Retrieval-Augmented Generation (RAG) has revolutionized how we use large language models by grounding their responses in external knowledge. But here’s…
MiniRAG: Enable Small Language Models to Deliver Powerful RAG with Minimal Resources 1605
Retrieval-Augmented Generation (RAG) has become a cornerstone technique for grounding language models in factual knowledge. However, traditional RAG pipelines struggle…
EASYTOOL: Streamline LLM Agent Tool Usage with Concise, Unified Instructions 24492
Building capable AI agents that interact with real-world tools—like APIs, software libraries, or external services—is a core challenge in deploying…
AutoGL: Automate Graph Learning Pipelines Without Manual Tuning or Expert GNN Knowledge 1131
Graph-based machine learning has become essential across domains—from social network analysis and fraud detection to drug discovery and recommendation systems.…
AutoAgents: Automatically Generate Specialized AI Teams for Complex Real-World Tasks 1444
Building intelligent systems that can handle open-ended, multi-step problems has long been a challenge in AI development. Traditional multi-agent frameworks…
Amphion: A Unified Open-Source Toolkit for Zero-Shot Speech, Singing, and Audio Generation 9539
Amphion is an open-source toolkit purpose-built for audio, music, and speech generation that dramatically lowers the entry barrier for junior…
PP-FormulaNet: High-Accuracy and High-Speed Math Formula Recognition for Document Intelligence 5930
In the world of scientific publishing, academic research, and educational technology, one persistent bottleneck remains: converting handwritten or printed mathematical…
SGLang: High-Performance LLM Serving for Structured, Multi-Step, and Multimodal AI Applications 21238
Large language models (LLMs) are no longer just tools for answering questions—they power agents, structured data pipelines, multi-turn conversations, and…
PP-OCR: Ultra-Lightweight, Multilingual OCR and Document AI for Real-World Applications 66154
In today’s AI-driven world, turning unstructured visual data—like scanned invoices, handwritten notes, or multilingual PDFs—into structured, machine-readable formats is a…
MinerU: High-Precision Open-Source Document Parsing for Real-World PDFs, Tables, and Formulas 50296
Converting real-world documents—especially PDFs containing mixed content like equations, tables, multi-column layouts, and scanned text—into clean, structured, machine-readable formats remains…