Use OpenAI's realtime API for a chatting with your documents

Vision model based PDF chunking.

A full-featured, hackable Next.js AI chatbot built by Vercel

React app for inspecting, building and debugging with the Realtime API

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

dev log

The latest graphrag interface is used, using the local ollama to provide the LLM interface.Support for using the pip installation

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Querying DNS Resolution Results in Different Regions Worldwide.

Minimalistic web app designed for sending private and secure notes.

A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| 基于 Webgpu 技术和 wasm 技术的免费开源 inpainting & image-upscaling 工具, 纯浏览器端实现。

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Expert Specialized Fine-Tuning

AirLLM 70B inference with single 4GB GPU

Incremental Knowledge Graphs Constructor Using Large Language Models

Model components of the Llama Stack APIs

Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

Converts text input or URL into knowledge graph and displays

The First Multimodal Seach Engine Pipeline and Benchmark for LMMs

The easiest way to use Agentic RAG in any enterprise

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

提升部署在cloudflare、vercel或netlify的网页在中国的访问速度和稳定性 Improve the access speed and stability in China of web pages hosted on cloudflare, vercel or netlify by merely changing your CNAME record. cf优选域名 | cf优…

Zep | The Memory Foundation For Your AI Stack