Stars
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
A programming framework for agentic AI 🤖
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…
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…
PDF解析（文字，章节，表格，图片，参考），基于大模型(ChatGLM2-6B, RWKV)+langchain+streamlit的PDF问答，摘要，信息抽取
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…
A modular graph-based Retrieval-Augmented Generation (RAG) system
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。
A unified, comprehensive and efficient recommendation library
数据挖掘、计算机视觉、自然语言处理、推荐系统竞赛知识、代码、思路
🦜🔗 Build context-aware reasoning applications
rknn-3588部署yolov5，利用线程池实现npu推理加速；Deploying YOLOv5 on RKNN-3588, utilizing a thread pool to achieve NPU inference acceleration.
YMIR, a streamlined model development product.
Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，支持sso登录，多租户，大数据平台对接，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU，边缘计算，serverless，标注平台，自动化标注，数据集管理，大模型微调，vllm大模型推理，llmops，私有知识库，AI模型应用商店，支持模型一键开发/推理/微调，…
Multi-thread tracking of YOLOv5 and ByteTrack implemented by C++, accelerated by TensorRT. YOLOv5 和 ByteTrack 的多线程追踪 C++ 实现, 使用 TensorRT 进行推理加速
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
A simple version of "GPU based parallel optimization for real time panoramic video stitching".
A curated list of radar datasets, detection, tracking and fusion
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
Official code for our ECCV'22 paper "A Fast Knowledge Distillation Framework for Visual Recognition"