# Docling vs Unstructured

**Leader by Vioscale score:** Unstructured

| Attribute | Docling | Unstructured |
|---|---|---|
| **Vioscale score** | 59.6 (32% (low)) | 84.3 (55% (medium)) |
| activity.commits_last_30d | 100 | - |
| adoption.dependent_repos | 0 | - |
| adoption.github_stars | 65,599 | - |
| deployment.options | `{"cloud":true,"on_prem":true,"air_gapped":true,"self_hosted":true}` | `{"cloud":true,"on_prem":true,"self_hosted":true}` |
| description.long | 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. | Unstructured provides enterprise-grade data preprocessing and ETL capabilities that convert messy, unstructured documents (PDFs, images, tables, etc.) into machine-readable formats optimized for language models and AI workflows. It handles data ingestion, transformation, enrichment, and embedding across multiple sources and destinations with built-in security and compliance. |
| features.capabilities | `{"open_source":true,"pricing_model":"free_open_source","prebuilt_models":true,"table_extraction":true,"architecture_model":"open_source_library","llm_vlm_based_extraction":true,"mit_or_apache_permissive_oss_license":true,"pdf_and_multimodal_image_ocr_parsing":true,"zero_data_retention_privacy_guarantees":true,"native_chunking_and_vectorization_for_rag":true,"fine_tuned_document_layout_analysis_models":true,"tabular_layout_preservation_for_complex_tables":true}` | `{"open_source":true,"soc2_type_ii":true,"pricing_model":"pay_per_page_api","prebuilt_models":true,"table_extraction":true,"architecture_model":"managed_cloud_api","confidence_scoring":false,"id_document_parsing":false,"rpa_erp_integration":false,"custom_model_training":true,"handwriting_recognition":false,"human_in_the_loop_review":false,"llm_vlm_based_extraction":true,"web_scraping_to_markdown_or_json":true,"mit_or_apache_permissive_oss_license":true,"pdf_and_multimodal_image_ocr_parsing":true,"zero_data_retention_privacy_guarantees":true,"javascript_rendering_for_spa_web_scraping":false,"native_chunking_and_vectorization_for_rag":true,"strict_json_schema_forcing_and_validation":false,"fine_tuned_document_layout_analysis_models":true,"human_in_the_loop_hitl_confidence_review_queue":false,"tabular_layout_preservation_for_complex_tables":true}` |
| integrations.count | 5 | 40 |
| integrations.list | `[{"name":"LangChain"},{"name":"LlamaIndex"},{"name":"Crew AI"},{"name":"Haystack"},{"name":"OpenContracts"},{"name":"Apify"}]` | `[{"name":"Airtable"},{"name":"Google Cloud Storage"},{"name":"Google Drive"},{"name":"Jira"},{"name":"PostgreSQL"},{"name":"S3"},{"name":"Salesforce"},{"name":"SFTP"},{"name":"Slack"},{"name":"Snowflake"},{"name":"SQLite"},{"name":"Zendesk"},{"name":"Amazon Bedrock"},{"name":"Astra DB"},{"name":"DuckDB"},{"name":"Elasticsearch"},{"name":"IBM Milvus"},{"name":"IBM watsonx.data"},{"name":"Weaviate"},{"name":"OpenAI"},{"name":"Anthropic"},{"name":"Azure OpenAI"},{"name":"Google Gemini"},{"name":"AWS Bedrock"},{"name":"IBM watsonx"},{"name":"NVIDIA"},{"name":"Together.ai"},{"name":"VertexAI"},{"name":"Cohere"},{"name":"Amazon S3"},{"name":"Azure Blob Storage"},{"name":"Databricks"},{"name":"OpenSearch"},{"name":"Neo4j"},{"name":"Kafka"},{"name":"Box"},{"name":"OneDrive"},{"name":"Confluence"},{"name":"Dropbox"},{"name":"LangChain"},{"name":"SAP"},{"name":"Teradata"},{"name":"Cursor"},{"name":"Codex"}]` |
| language.primary | Python | - |
| license.spdx | MIT | - |
| market.availability | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"hqCountry":"US","primaryMarkets":["US","GB","EU"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"mac":true,"web":true,"linux":true,"windows":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"open_source","summary":"Open source project, free to use","freeTier":true,"sourceUrl":"https://docling-project.github.io/docling/","retrievedAt":"2026-08-20T16:31:10.636Z"}` | `{"type":"hybrid","plans":[{"free":true,"name":"Free","summary":"15,000 pages/month free","features":["All features included"],"components":[{"kind":"fixed","amount":0,"period":"month","currency":"USD"}],"description":"Monthly free allowance with automatic resets","contactSales":false,"includedLimits":{"pages":"15,000/month"}},{"free":false,"name":"Pay-As-You-Go","summary":"$0.03/page