docling-project/docling-serve

Running Docling as an API service

What it solves

Docling Serve allows users to run Docling—an AI-driven document conversion toolkit—as a scalable API service. This removes the need to integrate the library directly into application code, enabling document conversion to be handled as a standalone network service.

How it works

It wraps the Docling conversion engine in a web server (built with FastAPI), providing a stable v1 API for document processing. Users can send documents via HTTP requests (e.g., using curl or a custom client) and receive converted output. The project provides several deployment options, including a Python package and various container images optimized for different hardware (CPU, CUDA 12.8, CUDA 13.0, and ROCm).

Who it’s for

Developers and organizations that need to integrate high-quality document conversion into their existing software pipelines or deploy the conversion engine in a containerized environment.

Highlights

  • API-First Approach: Provides a stable v1 API and automatic API documentation.
  • Flexible Deployment: Offers specialized container images for CPU and multiple NVIDIA CUDA versions to optimize performance.
  • Interactive Playground: Includes a built-in UI for testing conversions without writing code.
  • Hardware Support: Supports multiple architectures including linux/amd64 and linux/arm64.

Related

  • Project
    drmingler/docling-api

    A scalable backend server that uses IBM's Docling to convert various document formats like PDF and DOCX into Markdown via a FastAPI and Celery-based API.

  • Project
    docling-project/docling

    Docling is an open‑source Python library/CLI that parses many document types (PDF, Word, slides, spreadsheets, HTML, e‑books, audio, video, email, etc.) into a unified, structured representation. It extracts layout, tables, code, formulas, images, and speech‑to‑text, then exports to Markdown, HTML, JSON, DocLang, DocTags, etc. Designed for generative‑AI workflows, it offers plug‑and‑play integrations with LangChain, LlamaIndex, Crew AI, Haystack, and supports local execution for privacy‑sensitive data.

  • Project
    docling-project/docling-parse

    Docling Parse is a fast, configurable PDF‑parsing library (Python API with a C++ core) that extracts text, words, lines, vector shapes and bitmap images together with their coordinates. It supports both sequential and multi‑threaded parsing, lets you choose what to compute or materialize per page, and includes rendering utilities. Ideal for AI workflows that need layout‑aware document data.

  • Project
    docling-project/docling-mcp

    An MCP server that enables AI agents to convert PDFs into structured formats, generate documents, and integrate with RAG pipelines using the Docling library.

  • Project
    magicrew/doc7

    A document conversion tool that turns PDFs, Office files, and images into AI-ready Markdown using multimodal vision models, supporting local inference for privacy and cost-efficiency.