Stars
An NVIDIA AI Workbench example project for Retrieval Augmented Generation (RAG)
KylinMountain / graphrag-server
Forked from microsoft/graphrag添加🚀流式 Web 服务到 GraphRAG,兼容 OpenAI SDK,支持可访问的实体链接🔗,支持建议问题,兼容本地嵌入模型,修复诸多问题。Add streaming web server to GraphRAG, compatible with OpenAI SDK, support accessible entity link, support advice question, co…
Convert PDF to markdown quickly with high accuracy
Implementation of Nougat Neural Optical Understanding for Academic Documents
A Comprehensive Toolkit for High-Quality PDF Content Extraction
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。
GraphRAG4OpenWebUI integrates Microsoft's GraphRAG technology into Open WebUI, providing a versatile information retrieval API. It combines local, global, and web searches for advanced Q&A systems …
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.
[Paper][Preprint 2024] MyGO: Discrete Modality Information as Fine-Grained Tokens for Multi-modal Knowledge Graph Completion
A modular graph-based Retrieval-Augmented Generation (RAG) system
The Security Toolkit for LLM Interactions
Generate dialog data from documents using LLM like ChatGLM2 or ChatGPT;利用ChatGLM2,ChatGPT等大模型根据文档生成对话数据集
[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
Universal LLM Deployment Engine with ML Compilation
Python module (C extension and plain python) implementing Aho-Corasick algorithm
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。
[ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"
Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety.
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search…
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.