text-extract-api vs gptpdf
Document extraction projects compared
text-extract-api processes PDFs, images, and Office documents into Markdown or JSON, while gptpdf converts PDFs into Markdown using a vision-capable model. The main difference is that text-extract-api offers a self-hostable API and multiple OCR workflows, whereas gptpdf is a PDF parsing library that relies on a compatible model API.
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.
gptpdf: Convert PDFs into Markdown with Vision Models
gptpdf turns PDF pages into Markdown using a vision-capable model, aiming to preserve layouts such as tables, formulas, and figures. It suits developers who need an API-based PDF parsing component and can provide access to a compatible model.
| text-extract-api | gptpdf | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 3.2k | 3.6k |
| Forks | 279 | 261 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- text-extract-api handles PDFs, images, and Office documents; gptpdf focuses on PDFs.
- text-extract-api can produce Markdown or structured JSON; gptpdf converts PDFs into Markdown and returns paths to extracted images.
- text-extract-api offers OCR strategies and optional Ollama processing; gptpdf sends page content to a multimodal model through an OpenAI-compatible API.
- text-extract-api is designed to run in an organization's environment, while gptpdf requires access to a compatible model API and may incur per-page costs.
- text-extract-api includes asynchronous processing, OCR-result caching, and configurable storage profiles; gptpdf offers configurable worker threads for model parsing.
- Both projects are written in Python and use the MIT license.
Choose text-extract-api if you…
- need to process images or Office documents as well as PDFs.
- want a self-hostable service with OCR options, optional Ollama processing, and Markdown or JSON output.
- need asynchronous tasks, caching, or configurable result storage for document workflows.
Choose gptpdf if you…
- need a PDF parsing library that converts pages to Markdown and returns paths to extracted images.
- want model-based interpretation of visually complex PDF content through an OpenAI-compatible API.
- can configure access to a compatible multimodal model and accept potential per-page costs.
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.