Docling
Document converter that processes multiple file formats with advanced PDF layout analysis and AI integration
- Also known as
- docling
Available worldwide
What is Docling?
A document processing platform that transforms diverse document formats into structured representations with detailed understanding of layout, structure, and content. It supports integration with AI systems and provides both cloud-based and local processing options.
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
- Web
- Cloud / SaaS
- Air-gapped
- Self-hosted
Integrations (8)
Independently observed- Semantica→•
- LangChain
- LlamaIndex
- Crew AI
- Haystack
- OpenContracts
- Apify
- Label Studio
Security & compliance
Known vulnerabilities: 8 (8 in the last 12 months), max severity HIGH sourcea count reflects scale & disclosure, not quality
Docling FAQ
Common questions about Docling, answered from independent, dated evidence.
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. It is indexed under Document AI.
Is Docling free to use?
Docling is open source, so it can be self-hosted and used at no licence cost. It is released under the MIT licence. Pricing changes often, so verify at source before relying on it.
What platforms does Docling support?
Docling supports the web, Windows, macOS, Linux and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.
Can Docling be self-hosted?
Yes. Docling can be deployed cloud / SaaS, on-premise, air-gapped and self-hosted, so it does not have to run on the vendor's infrastructure.
What does Docling integrate with?
We have confirmed 6 integrations for Docling, including LangChain, LlamaIndex, Crew AI, Haystack, OpenContracts and Apify. This is what we could verify from public sources, so the vendor may support others we have not indexed.
Is Docling open source?
Yes. Docling is published under the MIT licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.
Docling alternatives
Other document ai we track, ranked by the same independent score.
- UnstructuredCloud API for converting document files into machine-readable structured datamedium · 53%
- MindeeCloud-based API for extracting structured data from documents using AImedium · 55%
- NanonetsAI automation agents powered by enterprise data extraction and business rule processingmedium · 51%
- HyperscienceAI-powered document processing platform that extracts structured data from unorganized business documentslow · 29%
- RossumAutomate document reading, extraction, validation, and business approvals using AI agentslow · 42%
- AWS TextractMachine learning service that automatically identifies and extracts text, handwriting, and data from documentshigh · 75%
Compare Docling
Side by side against other document ai, attribute by attribute, with a source on every value.
The vioscaleAI 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 |
|---|---|---|---|---|
| Development activity | 63 | 0.14 | 8.5 | ✓ |
| Capabilities | 100 | 0.08 | 8.0 | ✓ |
| Release cadence | 99 | 0.08 | 8.0 | ✓ |
| Stars | 91 | 0.05 | 4.3 | ✓ |
| Integrations | 9 | 0.05 | 0.5 | ✓ |
| Dependent projects | 0 | 0.05 | 0.0 | ✓ |
| Security posture | 0 | 0.12 | 0.0 | - |
| Package downloads | 0 | 0.04 | 0.0 | - |
| Security score | 0 | 0.05 | 0.0 | - |
| Developer Q&A activity | 0 | 0.14 | 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 · 2026-10-13 · 65% |
Adoption
Content
| Attribute | Value | Evidence |
|---|---|---|
| Faq | 6 items | mediumsource · 2026-09-10 · 66% |
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 · 2026-10-13 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 1 | mediumsource · 2026-10-13 · 60% |
Language
| Attribute | Value | Evidence |
|---|---|---|
| Primary | Python | highsource · 2026-10-13 · 90% |
License
| Attribute | Value | Evidence |
|---|---|---|
| Spdx | MIT | highsource · 2026-10-13 · 95% |
Market
| Attribute | Value | Evidence |
|---|---|---|
| Availability | PrimaryMarkets: … · AvailabilityScope: global · AvailableCountries: … · NotAvailableCountries: … | highsource · 2026-08-21 · 75% |
Pricing
Release
Security
| Attribute | Value | Evidence |
|---|---|---|
| Vulnerabilities | Count: 8 · Source: https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=docling-slim&per_page=100 · Last 12m: 8 · Max severity: HIGH | highsource · 2026-10-13 · 90% |
Is Docling the right choice for you?
Tell us the job, the constraints and what you weigh most, and we will rank Docling against the rest of the document ai we index, using the same dated evidence weighted your way.
Free to run, no account needed to start. How the evaluation works
Is this your product?
This profile was built from public sources without asking you. You can take the badge below and use it anywhere, and you can claim the profile to correct anything we got wrong. Both are free, and neither moves Docling up or down: nobody can buy rank here, including you.
Take the badge
Live, always current, and free to use on your own site. It shows Docling's independent score and links back to this profile.
<a href="https://www.vioscale.ai/software/docling" target="_blank" rel="noopener">
<img src="https://www.vioscale.ai/badge/software/docling.svg" alt="Docling, verified on vioscaleAI" width="330" height="76" loading="lazy" />
</a>Markdown, for a README →
[](https://www.vioscale.ai/software/docling)Claim the profile
Verify you control the domain, then point us at the pages that state the facts about Docling and add your own description and media. Free, and it does not change the score.
- Correct anything wrong, with evidence
- Point our crawler at the pages that matter
- Write your own description and add media
Not the owner? How vendor profiles work