Pinned

1. Smartinput Smartinput Public

   旨在利用大模型对多种输入（文本，语言，图像）进行识别并进行操作，仍在起步阶段。Aims to recognise and manipulate multiple inputs (text, speech, images) using large models, still in its start part.

   Python 3 2

2. pdfdeal pdfdeal Public

   Easier to deal with PDF, extract readable text and OCR to recognise image text and clean the format. Make it more suitable for knowledge base construction. Comes with Doc2X support.使PDF更适合RAG处理，附带D…

   Python 7

3. Useful-Tools Useful-Tools Public

   Some useful applets/scripting tools, generally written in bash or python.一些实用的小程序/脚本工具，一般而言使用bash或者python编写。

   Python 1

4. Smartinput-Upscaler Smartinput-Upscaler Public

   The project is a GUI based on Real-ESRGAN for convenient and fast super-resolution processing of various images/PDF.基于Real-ESRGAN的对图片/PDF超分辨率处理的多平台图形化界面。

   Python 2

5. gpt_academic gpt_academic Public

   Forked from binary-husky/gpt_academic

   为ChatGPT/GLM提供实用化交互界面，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm2等本地模型。兼容文心一言, moss, llama2, rwkv, claude2, 通义千问, 书生, 讯飞星火等。

   Python

6. KAN-Models KAN-Models Public

   Trying to build some models using KAN (Kolmogorov-Arnold Networks)

   Python 5