Raymond Camden

Using media in your prompts (what's called 'multimodal') with the Gemini API is fairly simple in small cases. You can encode your input with base64 and pass it along with your prompt. While this works well, it's got limitations that may be quickly hit - most specifically a file size limit of 20 megs. A few months ago, I shared a demo of using your device's camera to detect cat breeds. With today's cameras taking incredibly detailed pictures, I hit that limit right away and had to write some code to resize the image to a smaller size. Luckily, the Gemini API has a better way of handling that, the File API.

development generative ai

I'm currently at Google I/O waiting for the next session to start and decided to take a quick look at the latest Gemini model to be released, Flash 1.5. As the name implies, this is a 'speedier' model built to return responses quicker than other models, with the tradeoff that the results may not be as good. Like most things in life, there's going to be tradeoffs. Gemini's Pro 1.5 model will definitely be slower but will return better results. When and how you choose is... well that's a good question, right? I decided to build a tool so I could play with this myself. The idea is to let me enter a prompt and have it run both Flash and Pro models and see both the result as well as how long it took. Here's what I built, and what I saw in my testing.

development generative ai

Yes, yes, I know it's not the weekend and that's when these posts are supposed to go out, but I was super busy being lazy and didn't even realize it had been two weeks since my last post. It happens. Today I'm (weather permitting) hopping on a plane to attend my first Google I/O and I can't wait to dig more into Gemini at the sessions there. If you're attending, let me know and come say hi!

misc links4you

This will be my third ColdFusion post in the past year. I'm not saying I'm going to continue the trend, but as I find interesting use cases, I'm going to share. Today, that involves the <cfoauth> tag that I recently had a chance to play with.

coldfusion

I don't normally blog about upcoming conference talks, but I'm really excited to announce my first talk on generative AI, specifically Google's Gemini will be in a few weeks at the F/ND Tech Conference. This is a free, online conference covering a wide range of topics. My talk, "Adding Generative AI to your Workflow with Google Gemini", will absolutely be appropriate for beginners (as that's what I am) and hopefully provide a gentle introduction to working with Gen AI. Now, one point of warning - this is a Europe-based event so my talk will be... 5:45 AM on a Saturday morning, but admit it, wouldn't you love to wake up early on a Saturday to hear me talk about AI?

development generative ai

Forgive the samewhat lame title, and this will be a quick little post, but I've recently been using such an incredibly helpful npm module I wanted to share it with others. open by Sindre Sorhus (you must click that link and look at their incredible GitHub profile) is a simple, but powerful utility that... opens things.

javascript nodejs

It's been on my queue to investigate how to use Generative AI in a 'chat' interface versus "one prompt and answer" mode for some time and today I finally got a chance to check it out. I'll share my thoughts below, but once again I want to thank Allen Firstenberg for his help while I worked through some issues. As always, take what I'm sharing as the opinion of a developer still very new to this space. Any mistakes are my fault!

development generative ai