GitHub - kreuzberg-dev/kreuzberg: A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 75+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

11782 shaares

Filters

Links per page

20 50 100

GitHub - kreuzberg-dev/kreuzberg: A polyglot document intelligence framework with a Rust core. Extract text, metadata, and structured information from PDFs, Office documents, images, and 75+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server.

Un outil d'extraction de texte pour injection dans les LLM qui semble supporter de tres nombreux formats. Ca doit tres certainement pouvoir s'utiliser dans d'autres contextes que les LLM

python · library · open-source · llm · texte · extraction

February 12, 2026 at 6:12:45 PM GMT+1 * · permalink

https://github.com/kreuzberg-dev/kreuzberg

Filters

Links per page

20 50 100