text-extract-api vs docling-api
Self-hosted document conversion APIs compared
text-extract-api and docling-api are Python services for processing documents in a self-hosted environment. text-extract-api combines OCR with optional Ollama processing to produce Markdown or structured JSON, while docling-api focuses on converting varied document formats into Markdown through Docling.

text-extract-api: Extract Text and Data from Documents
A self-hostable API that turns PDFs, images, and Office files into Markdown or structured JSON using OCR and Ollama models. It suits teams that need document processing and PII removal with control over where files are processed.

docling-api: Convert Documents to Markdown Through an API
docling-api is a self-hostable FastAPI service that converts documents and images into Markdown using Docling. It suits teams that need synchronous or queued batch processing, with CPU and GPU deployment options.
| text-extract-api | docling-api | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 3.2k | 1.7k |
| Forks | 279 | 425 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- text-extract-api can produce structured JSON as well as Markdown; docling-api describes Markdown conversion.
- text-extract-api offers several OCR strategies and optional Ollama model processing, including prompts for PII removal; docling-api uses Docling and supports multilingual OCR.
- docling-api lists support for formats including HTML, CSV, AsciiDoc, and Markdown; text-extract-api focuses on PDFs, images, and Office documents.
- Both use Celery and Redis for queued processing, while docling-api also describes batch endpoints, job status tracking, and Flower monitoring.
- text-extract-api includes configurable result storage profiles such as local files, Google Drive, and Amazon S3; docling-api highlights CPU-only and GPU-enabled deployments.
- Both projects use Python and have an MIT license; text-extract-api has 3.2k stars and 279 forks, while docling-api has 1.7k stars and 425 forks.
Choose text-extract-api if you…
- need structured JSON output as well as Markdown.
- want optional Ollama processing, custom prompts, or prompt-based PII removal.
- need configurable storage profiles or OCR strategies for PDFs, images, and Office files.
Choose docling-api if you…
- need a Docling-based service that converts a broad range of formats to Markdown.
- want synchronous or batch endpoints alongside asynchronous jobs with status tracking.
- need to deploy with CPU-only or GPU-enabled processing options.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.