I have been using the docling software for PDF and XLSX reading/viewing/comprehension by my local qwen3.6. Claude was telling me that docling includes within it a very small LLM model just to assist with what is basically "super OCR". We are definitely in this era of ultra-mega-huge frontier models and super-tiny-micro models, all finding their uses.
On an aside I tested docling by giving it the Ronin TTRPG rulebook PDF and it did an astounding job of converting it all into .txt and .md. Given the wild graphic design of the book that's pretty astounding. Next we'll see if it can read the other Borg books like Mörk Borg and Cy Borg, which are also famous for their messy information.
An alternative to Docling is Xberg: https://github.com/xberg-io/xberg
"A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server."
Amongst other things, you can use it with Open Webui: https://docs.xberg.io/integrations/openwebui/#choosing-an-en...
fyi, they are releasing their v1.0.0 release shortly and until then you will need to a release candidate docker image tag: https://github.com/xberg-io/xberg/issues/1192
As a layman, I would say Xberg is better than Docling because its one engine for everything while the former feels like a bunch of scripts and glue logic.