Toolkit for linearizing PDFs for LLM datasets/training

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Samples of advanced RAG techniques

Build an Interactive PDF Reader using LangChain and Streamlit

基于golang开发的网关。具有各种插件，可以自行扩展，即插即用。此外，它可以快速帮助企业管理API服务，提高API服务的稳定性和安全性。

API聚合网关 An Aggregation API Gateway 大模型网关、API集成、API脱敏、API安全、API溯源、

A collection of relevant books I found online, some are recommended and a lot are added because of my greed of perspectives.

OpenPDF is an open-source Java library for creating, editing, rendering, and encrypting PDF documents, as well as generating PDFs from HTML. It is licensed under the LGPL and MPL.

Use your locally running AI models to assist you in your web browsing

Papers from the computer science community to read and discuss.

yuque 语雀知识库下载

mini-spring is a simplified version of the Spring framework that helps you quickly familiarize yourself with Spring source code and master Spring's core principles. It extracts Spring's core logic …

🔥🔥🔥轻量级动态线程池，内置监控告警功能，集成三方中间件线程池管理，基于主流配置中心（已支持Nacos、Apollo，Zookeeper、Consul、Etcd，可通过SPI自定义实现）。Lightweight dynamic threadpool, with monitoring and alarming functions, base on popular config centers …