README.md

metadata

title: ALDDS
emoji: 💻
colorFrom: indigo
colorTo: red
sdk: gradio
sdk_version: 6.14.0
python_version: '3.13'
app_file: app.py
pinned: false

⚖️ Automated Legal Document Digitization System (ALDDS)

Upload a photo of a legal document (bailable warrant, summon, etc.) and seamlessly convert it into structured JSON data. ALDDS handles the OCR, AI parsing, secure storage, and live dispatcher notifications in a single streamlined pipeline.

🚀 Pipeline & Architecture

Image Upload → Cloudinary Hosting → Tesseract OCR → NVIDIA LLMs → MongoDB → WhatsApp Alert

1. OCR Extraction: Uses Tesseract to extract raw text from image uploads.
2. AI Parsing: Leverages advanced NVIDIA models (qwen/qwen3-coder-480b-a35b-instruct, Llama 3) to parse the unstructured OCR text into a strict 10-field JSON schema.
3. Secure Storage: Automatically commits the digital record to a MongoDB database.
4. Live Dashboard: A real-time, searchable Police Dashboard built directly into the UI.
5. Instant Notifications: Dispatchers can notify Investigating Officers (IOs) instantly via zero-cost WhatsApp wa.me links populated from an internal CSV database.

---

📋 Features

• Multi-Model Fallback: The app cycles through a priority list of NVIDIA LLMs ensuring maximum uptime and reliability during the parsing phase.
• 👮 Live Police Dashboard: A dedicated tab for station dispatchers to monitor incoming warrants. Includes a real-time MongoDB search filter (by Case No, IO Name, Station, etc.).
• 💬 WhatsApp Integration: Zero-API-cost notifications. Selecting an officer from the dropdown dynamically pulls their phone number from officers.csv and opens a pre-filled WhatsApp window for the dispatcher to send manually.

---

🔑 Environment Setup

To run ALDDS locally or in the cloud, you need the following API keys configured in a .env file (or as Secrets on Hugging Face).

# Cloudinary (Image Hosting)
CLOUDINARY_CLOUD_NAME=your_cloud_name
CLOUDINARY_API_KEY=your_api_key
CLOUDINARY_API_SECRET=your_api_secret

# NVIDIA API (LLM Parsing)
NVIDIA_API_KEY=your_nvidia_api_key

# MongoDB (Database)
MONGODB_URI=mongodb+srv://username:password@cluster0.../?retryWrites=true&w=majority

Variable	Where to get it
CLOUDINARY_*	Cloudinary Console → Dashboard
NVIDIA_API_KEY	NVIDIA Build → API Catalog → Get API Key
MONGODB_URI	MongoDB Atlas → Database → Connect

---

💻 Local Installation Guide

1. Install Tesseract OCR (System Binary)

Python's pytesseract requires the underlying Tesseract engine to be installed on your OS.

Windows

1. Download installer from: https://github.com/UB-Mannheim/tesseract/wiki
2. Run installer (default path: C:\Program Files\Tesseract-OCR\)
3. The app is hardcoded to look for this path on Windows.

Linux (Debian/Ubuntu)

sudo apt-get update
sudo apt-get install tesseract-ocr

macOS

brew install tesseract

2. Run the App

# Clone repository
git clone https://huggingface.co/spaces/LovnishVerma/ALDDS
cd ALDDS

# Install Dependencies
pip install -r requirements.txt

# Run the Server
python app.py

The interface will launch at http://127.0.0.1:7860.

---

☁️ Hugging Face Spaces Deployment

If you are deploying ALDDS to Hugging Face Spaces, follow these critical steps:

1. Set Up Secrets: Go to your Space Settings -> Variables and secrets. Add all variables from your .env file as Secrets.
2. System Dependencies: Hugging Face runs Debian Linux. The repository includes a packages.txt file telling Hugging Face to install tesseract-ocr and libtesseract-dev during the Docker build.
3. CRLF Warning: Ensure that packages.txt is saved with Unix (LF) line endings. If it has Windows (CRLF) line endings, the Hugging Face Docker build will fail with a Package not found error.
4. Restart: Always click Restart Space after adding or modifying Secrets so the new environment variables are loaded into the container.

---

📊 Extracted JSON Schema

The LLM is strictly prompted to extract the following fields. If a field cannot be found, it defaults to null.

JSON Key	Description
Case_FIR_Number	FIR or court case reference number
Act_and_Sections	Applicable IPC/CRPC legal acts and sections
Type_of_Document	Warrant, summon, notice, etc.
Target_Police_Station	Police station the document is addressed to
IO_Name_and_Belt_No	Investigating Officer's name and belt number
IO_Mobile_Number	IO's contact number
Person_Name_To_Serve	Name of the person to be served/arrested
Person_Address	Address of the target person
Court_Name	Issuing court name
Hearing_Date	Scheduled hearing or appearance date (DD-MM-YYYY)

---

Built to streamline station workflows, eliminate manual data entry, and instantly notify field officers.