Text & Image (multimodal) streaming chat with Gemini AI on iOS with SwiftUI
In this post we will see how to perform multimodal (text-and-image) conversations using the `gemini-pro` & `gemini-pro-vision` models.
My corner of the internet to share what I’m working on, what I’m figuring out, and whatever I happen to be obsessed with at the moment.
In this post we will see how to perform multimodal (text-and-image) conversations using the `gemini-pro` & `gemini-pro-vision` models.
In the previous post we saw how we could send some text-only input & get a response from Gemini AI's `gemini-pro` model. This is alright for simple tasks but to have a more conversational dialogue with the AI, this is not sufficient.
So Google released the Gemini SDK for developers just a few days ago and in this post I'm going to show you how you can get started with it in just a few steps and lines of code.
Ever since Rockstar Games released the trailer for GTA VI, there has been much exuberance over the latest installment in the long beloved franchise.
Learn how to edit screenshots of the iOS simulator with device bezels & without the toolbar.
The idea for this view came when I was going through Azam Sharp's video on drawing in SwiftUI using the `Canvas` view. I wondered if one could apply the strokes using the DragGesture to a view, it would somewhat replicate the scratch card effect that is normally seen in modern iOS applications
The idea for this animation was a gif I had seen on the now defunct gfycat website when looking for inspiration for creating a loading view for a personal project I'd been working on.
I decided to get the official logo than simply Googling for an image since you find so many variations online.
In the last post we learnt how you can create a static website using the GitHub Pages feature and apply themes to it using jekyll themes.