📑
Docling
IBM open-source document parsing for AI pipelines
Data & Analytics
Docling is an open-source document understanding library from IBM Research that converts PDFs, Word files, and images into structured Markdown or JSON. It preserves tables, figures, reading order, and document structure with high accuracy. AI engineers use Docling as a best-in-class PDF parser for RAG and document intelligence applications.
Key Features
- ✓High-accuracy PDF parsing
- ✓Table and figure extraction
- ✓Reading order preservation
- ✓Markdown and JSON output
- ✓Local processing — no API needed
#document parsing#pdf extraction#open source#rag#document intelligence
Quick Info
- Category
- Data & Analytics
- Pricing
- Free
More Data & Analytics Tools
Julius AI
Data & AnalyticsAnalyze spreadsheets and databases by asking plain-English questions
Obviously AI
Data & AnalyticsBuild machine learning models without code
Polymer
Data & AnalyticsTransform spreadsheets into searchable apps
Hex
Data & AnalyticsCollaborative data notebooks with AI