A Heterogeneous Benchmark for Information Retrieval
The SILE Typesetter — Simon’s Improved Layout Engine
BISHENG is an open LLM devops platform for next generation apps
Fast streaming XML parser written in C99 with >90% test coverage
JupyterLab extension for live editing of LaTeX documents
RSocket Kotlin multi-platform implementation
The Official MongoDB driver for C language
Self-contained, offline survival computer with tools, knowledge, & AI
PDFCraft is a free, privacy-focused PDF toolkit
A SOAP client and server for node.js
Pretty diagnostics, references, telescope results, quickfix, location
ContextGem: Effortless LLM extraction from documents
Simple reactive notebooks for Julia plutojl.org
A Docker-powered stateless API for PDF files
RAGLite is a Python toolkit for Retrieval-Augmented Generation
An open-source RAG-based tool for chatting with your documents
borb is a library for reading, creating and manipulating PDF files
Delve is a debugger for the Go programming language
Fully automated version management and package publishing
Floki is a simple HTML parser that enables search for nodes using CSS
Ready-to-use OCR with 80+ supported languages
Research project. A Memory solution for users, teams, and applications
SVG file parsing / rendering library
The official Python client for the Huggingface Hub
A TypeScript based PDF generator library, made with React