Docling

IBM's document conversion tool for AI pipelines

⭐15,000
Data ToolsFree (open-source)
🌐 Visit Website📦 GitHub

About Docling

Docling by IBM Research converts documents (PDFs, DOCX, PPTX, images) into clean, structured formats optimized for AI. It handles tables, OCR, and complex layouts — designed for RAG pipelines.

Features

✦PDF conversion
✦Table extraction
✦OCR
✦Markdown output
✦LlamaIndex integration

Pros & Cons

Pros

  • +Excellent PDF parsing
  • +Table extraction
  • +OCR capability
  • +IBM Research quality
  • +LlamaIndex integration

Cons

  • −Heavy dependencies
  • −Can be slow on large docs
  • −Python only
  • −Complex output format

Platforms

LinuxmacOSWindows

Tags

#documents#pdf#conversion#ibm

Similar Tools

Qdrant

High-performance vector database for AI applications

Free (open-source) + Cloud

Firecrawl

Turn websites into LLM-ready markdown or structured data

Free (open-source) + Cloud

ChromaDB

Open-source embedding database for AI applications

Free (open-source)

Weaviate

Open-source vector database with built-in AI modules

Free (open-source) + Cloud

Need help choosing?

Compare Docling with alternatives side by side

Compare Tools →