awesome-generative-ai-meets-julia-language

Enhanced AI code assistance by leveraging package documentation (Retrieval Augmented Generation). Comes pre-packaged for common Julia packages, but can be used for any package.

Web-based graphical interface for AIHelpMe.jl built on top of Stipple.jl.

A

Calls ChatGPT to explain any errors in Julia code.

Leverage Large Language Models to uncover, evaluate, and label themes/concepts/spectra in large document collections. (Disclaimer: I'm the author of this package.)

Helps with everyday applications of Large Language Models in Julia by wrapping coming APIs, re-using prompts via templates, and enabling easy transition between different model providers (eg, OpenAI, Ollama). (Disclaimer: I'm the author of this package.)

Great list for all things generative AI. An inspiration for this list!

A hands-on guide on how to build a RAG chatbot over DataFrames.jl documentation using only minimal dependencies.

A tutorial on structured data extraction. A part of a larger series of tutorials on small tasks that can be done with GenAI.

An excellent deep-dive on semantic search (the "R" in RAG). It showcases that with 100 lines of Julia, you can search 15M chunks (~size of Wikipedia) in <20ms.

A brief tutorial on how to use Transformers.jl to access LLMs from HuggingFace Hub.

Pure Julia implementation of Byte Pair Encoding (BPE) algorithm. It's used by Transformers.jl to tokenize text.

Flux is a machine learning library for Julia that is flexible and allows building complex models. However, at the time of writing, I'm not aware of any Large Language Models (LLMs) that have been implemented and trained in Flux.

Llama2.jl provides simple code for inference and training of llama2-based language models based on

Julia interface to llama.cpp, a C/C++ library for running language models locally. Supports a wide range of models.

Great package for loading Pytorch weights into Julia (if you want to implement models yourself).

Transformers.jl is a Julia package that provides a high-level API for using pre-trained transformer models. It also allows to download any models from Hugging Face hub with

Browser automation using the Chrome DevTools Protocol (CDP). Ideal for Computer Use with LLMs. Inspired by Python's Playwright but providing just the essential functionality to get you started with browser automation in Julia.

Fast and local document ranking with models that can run on any computer (CPU-based). Based on Python's

Hackable Llama3.1, Llama3.2 (text), and Qwen 2.5 (eg. base, Qwen2.5-Coder, and Qwen2.5-Math) in Julia.

Summarize GitHub repositories into AI-friendly cheatsheets with a single command.

A minimal and unofficial implementation of Milvus VectorDB client for Julia.

Lightweight Julia wrapper for Microsoft's OmniParser icon detection model with additional utilities for working with screenshots (eg, drawing detections, adding labels).

Free alternative to GitHub Copilot with extensions for most editors.

Great IDE or VSCode plugin for code analysis, suggestion and generation of test suites. Although the tests are written more in the style of Pytest rather than idiomatic Julia. It has a free tier.

A social network, messaging, and LLM interface built in Julia.

Alternative IDE based on VSCode with AI-powered code completion and suggestions. It works really well with Julia language.

Genie UI Assistant is a GPT-4 powered UI builder helping

Excellent inline suggestions with the help of OpenAI models. It works extremely well with Julia language for repetitive tasks one line at a time, but larger code chunks are rarely correct.

ElasticsearchClient.jl

SDK for Google Cloud. There is an

Unofficial wrapper for the Google Gemini API.

A community-maintained Julia wrapper to the OpenAI API.

ElasticsearchClient.jl

SDK for

Useful library to train more traditional generative models like VAEs. It's built on top of Flux.jl.

A desktop app for hosting and interacting with LLMs locally. It's a great option for those who want to use LLMs without coding. It's free for

The best option for those looking to host a Large Language Model locally. Simply start the server and send the requests with

For building interactive data applications in pure Julia (part of Genie.jl ecosystem). Excellent for building web-based interfaces for GenAI applications.

Powerful parser for various types of documents (interop to Java). Very useful for building Retrieval-Augmented Generation (RAG) applications.