taocao

AudioNotes

快速提取音视频内容，整理成一份结构化的markdown笔记

byaldi

Use late-interaction multi-modal models such as ColPali in just a few lines of code.

Deep-Live-Cam

real time face swap and one-click video deepfake with only a single image (uncensored)

EchoMimic

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

GraphRAG-Ollama-UI

GraphRAG using Ollama with Gradio UI and Extra Features

Linly-Dubbing

智能视频多语言AI配音/翻译工具 - Linly-Dubbing — “AI赋能，语言无界”

LivePortrait

Bring portraits to life!

llamatutor

An AI personal tutor built with Llama 3.1

llm-math-education

Retrieval augmented generation for middle-school math question answering and hint generation.

MaxKB

🚀 基于 LLM 大语言模型的知识库问答系统。开箱即用、模型中立、灵活编排，支持快速嵌入到第三方业务系统。

Open-LLM-VTuber

Talk to any LLM with fast hands-free voice interaction, Live2D taking face, and long-term memory running locally across platforms

OpenVoice

Instant voice cloning by MIT and MyShell.

paper-qa

High accuracy RAG for answering questions from scientific documents with citations

RAGLAB

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation

system-2-research

System 2 Reasoning Link Collection

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

textbooks

Source code of Mathigon's interactive textbooks

whisper-medusa

Whisper with Medusa heads

wiseflow

Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and uploads them to the database.

x-ai-content-filter-groq

Filter X content using LLM API requests, configurable, based on Groq API

azure-search-static-web-app

Code sample demonstrates how to create an Azure Static Web app for searching on Azure AI Search.

Build-your-own-copilot-Solution-Accelerator

Solution Accelerator to show how to build your own copilot

crawl4ai

🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper

CyberScraper-2077

A Powerful web scraper powered by LLM | Open-AI & Ollama

docai

Structured information extraction from documents

PDF2Audio

Qwen2-Audio

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Qwen2-VL

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

vizier

Python-based research interface for blackbox and hyperparameter optimization, based on the internal Google Vizier Service.

winter2022

Website