Stars
Implementation of my RAG system that won all categories in Enterprise RAG Challenge 2
An extremely fast Python package and project manager, written in Rust.
The official Python SDK for Model Context Protocol servers and clients
分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Open-source project showcasing how single or multiple AI Agents interact with MCP in real-world tasks. Includes both frontend and backend implementations.
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
astordu / r1-reasoning-rag
Forked from deansaco/r1-reasoning-ragrecursive rag with r1 reasoning
Paper list for Efficient Reasoning.
SkyRL-v0: Train Real-World Long-Horizon Agents via Reinforcement Learning
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
Empowering RAG with a memory-based data interface for all-purpose applications!
Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception
Model Context Protocol Servers
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案
official implementation of Entropy Minimized Policy Optimization (EMPO)
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
LlamaIndex is the leading framework for building LLM-powered agents over your data.
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personali…
Code for explaining and evaluating late chunking (chunked pooling)
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
Retrieval and Retrieval-augmented LLMs
💬 MaxKB is an open-source AI assistant for enterprise. It seamlessly integrates RAG pipelines, supports robust workflows, and provides MCP tool-use capabilities.
"LightRAG: Simple and Fast Retrieval-Augmented Generation"