text-extract-api vs docling
Document extraction and conversion projects compared
text-extract-api and docling both turn documents into structured content such as Markdown or JSON, and both can run locally. text-extract-api focuses on OCR, Ollama-based processing, and configurable result storage, while docling covers a wider range of formats and offers document-analysis and AI-framework integrations.
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: Convert Documents into Structured Content
Docling parses documents such as PDFs, Word files, spreadsheets, and images into structured content for applications and generative AI workflows. It offers local processing, a Python library, and a command-line interface.
| text-extract-api | docling | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 3.2k | 68.7k |
| Forks | 279 | 5k |
| Last analyzed | Oct 3, 2026 | Oct 12, 2026 |
Key differences
- text-extract-api accepts PDFs, images, and Office documents; docling also lists formats such as HTML and audio.
- text-extract-api combines OCR strategies with optional Ollama processing and custom prompts; docling focuses on parsing, including PDF layout, reading order, and table analysis.
- text-extract-api offers Markdown and JSON output; docling also lists HTML and WebVTT exports, among other formats.
- text-extract-api supports asynchronous tasks, Redis caching, and storage profiles such as Google Drive and Amazon S3; docling offers integrations with LangChain, LlamaIndex, Haystack, and Crew AI.
- Both are Python projects under the MIT license. The supplied project facts list 3.2k stars for text-extract-api and 68.3k for docling.
- Both support local use; text-extract-api documents a stack including FastAPI, Celery, Redis, and Ollama, while docling supports air-gapped environments.
Choose text-extract-api if you…
- need an API or CLI centered on OCR and extracting content from PDFs, images, and Office files.
- want to refine OCR output with Ollama models or custom prompts, including prompt-based PII removal.
- need asynchronous processing, OCR-result caching, or configurable result storage.
Choose docling if you…
- need parsing across a broader range of document and media formats, including HTML and audio.
- want PDF layout, reading-order, and table analysis or exports such as HTML and WebVTT.
- plan to connect document conversion to retrieval or AI frameworks, or run it in an air-gapped environment.
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.