This is a rapid prototype for an AI-powered tool that analyzes legal contracts for risky clauses using keyword-based detection.
- Upload contracts in PDF, DOCX, or TXT format
- Extracts text (with OCR for scanned PDFs)
- Identifies and highlights risky clauses (High, Medium, Low risk)
- Simple, interactive dashboard (Streamlit UI)
- Install dependencies:
pip install -r requirements.txt
- (Optional) For OCR, install Tesseract:
- Windows: Download from https://github.com/tesseract-ocr/tesseract
- Linux:
sudo apt-get install tesseract-ocr
- Start the app:
streamlit run app/main.py
app/main.py- Streamlit UIapp/analyzer.py- Clause extraction & risk analysisapp/file_utils.py- File upload & text extractionapp/risk_keywords.py- Risk keyword lists