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
Why this job: works in the areas we cover, but does not say which job it does
What it does
- No Cloud/external dependencies all you need. PyTorch based OCR (EasyOCR) + Ollama are shipped and configured via docker-compose no data is sent outside your dev/server environment,
- PDF/Office to Markdown conversion with very high accuracy using different OCR strategies including llama3.2-vision, easyOCR, minicpm-v, remote URL strategies including marker-pdf
- PDF/Office to JSON conversion using Ollama supported models (eg. LLama 3.1)
- LLM Improving OCR results LLama is pretty good with fixing spelling and text issues in the OCR text
- Removing PII This tool can be used for removing Personally Identifiable Information out of document - see examples
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 11 months ago
- Stars
- 3,197
- +9 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3.0
- Released 18 months ago
- Built with
- Python
- 88% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 43% closed
- 47 still open
- Pull requests
- 35 merged
- 2 waiting
- Releases
- 3
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Rizzo-AI-Academy / rizzo-pii | 1,265 | 21 days ago | MIT | Mac, Windows, Linux |
| danyuchn / pii-guard | 255 | 18 days ago | MIT | No downloads |
| qiaohaoforever / DeepLearningFromScratch | 1,303 | 11 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 88%
- Makefile 6%
- Shell 4%
- Dockerfile 3%
Topics
- api
- extract
- json
- llm
- anonymization
- ocr
- ocr-python
- pii
Project record
- JobOther AI tools
- StatusListed
- Commits251
- Forks280
- Watching14
- Stars in 28 days+17
- CreatedOct 23, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026