Available worldwide
What is Docling?
A Python library that converts documents from multiple formats (PDF, Word, Excel, images, audio, video, etc.) into structured data representations. Offers sophisticated PDF analysis capabilities for layout, tables, and content extraction, plus OCR support and AI framework integration.
Docling pricing
We don't have Docling's full plan breakdown yet (its pricing page resisted automated reading). Here's what we could confirm. Always check live pricing for exact numbers.
Open source project, free to use
What Docling does
The capabilities that matter for document ai, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Prebuilt models
- ✓
- Custom model training
- -
- Table extraction
- ✓
- Handwriting recognition
- -
- Id document parsing
- -
- Human in the loop review
- -
- Confidence scoring
- -
- LLM vlm based extraction
- ✓
- RPA ERP integration
- -
- Open source
- ✓
Platform & deployment
Independently observed- CLI
- macOS
- Web
- Linux
- Windows
- Cloud / SaaS
- On-premise
- Air-gapped
- Self-hosted
Integrations (6)
Independently observed- LangChain
- LlamaIndex
- Crew AI
- Haystack
- OpenContracts
- Apify
Security & compliance
Known vulnerabilities: 0 (0 in the last 12 months) sourcea count reflects scale & disclosure, not quality
Docling alternatives
Other document ai we track, ranked by the same independent score.
- UnstructuredTransform complex documents and unstructured data into clean, structured formats ready for AI applications.medium · 55%
- MindeeCloud-based machine learning API that automatically extracts structured data from documentslow · 43%
- NanonetsAutomate enterprise workflows by converting business processes into autonomous AI agentsmedium · 52%
- HyperscienceEnterprise AI platform for intelligent document automationlow · 13%
- RossumAI-powered platform that automates reading, validating, and processing transactional documents end-to-endlow · 41%
- PaddleOCRlow · 16%
Compare Docling
Side by side against other document ai, attribute by attribute, with a source on every value.
The Vioscale score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Docling, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Capabilities | 100 | 0.08 | 7.8 | ✓ |
| Development activity | 63 | 0.09 | 5.9 | ✓ |
| Release cadence | 99 | 0.05 | 5.1 | ✓ |
| Stars | 91 | 0.03 | 2.4 | ✓ |
| Integrations | 22 | 0.07 | 1.6 | ✓ |
| Dependent projects | 0 | 0.06 | 0.0 | ✓ |
| Security posture | 0 | 0.07 | 0.0 | - |
| Package downloads | 0 | 0.14 | 0.0 | - |
| Security score | 0 | 0.04 | 0.0 | - |
| Developer Q&A activity | 0 | 0.06 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Activity
| Attribute | Value | Evidence |
|---|---|---|
| Commits last 30d | 100 | mediumsource · 2026-08-26 · 65% |
Adoption
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Open source: Yes · Pricing model: free_open_source · Prebuilt models: Yes · Table extraction: Yes · Architecture model: open_source_library · Llm vlm based extraction: Yes | mediumsource · 2026-08-21 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 5 | mediumsource · 2026-08-20 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | Python | highsource · 2026-08-26 · 90% |
License
| Attribute | Value | Evidence |
|---|---|---|
| Spdx | MIT | highsource · 2026-08-26 · 95% |
Market
| Attribute | Value | Evidence |
|---|---|---|
| Availability | PrimaryMarkets: … · AvailabilityScope: global · AvailableCountries: … · NotAvailableCountries: … | highsource · 2026-08-21 · 75% |
Pricing
Release
Security
| Attribute | Value | Evidence |
|---|---|---|
| Vulnerabilities | Count: 0 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=go&package_name=github.com%2Fdocling-project%2Fdocling&per_page=100 · Last 12m: 0 | highsource · 2026-08-26 · 90% |