double-k-3033/Legal-AI-project
The Automated Legal Document Analysis Platform is a powerful web application that automates the laborious process of analyzing legal documents. By leveraging cutting-edge technologies such as Next.js, NLP, and machine learning models, our platform extracts relevant information and identifies potential risks from legal documents.
The platform combines a Next.js frontend with a Flask backend serving PyTorch-based NLP models, including a SQuAD-trained reading comprehension model, a T5-based paraphrasing engine, and TextBlob sentiment analysis to surface clause-level risk insights. It trains on a custom 500-contract CUAD dataset targeting lawyer-relevant question patterns, then containerizes the full stack with Docker Compose for simplified deployment. The architecture decouples the UI from ML inference, allowing independent scaling of the web interface and model serving layers.
Stars
28
Forks
1
Language
TypeScript
License
—
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/double-k-3033/Legal-AI-project"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.