Skip to content
FindOpenSource

Docling

Document parsing library that converts PDFs, Word docs, and other formats into clean, structured data ready for LLM and RAG pipelines.

Overview

Docling parses complex document formats - PDFs with tables and figures, Word documents, PowerPoint files, and more - into structured representations (like Markdown or JSON) that preserve layout information an LLM can actually use, rather than the garbled plain text a naive PDF-to-text conversion produces. It's built specifically with RAG and LLM ingestion pipelines in mind.

Docling is a fit for teams feeding documents into an LLM or RAG pipeline who need accurate structure preservation, complementing Tesseract (also in this catalog) - Tesseract recognizes text from raw pixels, while Docling focuses on understanding a document's structure and layout.

Categories
AI & Machine Learning
Keywords
document-parsingragpdf-processingdata-extraction
Languages
Python
License
MIT

Spotted an error? Suggest an edit on GitHub.