- Home
- PDF Converter Software
- Docling
Docling
What it is
Docling converts documents into structured data for AI workflows. It accepts PDFs, DOCX, PPTX, XLSX, HTML, EPUB, audio, video, images, email, and Apple iWork files. PDF processing covers page layout, reading order, table structure, code, formulas, and image classification. Export targets include Markdown, HTML, WebVTT, DocLang, DocTags, lossless JSON, text, LaTeX, and JSONL chunks. Multiple OCR engines are supported, including EasyOCR, Tesseract, OcrMac, and RapidOCR. Documented integrations include LangChain, LlamaIndex, Haystack, Crew AI, and other AI frameworks and agent tools. Docling can run as a local Python library, a self-operated HTTP service, or through managed and private deployments. The project says local processing can continue offline after models are downloaded and cached, without uploading documents. Managed service requests have size, rate, and concurrency limits, with provider terms defining retention and processing boundaries. The MIT-licensed open-source library costs nothing; an IBM watsonx trial is also free for 30 days and 5,000 pages.
For and against
For
- Handles PDFs, Office files, media, email, and iWork inputs
- Exports Markdown, HTML, JSON, XML, and more
- Supports several OCR engines
- Can run locally and offline after model caching
- Offers documented AI framework integrations
Against
- Managed requests have size, rate, and concurrency limits
- Provider terms govern managed-service retention boundaries
- Offline operation requires downloading and caching models
The verdict
Docling offers broad document ingestion, PDF understanding, OCR, and export choices for AI pipelines. Its local, self-operated, and managed deployment paths let teams choose where processing occurs, with managed limits to consider.
Who it suits
Docling suits developers and AI teams converting varied business files into structured formats. It is also relevant to users who need local or offline processing and integrations with agent frameworks.
Plans and prices
Docling for IBM watsonx trial
30-day trial · free for 5,000 pages
Read 5 Oct 2026 · ibm.com
Docling open-source library
MIT licensed · local install · offline after model download
Read 5 Oct 2026 · docling.ai
On the record
- AI integrations
- Documented integrations include LangChain, LlamaIndex, Haystack, Crew AI, and other AI frameworks and agent tools.docling-project.github.io · read 5 Oct 2026
- Deployment options
- Docling can run as a local Python library, as a self-operated HTTP service, or through managed and private deployment offerings.docling.ai · read 5 Oct 2026
- Exports
- Docling can export to formats including Markdown, HTML, WebVTT, DocLang, DocTags, and lossless JSON.docling-project.github.io · read 5 Oct 2026
- Local privacy
- The project says it can run locally, including offline after its models are downloaded and cached, without uploading documents.docling.ai · read 5 Oct 2026
- Managed service limits
- The deployment page says managed service requests have size, rate, and concurrency limits, and provider terms determine retention and processing boundaries.docling.ai · read 5 Oct 2026
- OCR
- The project supports multiple OCR engines, including EasyOCR, Tesseract, OcrMac, and RapidOCR.docling-project.github.io · read 5 Oct 2026
- PDF understanding
- Its PDF processing handles page layout, reading order, table structure, code, formulas, and image classification.docling-project.github.io · read 5 Oct 2026
- Project home
- Docling is hosted as a project in the LF AI & Data Foundation and was started by IBM Research Zurich's AI for knowledge team.docling-project.github.io · read 5 Oct 2026
- Purpose
- Docling converts documents such as PDFs, Office files, HTML, images, and audio into structured data for AI workflows.docling.ai · read 5 Oct 2026
- Support
- The documentation links to a Docling community Discord and a live assistant for support.docling-project.github.io · read 5 Oct 2026
- Supported inputs
- The documentation lists formats including PDF, DOCX, PPTX, XLSX, HTML, EPUB, audio, video, images, email, and Apple iWork files.docling-project.github.io · read 5 Oct 2026
