Empowering RAG with a memory-based data interface for all-purpose applications!

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Vocabulary list of GPT-4o (o200k_base) and GPT-4/GPT-3.5 (cl100k_base) tokenizers. Special tokens are excluded.

o1-engineer is a command-line tool designed to assist developers in managing and interacting with their projects efficiently. Leveraging the power of OpenAI's API, this tool provides functionalitie…

24/7 local AI screen & mic recording. Build AI apps that have the full context. Works with Ollama. Alternative to Rewind.ai. Open. Secure. You own your data. Rust.

Curate better data for LLMs

Resource list for generating JSON using LLMs via function calling, tools, CFG. Libraries, Models, Notebooks, etc.

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

Split text into semantic chunks, up to a desired chunk size. Supports calculating length by characters and tokens, and is callable from Rust and Python.

Things you can do with the token embeddings of an LLM

Easily embed, cluster and semantically label text datasets

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

OpenLIT: Complete Observability and Evals for the Entire GenAI Stack, from LLMs to GPUs. Improve your LLM apps from playground to production 📈. Supports 20+ monitoring integrations like OpenAI & La…

A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).

Anthropic's educational courses

Chat with any codebase with 2 commands

📘 Automatic documentation from sources, for MkDocs.

PyTorch native quantization and sparsity for training and inference

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

Model components of the Llama Stack APIs

Making the community's best AI chat models available to everyone.

🦙 Ollama Telegram bot, with advanced configuration

A system for agentic LLM-powered data processing

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

The First Multimodal Seach Engine Pipeline and Benchmark for LMMs

Trio – a friendly Python library for async concurrency and I/O

Machine Learning Course, Sharif University of Technology

Model2Vec: Distill a Small Fast Model from any Sentence Transformer