Generative Images with Gemini (New Updates)

Back in January of this year, I wrote up my experience testing out Google’s Imagen 3 APIs to generate dynamic images. A few days ago, Google updated their support with new experimental support in Flash. I’ve been playing with this the last few days and have some code and samples to share with you, but before that, what exactly changed? Gemini and Imagen 3 There are now two different models, and different APIs, to generate images with Google’s AI platform. The new one is Gemini 2.0 Flash Experimental and the previous one (the one covered in my blog post) is Imagen 3. Of course the next question is, why two, and what do you pick? The docs do a great job of explaining the differences,... more →
Posted in: JavaScript

BoxLang Quick Tips – Database Access

Today I’m kicking off a new blog/video series of quick tips for people interested in BoxLang. These ‘quick tips’ are just that, a look at how BoxLang can simplify working with the JVM and building CLI scripts, web apps, and serverless applications. Each of these posts will include a video along with sample code and help highlight some of the ways BoxLang can be powerful in just a few lines of code. For my first quick tip, let’s talk database access, which by the way was one of the reasons I got into ColdFusion nearly thirty years ago (I didn’t want to figure out how to do it in Perl!). Working with databases in BoxLang can be done in a few steps. Step One –... more →
Posted in: JavaScript

Automating and Responding to Sentiment Analysis with Diffbot’s Knowledge Graph

Diffbot’s Knowledge Graph has a simple purpose – bring the sum total of all knowledge to your fingertips via a search that emphasis data and relations over a simple text based search engine experience. Sourced by the entire web, Knowledge Graph lets you perform complex queries against billions of data points instantly via a simple API. I decided to take a spin with their API and build a "relatively" simple tool – news analysis for a product run in on automated platform. Should be easy, right? Let’s get to it. Note that the examples in this blog post assume you’ve gotten a free key from Diffbot. Be sure to do that before trying the samples. Designing the... more →
Posted in: JavaScript

Links For You (3/8/25)

Happy afternoon, programs. I just got back one of my kid’s soccer games (unlike last season, the weather is pleasant and not scorching hot) and I’ve got a Saturday now that is 100% open! Which means I’ll get a lot done! (Or, more likely, play video games.) So that I can more quickly get to all the important chores and cleaning I’m not going to do, let’s get to the links. Code Listings via API First up is a two-fer kinda. Showcode is an excellent web app to create screenshots from code. It supports numerous languages, numerous display options, and so forth, and creates really good output. As an example: While it’s a great webapp, they also have a cool API... more →
Posted in: JavaScript

Code Break this Thursday – Ray Finally Learns React

Ok, so if you attended my last Code Break session you know I was hinting that I was really excited for my next one. For years now I’ve wanted to give React a fair shake and actually try to build something with it. Finally I’m making time to do so. This Thursday at 12PM CST, my next session will be: I Don’t like React. Let’s Learn React! To be clear, it isn’t that I dislike React, it’s just that every time I’ve looked at the code, it just didn’t gel with me. I know it’s incredibly popular, but I always felt like if I needed to build a proper "web app", I’d just use Vue (despite my feelings about Vue 3, feel free to ask me in... more →
Posted in: JavaScript

Parsing Uploaded Resumes into Form Fields with Google Gemini

As I’ve recently become somewhat familiar with job application sites (sigh, thanks Adobe), I’ve noticed an interesting feature some sites use. After selecting your resume to upload, they will parse the resume and either offer to, or automatically, fill in some of the form fields of the application for you. I thought it would be interesting to try this myself making use of Google’s Gemini APIs. Here’s what I discovered. The Test Script As always, I began with a script that would take a hard-coded resume and attempt to parse it. For the most part, this is basic "upload a file and ask the AI to talk about", but in my case, I wanted a very particular set of data... more →
Posted in: JavaScript

Quick Demo of Chrome’s Summarization GenAI (Upcoming) API

I’ve blogged a few times recently about Google’s AI on Chrome initiative to bring AI features to the browser itself. Yesterday, my Code Break episode was specifically on this topic: Play Video In that session, I talk specifically about the Summarizer API, which does… wait for it… summarization. (It also covers the Writer and Rewriter API which I covered… woah, way back in September of last year: "Using Chrome AI to Rewrite Text") One interesting aspect of the API is that it offers multiple types of summarization: key points (the default) tl;dr teaser headline You can also request three different lengths: short medium (default) long According... more →
Posted in: JavaScript

Using AI in the Browser for Typo Rewriting

Last week I gave a presentation on Chrome’s new built-in AI support (I’ll link the video at the end) and it’s gotten me inspired to consider new and different ways these APIs can be used to enhance the user experience. These APIs still aren’t quite ready for production use, and it’s absolutely possible we may never see these in Safari or Firefox, but the possibility of using them to enhance an application where available is exciting. For today, I want to share an interesting use case that occurred to me a few weeks ago. One of the APIs being built is a translation API (along with a language detection) API as well. In general the idea here is to go from one language... more →
Posted in: JavaScript
1 4 5 6 7 8 97