Verba is an open-source application designed to offer an end-to-end, streamlined, and user-friendly interface for Retrieval-Augmented Generation (RAG) out of the box. It supports various RAG techniques, data types, LLM providers, and offers Docker support and a fully-customizable frontend.
This is a local LLM chatbot project with RAG for processing PDF input files
Podman AI Lab is an open source extension for Podman Desktop that allows users to work with LLMs on a local environment, featuring a recipe catalog with common AI use cases, a curated set of open source models, and a playground for learning, prototyping, and experimentation. It uses Podman machines to run inference servers for LLM models and supports various formats like GGUF, Pytorch, and Tensorflow.
The Pipe is a multimodal-first tool for feeding files and web pages into vision-language models such as GPT-4V. It is best for LLM and RAG applications that want to support comprehensive textual and visual understanding across a wide range of data sources. The Pipe is available as a 24/7 hosted API at thepi.pe, or it can be set up locally to let you run the compute.
Scrapegraph-ai is a Python library for web scraping using AI. It provides a SmartScraper class that allows users to extract information from websites using a prompt. The library uses LLM models like Ollama, OpenAI, Azure, Gemini, and others for information extraction.
Mistral.rs is a fast LLM inference platform supporting inference on a variety of devices, quantization, and easy-to-use application with an Open-AI API compatible HTTP server and Python bindings. It supports the latest Llama and Phi models, as well as X-LoRA and LoRA support. The project aims to provide the fastest LLM inference platform possible.
Jemma is a GitHub repository that utilizes AI agents to build software from text-based ideas
It takes an idea in text form and assembles a team to create a web-based prototype
- Works best with Claude models, such as claude-3-haiku-20240307
- Project managers, business owners, and engineers work together to create prototypes
- Users can provide feedback to improve the prototypes
This tutorial introduces promptrefiner, a tool created by Amirarsalan Rajabi that uses the GPT-4 model to create perfect system prompts for local LLMs.
This GitHub repository contains a course on Large Language Models (LLMs) with roadmaps and Colab notebooks. The course is divided into three parts: LLM Fundamentals, The LLM Scientist, and The LLM Engineer. Each part covers various topics, including mathematics, Python, neural networks, instruction datasets, pre-training, supervised fine-tuning, reinforcement learning from human feedback, evaluation, quantization, new trends, running LLMs, building a vector storage, retrieval augmented generation, advanced RAG, inference optimization, and deployment.