An e-book manager for organizing, viewing, converting, and editing digital books.
Document Processing
Parsing, text recognition, extraction, conversion, and management of documents.
27 saved linksSearch in this topic →
Saved Links in Document Processing
A rendering engine for generating images and paged documents from JSX, HTML, and CSS without launching a browser.
A rendering engine for generating images and paged documents from JSX, HTML, and CSS without launching a browser.
A tool for converting HTML into Markdown for language-model and content-processing workflows.
A command-line tool and library for converting documents, web pages, and other file formats into Markdown.
A document parser for extracting text and layout information from PDFs and related formats.
A local search engine for Markdown documents, transcripts, and knowledge collections.
A library for extracting the main content and metadata from web pages.
A system for building retrieval-augmented applications from documents and other data sources.
A vision-language model project for extracting document content and layout.
A Python library for extracting structured information from text with language models.
An API for turning web pages and supported documents into text suitable for language-model workflows.