after 15,000 free pages; bill capped at $3,000/month","features":["All features included"],"components":[{"per":{"qty":1,"unit":"page"},"kind":"metered","amount":0.03,"currency":"USD"}],"description":"Usage-based pricing after free monthly allowance","contactSales":false},{"free":false,"name":"Business","summary":"Custom pricing","features":["Multi-user accounts","Dedicated Instance or VPC","Full data isolation","24/7 technical support"],"description":"Enterprise deployment with dedicated infrastructure and support","contactSales":true}],"summary":"Free tier with 15,000 pages/month. Pay-as-you-go at $0.03/page with $3,000 monthly cap. Custom enterprise pricing available.","currency":"USD","freeTier":true,"sourceUrl":"https://unstructured.io/pricing","retrievedAt":"2026-08-21T13:45:12.559Z","startingPrice":{"unit":"page","amount":0.03,"currency":"USD"},"billingPeriods":["month"]}` |
| pricing.free_tier | yes | yes |
| pricing.model | open_source | freemium |
| pricing.price_level | free | low |
| pricing.starting_price | - | `{"amount":0.03,"currency":"USD"}` |
| pricing.transparent | yes | yes |
| release.cadence_days | 2 | - |
| release.history | `[{"url":"https://github.com/docling-project/docling/releases/tag/v2.123.0","date":"2026-08-26T16:15:07Z","type":"stable","version":"v2.123.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.122.0","date":"2026-08-25T09:28:52Z","type":"stable","version":"v2.122.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.121.0","date":"2026-08-20T09:05:04Z","type":"stable","version":"v2.121.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.120.3","date":"2026-08-18T07:50:48Z","type":"stable","version":"v2.120.3"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.120.2","date":"2026-08-17T10:00:58Z","type":"stable","version":"v2.120.2"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.120.1","date":"2026-08-14T11:48:42Z","type":"stable","version":"v2.120.1"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.120.0","date":"2026-08-14T09:29:25Z","type":"stable","version":"v2.120.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.119.0","date":"2026-08-10T10:26:09Z","type":"stable","version":"v2.119.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.118.1","date":"2026-08-07T13:56:13Z","type":"stable","version":"v2.118.1"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.118.0","date":"2026-08-03T15:29:51Z","type":"stable","version":"v2.118.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.117.0","date":"2026-07-30T12:22:45Z","type":"stable","version":"v2.117.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.116.0","date":"2026-07-29T11:24:35Z","type":"stable","version":"v2.116.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.115.0","date":"2026-07-23T14:44:10Z","type":"stable","version":"v2.115.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.114.0","date":"2026-07-20T14:05:50Z","type":"stable","version":"v2.114.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.113.0","date":"2026-07-14T10:41:42Z","type":"stable","version":"v2.113.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.112.0","date":"2026-07-11T04:28:02Z","type":"stable","version":"v2.112.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.111.0","date":"2026-07-08T11:23:53Z","type":"stable","version":"v2.111.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.110.0","date":"2026-07-04T13:53:13Z","type":"stable","version":"v2.110.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.109.0","date":"2026-07-03T14:02:41Z","type":"stable","version":"v2.109.0"},{"url":"https://github.com/docling-project/docling/releases/tag/v2.108.0","date":"2026-07-01T10:28:50Z","type":"stable","version":"v2.108.0"}]` | - |
| security.gdpr | - | yes |
| security.hipaa | - | yes |
| security.iso27001 | - | yes |
| security.soc2 | - | yes |
| security.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,"max_severity":null}` | - |

## Capabilities (Document AI)

| Capability | Docling | Unstructured |
|---|:--:|:--:|
| **Capabilities** |  |  |
| 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 | ✓ | ✓ |

*Source: Vioscale. Generated 2026-09-01T16:32:17.269Z. "-" = undocumented, not absent.*