# drmingler/docling-api

Easily deployable and scalable backend server that efficiently converts various document formats (pdf, docx, pptx, html, images, etc) into Markdown. With support for both CPU and GPU processing, it is Ideal for large-scale workflows, it offers text/table extraction, OCR, and batch processing with sync/async endpoints.

Repository: https://github.com/drmingler/docling-api
Canonical: https://ross.abutalabs.com/products/docling-api
Language: Python
License: MIT
License Family: permissive
Topics: api, fastapi, markdown-parser, pdf-chatbot, pdf-conversion, pdf-converter, pdf-parser, pdf-parsing, pdf-to-markdown
Last push: 2026-08-04T08:06:41+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 35, longevity 47
- inputs: {"age_days": 666, "days_push": 29, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1557, forks 394 (observed 2026-08-28T04:05:03.328724+00:00)

## What it is
A self-hostable FastAPI backend service that converts documents (PDF, DOCX, PPTX, HTML, images, CSV, AsciiDoc, Markdown) into Markdown using IBM's Docling parser. It supports CPU and GPU processing, OCR, table/image extraction, and sync/async batch conversion with Celery and Redis job tracking.

## Use cases
- convert pdf files to markdown via an api
- extract text and tables from docx and pptx documents
- ocr scanned pdfs into markdown
- batch convert documents for llm rag pipelines
- self-host a document parsing service with gpu acceleration
- parse pdfs for chatbot ingestion

## When to choose
- you need a scalable, deployable document-to-markdown conversion API rather than a library
- you need OCR, table extraction, and batch/async job processing in one service
- you want GPU-accelerated parsing for large-scale workflows

## Facets
- artifact type: service
- maturity: active
- function: ocr, pdf, parser, api-framework, http-server, etl
- domain: pdf, files, developer-tools, self-hosted
- platform: python, self-hosted
- tags: docling, fastapi, celery, redis, markdown-conversion, document-conversion, batch-processing, pdf-to-markdown, natural-language-processing, docker, web-server, gpu

## Member repositories
- drmingler/docling-api (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:03.328724+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:29:56.872056+00:00, confidence not recorded.
  - readme: https://github.com/drmingler/docling-api (fetched 2026-08-28T04:05:03.328724+00:00, sha 37c3f6dead83)
- Data as of 2026-08-30T08:39:29.467469+00:00.