Results for unpdf

PDF extraction and rendering across all JavaScript runtimes

unpdf plugin for Uploadista document text extraction

Combined pdf-lib + unpdf DocumentPlugin for Uploadista Flow

Parse LinkedIn PDF exports into structured data with unpdf. Serverless-ready TypeScript library for Node, Vercel Edge, and other JS runtimes.

PDF.js redistributed as a single bundle for edge and serverless runtimes

Full-text PDF, DOCX, PPTX, XLSX search for static sites — Apache Solr for client-side apps, without Solr.

Advanced client-side PDF to HTML converter with WASM parsing, OCR support, and intelligent text layout reconstruction. Perfect for document management systems and web applications.

Convert anything to markdown. PDF, DOCX, PPTX, XLSX, HTML, EPUB, Jupyter, RSS, images, audio, URLs, and more. Pluggable converters, built-in LLM providers for image description and audio transcription. Works as a CLI and as a library.

PDF Extractor for n8n

pdf-lib plugin for Uploadista document processing

HireBase - AI-powered CV search engine with LanceDB and MCP

Hi, I'm Johann. Developer with an eye for design.

Model Context Protocol (MCP) server for PDF text extraction operations

Zero-dependency TypeScript PDF text extraction for RAG and AI pipelines

MCP server for Infomaniak kDrive — search, list, and read files (text, Excel, Word, PDF, PowerPoint)

Metadata extractor for document files

Vectorless, reasoning-based RAG. Builds hierarchical tree indices from PDFs and retrieves via LLM-driven tree search.

Extract text from PDF page range (CJS)

MCP server for PhilPapers / PhilArchive — search philosophy papers, fetch metadata, list recent submissions, and download open-access PDFs. No API key required.

High-performance PDF extraction to Markdown, text, and JSON (WebAssembly)

Pure, web-first, multi-provider TypeScript AI SDK (Anthropic, OpenAI, xAI, Gemini).

Zero-config CLI that ingests files into vector databases for RAG projects. Parse, chunk, embed, upsert — one command.