Stars
Every practical and proposed defense against prompt injection.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
Code accompanying the paper "Massive Activations in Large Language Models"
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Machine Learning, Python, Deep Learning, Linux, Pandas, Matplotlib, Git...
100+套大数据可视化炫酷大屏Html5模板；包含行业：社区、物业、政务、交通、金融银行等，全网最新、最多，最全、最酷、最炫大数据可视化模板。陆续更新中
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
LAVIS - A One-stop Library for Language-Vision Intelligence
🔥 官方推荐 🔥 RuoYi-Vue 全新 Pro 版本，优化重构所有功能。基于 Spring Boot + MyBatis Plus + Vue & Element 实现的后台管理系统 + 微信小程序，支持 RBAC 动态权限、数据权限、SaaS 多租户、Flowable 工作流、三方登录、支付、短信、商城、CRM、ERP、AI 大模型等功能。你的 ⭐️ Star ⭐️，是作者生发的动力！
Understanding Deep Learning - Simon J.D. Prince
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
Not only automatic, but also intelligent. An Intelligent data Visualization System, based on LLM.
[ICLR 2023] MultiViz: Towards Visualizing and Understanding Multimodal Models
Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023
AI Tool for querying natural language on tabular data.
hotpdf is a fast PDF parsing library to extract text and find text within PDF documents built on top of pdfminer.six
Implementation of Nougat Neural Optical Understanding for Academic Documents
BGPlay.js provides a graphical and intuitive representation of the inter-domain routing and its evolution over time
High performance edge bundling on the GPU for WebGL, works on all browsers. Based on the d3 CPU implementation + GPU implementation by Wu et al., but extensively modified.
godoorsun / d3.ForceBundle
Forked from upphiminn/d3.ForceBundleForce Directed Edge Bundling (FDEB) in Javascript; d3.js ready. (http://www.win.tue.nl/~dholten/papers/forcebundles_eurovis.pdf).
✨✨Latest Advances on Multimodal Large Language Models
Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.