Skip to content

An AI-powered tabular review tool for legal professionals. Ingest unstructured documents, define dynamic extraction columns, and query your data with an integrated analyst chat.

License

Notifications You must be signed in to change notification settings

jamietso/Tabular_Review

Repository files navigation

Tabular Review for Bulk Document Analysis

License React AI

An AI-powered document review workspace that transforms unstructured legal contracts into structured, queryable datasets. Designed for legal professionals, auditors, and procurement teams to accelerate due diligence and contract analysis.

🚀 Features

  • AI-Powered Extraction: Automatically extract key clauses, dates, amounts, and entities from PDFs using Google Gemini 2.5 Pro / 3.0.
  • High-Fidelity Conversion: Uses Docling (running locally) to convert PDFs and DOCX files to clean Markdown text, preserving formatting and structure without hallucination.
  • Dynamic Schema: Define columns with natural language prompts (e.g., "What is the governing law?").
  • Verification & Citations: Click any extracted cell to view the exact source quote highlighted in the original document.
  • Spreadsheet Interface: A high-density, Excel-like grid for managing bulk document reviews.
  • Integrated Chat Analyst: Ask questions across your entire dataset (e.g., "Which contract has the most favorable MFN clause?").

🎬 Demo

TabularReview.Final.mp4

🛠 Tech Stack

  • Frontend: React 19, TypeScript, Tailwind CSS
  • AI Integration: Google GenAI SDK (Gemini 2.5 Flash, 2.5 Pro, 3.0 Pro)

📦 Getting Started

1. Clone the repository

git clone https://github.com/yourusername/tabular-review.git
cd tabular-review

2. Setup Frontend

Install Node dependencies:

pnpm install

Create a .env.local file in the root directory for your Google API Key:

VITE_GEMINI_API_KEY=your_google_api_key_here

3. Setup Backend (Docling)

The backend is required for document conversion.

cd server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

4. Run

Start the backend (in one terminal):

cd server
source venv/bin/activate
python main.py

Start the frontend (in another terminal):

pnpm dev

🐳 Docker Deployment (Alternative)

You can also run the application using Docker:

  1. Setup environment:

    cp .env.example .env
    # Edit .env and add your Google Gemini API key
  2. Build and run with Docker:

    docker-compose up --build
  3. Access the application:

The Docker setup includes:

  • Frontend: React app served by Node.js static server
  • Backend: FastAPI with Docling document processing
  • Simple networking: Services communicate via Docker network

🛡 License

This project is licensed under the MIT License - see the LICENSE file for details.


Disclaimer: This tool is an AI assistant and should not be used as a substitute for professional legal advice. Always verify AI-generated results against the original documents.

About

An AI-powered tabular review tool for legal professionals. Ingest unstructured documents, define dynamic extraction columns, and query your data with an integrated analyst chat.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published