Stars
基于智能体 RAG 知识库的知识图谱问答系统。Langgraph + VueJS + Flask + Neo4j。大模型适配 OpenAI、Ollama、vLLM、国内主流大模型平台的模型调用。支持推理模型DeepSeek-R1、联网检索、工具调用。
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and …
InspireFace is a cross-platform face recognition SDK developed in C/C++, supporting multiple operating systems and various backend types for inference, such as CPU, GPU, and NPU.
A comprehensive list of awesome document image rectification papers.
Real time interactive streaming digital human
Toolkit for linearizing PDFs for LLM datasets/training
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…
Vite & Vue powered static site generator.
LangChat: Java LLMs/AI Project, Supports Multi AI Providers( Gitee AI/ 智谱清言 / 阿里通义 / 百度千帆 / DeepSeek / 抖音豆包 / 零一万物 / 讯飞星火 / OpenAI / Gemini / Ollama / Azure / Claude 等大模型), Java生态下AI大模型产品解决方案，快速构建企…
OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. Core Capabilities: 1) domain model constr…
Official implementation of the affective mobile sensing system called FacePsy proposed in the article "FacePsy: An Open-Source Affective Mobile Sensing System - Analyzing Facial Behavior and Head G…
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
An open-source RAG-based tool for chatting with your documents.
Question and Answer based on Anything.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
史上最大规模1.4亿知识图谱数据免费下载，知识图谱，通用知识图谱，融合了两千五百多万的实体，拥有亿级别的实体属性关系。
AngularJS Bootstrap Admin Panel Framework