Document Requirement Processor

This application processes documents using Docling and PydanticAI to identify and extract requirements from policy documents.

Setup

1. Install dependencies using UV:

# Create and activate a virtual environment
uv venv
source .venv/bin/activate  # On Unix/macOS
# or
.venv\Scripts\activate  # On Windows

# Install the project in editable mode (-e)
# This allows you to modify the code without reinstalling
uv install -e .

2. Create a .env file in the root directory and add your Anthropic API key:

ANTHROPIC_API_KEY=your_api_key_here

3. Place your policy documents in the policy-documents directory.

Usage

Run the application:

uv run src/main.py

The application will:

1. Load all documents from the policy-documents directory
2. Process each document to identify requirements
3. Save identified requirements to requirement-output.json

Output

Requirements are saved in JSON format with the following structure:

{
  "id": "REQ-001",
  "text": "The actual requirement text",
  "type": "functional|non-functional|security|performance",
  "priority": "high|medium|low",
  "dependencies": ["REQ-X", "REQ-Y"]
}