Escruta - Extractor

Caution

This repository has been deprecated. Its functionality has been merged into the unified Helper service.

Dedicated microservice for document parsing and content extraction within the Escruta platform. Converts various file formats (PDF, DOCX, PPTX, XLSX, audio, and YouTube URLs) into clean Markdown for AI processing.

Built with Python, FastAPI, and MarkItDown.

Note

This service is no longer part of the active Escruta ecosystem. Document extraction is now provided by Helper (POST /extract). This repository is kept for archival purposes only.

Getting Started (legacy)

Warning

The instructions below only apply if you are running this service for historical or development purposes. New deployments should use the Helper service instead.

1. uv sync - Install dependencies
2. uv run --env-file .env fastapi run --port 8000 - Start the development server

The extraction service will be available at localhost:8000.

Configuration

Environment Variables

The application is secured and configured using environment variables. These must be set in your .env file or environment.

Variable	Description	Default
ESCRUTA_INTERNAL_API_KEY	Internal API Key for service-to-service communication	(Required)