Loading page
Loading page

AI · LlamaParse alternative
Convert PDFs, Office files and scans into clean Markdown or JSON through an API, ready for RAG and AI pipelines.
Docling is an open-source toolkit that reads documents and turns them into clean, structured output. It understands PDF page layout, reading order and tables, runs OCR on scans, and exports to Markdown, HTML or JSON. Docling Serve wraps it in an HTTP API, so any app can send a document and get the result back.
The API has a stable v1 version, interactive docs at /docs and an optional playground UI.
It suits developers building RAG systems, search over documents, or data pipelines that start from PDFs and Office files. It also suits teams that need to process documents that cannot leave their network.
Hosted parsing APIs charge per page and see every document you send. Your own Docling Serve converts as many pages as your server can handle, and contracts, reports and scans stay inside your own service. Docling is built to run locally, even in air-gapped setups.
The trade-off is resources. The image is large, and conversion with layout models and OCR uses a lot of CPU and memory. Big batches are slow on CPU. The API has no login in this template, so keep it private. You also update the image yourself, and this template uses the latest tag.
Containers: quay.io/docling-project/docling-serve:latest
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose Docling Serve, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the Docling Serve setup screen.