This is just a quick thought experiment really. Yesterday I was working on a demo that made use of Google's Static Map API. I've blogged about this API for probably over a decade now and I rarely see people use it, but it's a lightweight, image only "API" for when you need simple map images without interactivity. Honestly, I see a lot of sites using the full JavaScript maps library when a simpler image would be fine. It's also an excellent way to use maps in presentations or emails as well. It occurred to me that the static map image could be a great way use of print media queries in CSS and I thought I'd build a quick demo to show this.
I am really excited about this post as it's one of the most powerful changes I've seen to Google's Gemini APIs in quite some time. For a while now it's been really easy to perform searches against a document, or a group of documents. You would upload the file (or files), ask your questions, and that was all you needed.
Good morning, programs. I'm sorry for the light posting the last few weeks, but, it's all for a good reason. Last week was my first week at my new job, which means all of my anxiety and fear are gone. Ok, maybe not, but, I'm absolutely delighted to be off the market again. I haven't blogged about the new job yet (or even gotten around to updating LinekdIn), but I'll do so soon. (My job isn't top secret or anything, I'm just waiting a bit.) Ok, let's get to the links!
Earlier this week I mentioned I'm looking at my previous server-based generative AI demos and seeing which could possibly make sense using on-device AI with Chrome's AI support. I remembered a demo from last year where I tested spam detection using Google Gemini. That demo had worked out rather well and so I thought I'd try it out in Chrome. (Note the update towards the bottom!)
I've blogged about PDF support in BoxLang previously, including a quick introduction and a more robust demo later. Basically, the free PDF module provides excellent PDF creation capabilities out of the box. But what about PDF manipulation?
As I explore Chrome's on-device AI initiatives, one of the things I'm doing is looking at some of my older demos (kinda funny to think of 'old' GenAI demos) and seeing which may make sense in the browser versus API calls. Last July, I investigated creating a template language parser with Google Gemini. The idea was - take a string with tokens that defined a type of word and have Gemini replace it. So for example:
Want to read everything? Head over to my giant list of every single freaking post ever!.
