Docling
by IBM · open-source · Last verified 2026-03-17
IBM's document conversion library for parsing PDFs and other formats into structured representations. Provides high-quality table extraction, OCR support, and export to Markdown or JSON formats.
https://ds4sd.github.io/docling/ ↗C
C—Below Average
Adoption: CQuality: AFreshness: A+Citations: CEngagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- pdf-parsing, table-extraction, ocr, markdown-export, json-export
- Integrations
- langchain, llamaindex
- Use Cases
- pdf-processing, document-conversion, data-extraction, rag-ingestion
- API Available
- Yes
- SDK Languages
- python
- Deployment
- self-hosted, docker
- Rate Limits
- N/A (open-source)
- Data Privacy
- Self-hosted, user-managed
- Tags
- document-conversion, pdf-parsing, ibm, structured-output
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
46.9Adoption
48
Quality
82
Freshness
90
Citations
45
Engagement
0