGPT how to make calls out to external APIs and use the responses to help generate further answers in the current conversation.
[... 1,801 words]Weeknotes: AI won’t slow down, a new newsletter and a huge Datasette refactor
I’m a few weeks behind on my weeknotes, but it’s not through lack of attention to my blog. AI just keeps getting weirder and more interesting.
[... 1,255 words]A simple Python implementation of the ReAct pattern for LLMs. I implemented the ReAct pattern (for Reason+Act) described in this paper. It's a pattern where you implement additional actions that an LLM can take - searching Wikipedia or running calculations for example - and then teach it how to request that those actions are run, then feed their results back into the LLM.
apple-notes-to-sqlite (via) With the help of ChatGPT I finally figured out just enough AppleScript to automate the export of my notes to a SQLite database. AppleScript is a notoriously read-only language, which is turns out makes it a killer app for LLM-assisted coding.
Weeknotes: A bunch of things I learned this week, plus datasette-explain
The Datasette table view refactor, JSON redesign and ?_extra= continues this week, mainly in this ongoing pull request and this tracking issue.
datasette-scraper, Big Local News and other weeknotes
In addition to exploring the new MusicCaps training and evaluation data I’ve been working on the big Datasette JSON refactor, and getting excited about a Datasette project that I didn’t work on at all.
[... 1,744 words]Examples of sites built using Datasette (via) I gave the examples page on the Datasette website a significant upgrade today: it now includes screenshots (taken using shot-scraper) of six projects chosen to illustrate the variety of problems Datasette can be used to tackle.
Exploring MusicCaps, the evaluation data released to accompany Google’s MusicLM text-to-music model
Google Research just released MusicLM: Generating Music From Text. It’s a new generative AI model that takes a descriptive prompt and produces a “high-fidelity” music track. Here’s the paper (and a more readable version using arXiv Vanity).
[... 1,323 words]How to implement Q&A against your documentation with GPT3, embeddings and Datasette
If you’ve spent any time with GPT-3 or ChatGPT, you’ve likely thought about how useful it would be if you could point them at a specific, current collection of text or documentation and have it use that as part of its input for answering questions.
[... 3,491 words]2022
2022 in projects and blogging
In lieu of my regular weeknotes (I took two weeks off for the holidays) here’s a look back at 2022, mainly in terms of projects and things I’ve written about.
Datasette 1.0a2: Upserts and finely grained permissions
I’ve released the third alpha of Datasette 1.0. The 1.0a2 release introduces upsert support to the new JSON API and makes some major improvements to the Datasette permissions system.
[... 2,844 words]Over-engineering Secret Santa with Python cryptography and Datasette
We’re doing a family Secret Santa this year, and we needed a way to randomly assign people to each other without anyone knowing who was assigned to who.
[... 2,044 words]AI assisted learning: Learning Rust with ChatGPT, Copilot and Advent of Code
I’m using this year’s Advent of Code to learn Rust—with the assistance of GitHub Copilot and OpenAI’s new ChatGPT.
[... 2,661 words]Datasette’s new JSON write API: The first alpha of Datasette 1.0
This week I published the first alpha release of Datasette 1.0, with a significant new feature: Datasette core now includes a JSON API for creating and dropping tables and inserting, updating and deleting data.
[... 2,817 words]Tracking Mastodon user numbers over time with a bucket of tricks
Mastodon is definitely having a moment. User growth is skyrocketing as more and more people migrate over from Twitter.
[... 1,534 words]Datasette Lite: Loading JSON data (via) I added a new feature to Datasette Lite: you can now pass it the URL to a JSON file (hosted on a CORS-compatible hosting provider such as GitHub or GitHub Gists) and it will load that file into a database table for you. It expects an array of objects, but if your file has an object as the root it will search through it looking for the first key that is an array of objects and load those instead.
Datasette is 5 today: a call for birthday presents
Five years ago today I published the first release of Datasette, in Datasette: instantly create and publish an API for your SQLite databases.
[... 548 words]Designing a write API for Datasette
Building out Datasette Cloud has made one thing clear to me: Datasette needs a write API for ingesting new data into its attached SQLite databases.
[... 1,493 words]Datasette 0.63: The annotated release notes
I released Datasette 0.63 today. These are the annotated release notes.
[... 1,531 words]Weeknotes: DjangoCon, SQLite in Django, datasette-gunicorn
I spent most of this week at DjangoCon in San Diego—my first outside-of-the-Bay-Area conference since the before-times.
[... 1,184 words]Measuring traffic during the Half Moon Bay Pumpkin Festival
This weekend was the 50th annual Half Moon Bay Pumpkin Festival.
[... 2,693 words]Half Moon Bay Pumpkin Festival traffic on Saturday 15th October 2022 (via) It’s the Half Moon Bay Pumpkin Festival this weekend... and its impact on the traffic between our little town of El Granada and Half Moon Bay—8 minutes drive away—is notorious. So I built a git scraper that archives estimated driving times from the Google Maps Navigation API, and used git-history to turn that scraped data into a SQLite database and visualize it on a chart.
shot-scraper 1.0 (via) Only a minor release in terms of features, but I decided that I’m comfortable enough with the CLI design at this point that I’m ready to stamp a 1.0 on it and commit to not making backwards-incompatible changes (at least without shipping a 2.0 release, which I’d like to avoid if possible).
Weeknotes: Publishing data using Datasette Cloud
My initial preview releases of Datasette Cloud (the SaaS version of my Datasette open source project) have focused on private data collaboration.
[... 582 words]Weeknotes: Datasette Cloud preview invitations
This week I finally started sending out invitations for people to try out the preview of the new Datasette Cloud, my SaaS offering for Datasette.
[... 713 words]A tool to run caption extraction against online videos using Whisper and GitHub Issues/Actions
I released a new project this weekend, built during the Bellingcat Hackathon (I came second!) It’s called Action Transcription and it’s a tool for caturing captions and transcripts from online videos.
[... 1,362 words]Exploring 10m scraped Shutterstock videos used to train Meta’s Make-A-Video text-to-video model
Make-A-Video is a new “state-of-the-art AI system that generates videos from text” from Meta AI. It looks incredible—it really is DALL-E / Stable Diffusion for video. And it appears to have been trained on 10m video preview clips scraped from Shutterstock.
[... 923 words]Weeknotes: Datasette Lite, s3-credentials, shot-scraper, datasette-edit-templates and more
Despite distractions from AI I managed to make progress on a bunch of different projects this week, including new releases of s3-credentials and shot-scraper, a new datasette-edit-templates plugin and a small but neat improvement to Datasette Lite.
[... 1,562 words]Open every CSV file in a GitHub repository in Datasette Lite (via) I built an Observable notebook that accepts a GitHub repository as input, scans it for CSV files and generates a link to open all of those CSV files in Datasette Lite.
Building a searchable archive for the San Francisco Microscopical Society
The San Francisco Microscopical Society was founded in 1870 by a group of scientists dedicated to advancing the field of microscopy.
[... 1,845 words]