In OctoCut, I have to perform a few tasks that are CPU or memory intensive. Instead of performing them on the machine serving web requests, I want to perform them on a different machine. FLAME is perfect for this. (If you're not familiar with FLAME, I highly recommend…
In a LiveView project I'm working on, I had to add a web worker. I was a bit unsure of how to do this, and was worried I'd have to do some esbuild config manipulation, but it turned out to be quite simple. For readers reading…
In a Phoenix Liveview app, I recently had to do some work in an assign_async(export a video). In terms of UI, I wanted to: * show a toast(or flash message) at the beginning indicating the work has started. * show toast once the work is completed, or if it…
The membrane_s3_plugin(as of version 0.1.2) has gotten outdated with changes in membrane_core. Here's an S3 sink implementation that works with the latest Membrane: defmodule Membrane.S3.Sink do @moduledoc """ Element that uploads incoming buffers to an S3 bucket. Pipeline…
Gemini with audio Video Code Mix.install([ {:req, "~> 0.4.14"}, {:kino, "~> 0.12.0"} ]) Form form = Kino.Control.form( [ prompt: Kino.Input.textarea("Prompt"), audio: Kino.Input.audio("Audio", format: :wav) ], submit: "Submit" ) frame = Kino.Frame.new(…
Video Code openai_api_key = System.fetch_env!("LB_OPENAI_API_KEY") form = Kino.Control.form( [ prompt: Kino.Input.textarea("Prompt"), size: Kino.Input.select( "Image size", ["1024x1024", "1792x1024", "1024x1792"] |> Enum.map(&{&1, &1}…
The Instructor Elixir library lets you retrieve structured output from LLMs like the OpenAI GPT models. But I found that having it return structs that are sum types is not that straightforward. Simple Instructor responses For this post, let’s looks at survey questions as an example. You can define…
The Req Elixir library doesn’t support file uploads(as of version 0.4.5). Instead, you need to use multipart to construct the HTTP request before you send it. Here is an example sending an mp3 file to the OpenAI audio transcription API(aka Whisper): def transcribe_audio(file_…