Interrogate Your PDFs with Chrome AI / / No Comments Yesterday I blogged about using PDF.js and Chrome’s on-device AI to create summaries of PDF documents, all within the browser, for free. In that post I mentioned it would be possible to build a Q and A system so users could ask questions about the document, and like a dog with a bone, I couldn’t let it go. Last I built not one, but two demos of this. Check it out. Version One Before I begin, note that this version makes use of the Prompt API, which is still behind a flag in Chrome. For this demo to work for you, you would need the latest Chrome and the right flags enabled. The Prompt API is available in extensions without the flag and it wouldn’t surprise me if this requirement... more → Posted in: JavaScript Tagged with: Chrome, Interrogate, PDFs
Meet Language Explorer: Google’s New Open-Source Linguistic Atlas / / No Comments Google Research’s Language Explorer, is a new interactive map that anyone can use to explore the world’s languages.Mapping the World’s TonguesThe interface of the Language Explorer is built around a highly responsive interactive map. Users can dive into the data in several ways:Spatial Discovery: You can use the map to zoom into a specific region – like the Highlands of Papua New Guinea or the Maps Mania… more → Posted in: Interactive Maps Tagged with: atlas, Explorer, Google's, Language, Linguistic, meet, opensource
Summarizing PDFs with On-Device AI / / No Comments You can take the man out of the PDFs, but you can’t take the PDFs out of the man. Ok, I’m not sure that exactly makes sense, but with a couple years in me of working with PDFs, I find myself using them quite often with my AI demos. For today, I’m going to demonstrate something that’s been on my mind in a while – doing summarizing of PDFs completely in the browser, with Chrome’s on-device AI. Unlike the Prompt API, summarization has been released since Chrome 138, so most likely those of you on Chrome can run these demos without problem. (You can see more about the AI API statuses if you’re curious.) Getting PDF Text – Client-Side There’s plenty... more → Posted in: JavaScript Tagged with: OnDevice, PDFs, Summarizing
Subways Built by Slime Mold / / No Comments Subway Sim: Watching a City Think In 2010, researchers in Tokyo ran a slime mold experiment on a map of the city.They placed oat flakes on a map of the Greater Tokyo Area, positioning each flake over a metropolitan center. Then they released a slime mould – Physarum polycephalum – at the location of Tokyo itself.Slime moulds are single-celled organisms with no brain, no nervous system, Maps Mania… more → Posted in: Interactive Maps Tagged with: Built, Mold, Slime, Subways
How Big is Big? / / No Comments META is building a massive (AI)-focused data centre in northeast Louisiana. The site footprint is 2,250 acres of land – making the Hyperion Data Center one of the largest data-center construction sites ever attempted in the United States. It is a nearly five-mile-long, one-mile-wide tract of land that is being developed to power Meta’s AI ambitions.It is hard to understand the true scale of a Maps Mania… more → Posted in: Interactive Maps
Building a UI for Gemini File Stores / / No Comments Back in November of last year I wrote up a blog post talking about a new (at the time) Google Gemini feature, File Stores: "Gemini File Search and File Stores for Easy RAG". In that post I discussed what it was, how it worked, and built up a simple example. You should definitely read that post first, but if you want the TLDR, here ya go: File Stores (referred to as "File Search") expands on Gemini’s previous ability to work on files in a temporary fashion by allowing you to create a permanent "store" of folders. You can use this for RAG systems and use flexible metadata filter for complex queries. This feature has been out for a few months now and I’ve... more → Posted in: JavaScript Tagged with: building, file, Gemini, Stores
Make a Map Poster / / No Comments Ankur Gupta has created an impressive Map Poster Generator. The code for which is available on GitHub.While the original repository is fantastic for developers, it also requires a local Python setup, terminal commands, and the installation of geospatial libraries like OSMnx and GDAL – which can be intimidating if you aren’t a coder.I’ve therefore adapted the core logic into a Google Colab Maps Mania… more → Posted in: Interactive Maps Tagged with: Poster
Using Chrome AI to Rewrite Monstrous JSON / / No Comments Happy Saturday folks, and while this is a topic I’ve covered many times here, I was bored and wanting to write some code, so I whipped up a quick demo. One of my favorite uses of AI is to take abstract data and write a human readable form of it. Now to be clear, this is not something you need AI for. Given that you know the shape of your data, you can create your own summary using hard-coded rules about what values to show, how to present them, and so forth. What I like about the Gen AI use-case for this is the amount of randomness and creativity you get in the responses. In the past I’ve done this with weather forecasts and chart data, but today I thought I’d try something... more → Posted in: JavaScript Tagged with: Chrome, JSON, Monstrous, Rewrite, using