Starred repositories
Tongyi Deep Research, the Leading Open-source Deep Research Agent
UltraRAG v2: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it.
《Agentic Design Patterns》中文翻译版
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
"RAG-Anything: All-in-One RAG Framework"
医学中文RAG项目，使用langchain+milvus，支持快速一键式部署，支持无缝领域迁移
Add vLLM provider plugin for LangExtract
Generic rag framework to apply the power of LLMs on any given dataset
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…
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
I used open-mmlab/mmdetection3d to train the 3D object detection model, PartA2 on a custom LiDAR dataset. Since it is very challenging to adapt the existing code to fit your custom data, I am shari…
基于FunASR官方Demo修改的WS服务端，配合FastAPI提供HTTP服务，可以在浏览器中进行实时ASR测试
Live2D + ASR + LLM + TTS → Real-time communication + Offline Deployment/Cloud Inference 实时沟通 本地部署/云端推理
实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.
百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
Lightning-responsive CosyVoice2 streaming API based on FastAPI.
This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three …
基于SenseVoice的funasr版本进行的api发布，可以无缝对接oneapi
Multilingual Voice Understanding Model