2023’s Most Exciting LLM-powered Projects

05 Jan 2024 Coding Digital analytics 795

The world of artificial intelligence is rapidly evolving, and 2023 has seen some of the most innovative and groundbreaking developments in AI technology. This article takes a closer look at the most exciting LLM-powered projects and libraries that are shaping the future of technology.

LangChain

LangChain is revolutionizing the way we interact with language models. This platform provides a comprehensive suite of tools for building and deploying advanced language applications, making it a valuable resource for developers and linguists alike. Discover more at LangChain (Github 73K Stars).

Flowise AI

Flowise AI stands out for its sophisticated approach to AI integration in business processes. This platform is designed to streamline complex workflows, making it a go-to solution for businesses looking to leverage AI for efficiency and growth. Learn more about their innovative approach at Flowise AI (Github 19K Stars).

The discussion below is a great intro into the world of LLM no-code solutions with the creator of LangChain and Flowise AI.

LangChain Low-Code/No-Code Webinar

LangFuse

Open Source Observability & Analytics for LLM Apps – LangFuse is a pioneering platform providing open-source observability and analytics specifically designed for large language model applications. Their focus on transparency and performance makes them a standout in the field. Explore LangFuse at LangFuse (Github 2K Stars)

Open Interpreter

OpenAI’s Code Interpreter in your terminal, running locally – This project brings the power of OpenAI’s code interpreter to your local terminal. It’s an innovative tool for developers seeking to integrate AI coding assistance directly into their workflow. Might not be as powerful as OpenAI’s code interpreter but being able to run it locally with just a an OpenAI API subscription is a huge advantage for me! Check it out on GitHub (36K Stars).

AppAgent

Multimodal Agents as Smartphone Users – AppAgent is a trailblazing LLM-based multimodal agent framework. It’s designed to operate smartphone apps, representing a significant advancement in AI interaction with everyday technology. Learn more about AppAgent on GitHub (2.7K Stars).

Llamafile by Mozilla Ocho

Mozilla Ocho’s Llamafile aims to make large language models more accessible. By simplifying the complexity of LLMs into a single-file executable, they are opening up new possibilities for developers and end-users alike. Dive into Llamafile at Mozilla Ocho (8.1K Stars).

GPT-4V-Act

AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI – This innovative project showcases an AI agent equipped with GPT-4 Vision, capable of interacting with web interfaces just like a human user. More details in Github (670 stars)

LLaVA

LLaVA is not just another AI project; it’s a groundbreaking open-source initiative. As the first end-to-end trained large multimodal model (LMM), LLaVA mimics the capabilities of the multimodal GPT-4, offering extensive chat capabilities and more. Join their journey at LLaVA (12K Stars).
[Project] [Paper] [Github] [Demo] [Data] [Model] [Scaling Note]

GPT-Crawler

Crawl a site to generate knowledge files to create your own custom GPT from a URL – The GPT-Crawler is a game-changer for personalized AI models. This tool allows you to generate custom GPT models from website content, opening up a world of tailored AI experiences. Learn more at Builder.io.

OpenAI API automatic load balancing

Many service providers, including OpenAI, usually set limits on the number of calls that can be made. In the case of Azure OpenAI, there are token limits (TPM or tokens per minute) and limits on the number of requests per minute (RPM). When a server starts running out of resources or the service limits are exhausted, the provider may issue a 429 or TooManyRequests HTTP Status code, and also a Retry-After response header indicating how much time you should wait until you try the next request.

Available on github

Bonus

As a bonus one of the most fun and inspiring LLM-powered projects I saw in 2023 is the David Attenborough life narrator. It’s a small and easy project to replicate, so go on give it a try. You will get the chance to have real-time narration of your life in David Attenborough’s voice!

Looking forward to 2024

These projects and libraries represent the pinnacle of AI development in 2023, each contributing to a future where AI is more integrated, accessible, and influential in our daily lives. Whether you’re a developer, a tech enthusiast, or just curious about the future of AI, these resources offer a glimpse into a world transformed by artificial intelligence.

Newer projects are available in the 2024 collection.

Panagiotis

Written By

Panagiotis (pronounced Panayotis) is a passionate G(r)eek with experience in digital analytics projects and website implementation. Fan of clear and effective processes, automation of tasks and problem-solving technical hacks. Hands-on experience with projects ranging from small to enterprise-level companies, starting from the communication with the customers and ending with the transformation of business requirements to the final deliverable.