CatchTheTornado/text-extract-api

Health v2 · maintenance only

Adoption not part of the score

3175 stars · 279 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A self-hosted FastAPI-based API that converts PDFs, Office documents, and images into Markdown or structured JSON using OCR engines (EasyOCR, marker-pdf) and Ollama LLM models. It also supports PII removal/anonymization, Redis caching of OCR results, and asynchronous processing via Celery.

Use cases

• convert pdf to markdown
• extract structured json from invoices
• remove pii from documents
• ocr scanned documents locally
• parse word and pptx files to text
• anonymize documents before sharing
• improve ocr results with an llm

When to choose

• you need self-hosted document extraction with no cloud dependencies
• you want LLM-enhanced OCR with structured JSON output
• you need PII removal or document anonymization
• you process many documents and want async queue processing with caching

When to avoid

• you only need simple text extraction without OCR or LLM overhead
• you cannot run Ollama models or lack suitable hardware
• you need a fully managed cloud document API
• you need Apple GPU support via Docker, which is not supported

Facets

service · maturity active

ocr pdf llm-inference api-framework caching privacy nlp pdf privacy developer-tools large-language-models self-hosted self-hosted python cli document-parsing pii-removal anonymization markdown-conversion easyocr ollama fastapi celery structured-extraction ocr docker web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="CatchTheTornado/text-extract-api")