# CatchTheTornado/text-extract-api

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

Repository: https://github.com/CatchTheTornado/text-extract-api
Canonical: https://ross.abutalabs.com/products/text-extract-api
Homepage: https://demo.doctractor.com
Language: Python
License: MIT
License Family: permissive
Topics: api, extract, json, llm, pdf, anonymization, ocr, ocr-python, pii
Last push: 2025-12-08T21:27:14+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 56, release rhythm 28, longevity 48
- inputs: {"age_days": 679, "days_push": 268, "days_rel": 492, "gap_med": 51.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3175, forks 279 (observed 2026-08-28T04:07:47.565676+00:00)

## What it is
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
- artifact type: service
- maturity: active
- function: ocr, pdf, llm-inference, api-framework, caching, privacy, nlp
- domain: pdf, privacy, developer-tools, large-language-models, self-hosted
- platform: self-hosted, python, cli
- tags: document-parsing, pii-removal, anonymization, markdown-conversion, easyocr, ollama, fastapi, celery, structured-extraction, ocr, docker, web-server

## Member repositories
- CatchTheTornado/text-extract-api (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.565676+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 2026-08-29T18:45:25.237035+00:00, confidence not recorded.
  - readme: https://github.com/CatchTheTornado/text-extract-api (fetched 2026-08-28T04:07:47.565676+00:00, sha 7eb042cbae2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.