Library (Docsplit wrapper) for text extraction from pdf, doc/x, txt files with OpenOffice

Ruby chain tools to work with LLMs

["A service to generate pdf reports"]

Processa documentos do condominio ph1341c118 para arquivo. Pode tambem segmentar PDFs e MINUTAS. Tendo os documentos em pastas separadas, pode ainda criar arquivos apropriados.

Fetch title, author, abstruct, and citations list of paper in arXiv from pdf file

This gem uses Ghostscript and Tesseract to perform OCR on various file formats.

Bidi2pdf Rails provides a seamless integration between Rails and the Bidi2pdf gem for generating high-quality PDFs using Chrome/Chromium's headless browser. It supports rendering PDFs from controller actions, remote URLs, or HTML strings with configurable options for orientation, margins, page size, and more. The gem handles browser lifecycle management and provides a clean API for PDF generation with proper asset handling.

LangChain but for the builder tech stack.

Code Zauker is based from ideas taken by old Google Code Search and uses Redis as a basic platform

A set of utility classes to extract meta data from different file types

COVID19 data fetcher and parser for Portugal

A gem to convert PDF, Word, Excel, and image files to rich HTML format compatible with Trix editor

Modular extension providing invoice document type functionality

Dragonfly PDF analysers and processors.

Create Dvorak deck PDFs using YAML files.

Generate PDF, ePub, and Mobi eBooks

generate an organized library from a local ebook directory.

Bulk rename multiple ebook files (pdf, epub, mobi) using embedded metadata if available (pure ruby implementation)

电子书工具集.

Loads records from Druginfo Interview Form.