Upload 5 files

.env.example

@@ -8,7 +8,3 @@ NVIDIA_API_KEY=your_nvidia_api_key
 
 # MongoDB
 MONGODB_URI=mongodb+srv://username:password@cluster0.sxci1.mongodb.net/?retryWrites=true&w=majority
-
-# Telegram API
-TELEGRAM_BOT_TOKEN=your_bot_token_here
-TELEGRAM_GROUP_ID=your_group_chat_id_here

README.md

@@ -1,139 +1,135 @@
----
-title: ALDDS
-emoji: 💻
-colorFrom: purple
-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)
-
-![Python](https://img.shields.io/badge/Python-3.13-blue.svg)
-![Gradio](https://img.shields.io/badge/Gradio-6.14.0-orange.svg)
-![MongoDB](https://img.shields.io/badge/MongoDB-Atlas-green.svg)
-![Hugging Face](https://img.shields.io/badge/Deploy-Hugging%20Face-yellow.svg)
-
-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
-
-```text
-Image Upload → Cloudinary Hosting → Tesseract OCR → NVIDIA LLMs → MongoDB → Telegram IO 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 ping Investigating Officers (IOs) via Telegram with the parsed data using a secure Frontend JavaScript bypass.
-
----
-
-## 📋 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.).
-- **📨 Frontend JS Telegram Alerts**: Send an automated markdown summary and document link to an IO via Telegram. The request executes directly in the browser using JavaScript to bypass restrictive institutional or cloud IP firewalls (like Hugging Face).
-
----
-
-## 🔑 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).
-
-```env
-# 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
-
-# Telegram (IO Notifications)
-TELEGRAM_BOT_TOKEN=your_bot_token_here
-```
-
-| Variable | Where to get it |
-|---|---|
-| `CLOUDINARY_*` | [Cloudinary Console](https://console.cloudinary.com/) → Dashboard |
-| `NVIDIA_API_KEY` | [NVIDIA Build](https://build.nvidia.com/) → API Catalog → Get API Key |
-| `MONGODB_URI` | [MongoDB Atlas](https://www.mongodb.com/cloud/atlas) → Database → Connect |
-| `TELEGRAM_BOT_TOKEN` | [Telegram](https://core.telegram.org/bots) → @BotFather |
-
----
-
-## 💻 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)**
-```bash
-sudo apt-get update
-sudo apt-get install tesseract-ocr
-```
-
-**macOS**
-```bash
-brew install tesseract
-```
-
-### 2. Run the App
-```bash
-# 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.*
+---
+title: ALDDS
+emoji: 💻
+colorFrom: purple
+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)
+
+![Python](https://img.shields.io/badge/Python-3.13-blue.svg)
+![Gradio](https://img.shields.io/badge/Gradio-6.14.0-orange.svg)
+![MongoDB](https://img.shields.io/badge/MongoDB-Atlas-green.svg)
+![Hugging Face](https://img.shields.io/badge/Deploy-Hugging%20Face-yellow.svg)
+
+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
+
+```text
+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).
+
+```env
+# 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](https://console.cloudinary.com/) → Dashboard |
+| `NVIDIA_API_KEY` | [NVIDIA Build](https://build.nvidia.com/) → API Catalog → Get API Key |
+| `MONGODB_URI` | [MongoDB Atlas](https://www.mongodb.com/cloud/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)**
+```bash
+sudo apt-get update
+sudo apt-get install tesseract-ocr
+```
+
+**macOS**
+```bash
+brew install tesseract
+```
+
+### 2. Run the App
+```bash
+# 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.*

app.py

@@ -14,6 +14,7 @@ import re
 import json
 import concurrent.futures
 import requests
+import csv
 
 import gradio as gr
 import cloudinary
@@ -65,6 +66,15 @@ if mongo_uri:
         print(f"❌ MongoDB connection failed: {exc}")
         collection = None
 
+# Load Officers Database
+officers_db = {}
+try:
+    with open("officers.csv", "r", encoding="utf-8") as f:
+        reader = csv.DictReader(f)
+        for row in reader:
+            officers_db[row["Officer_Name"]] = row["Phone_Number"]
+except Exception as e:
+    print(f"⚠️ Could not load officers.csv: {e}")
 
 # ──────────────────────────────────────────────
 # B.  Core Processing Logic
@@ -608,13 +618,17 @@ with gr.Blocks(
                 raw_ocr_out          = gr.Textbox(label="🔍 Raw OCR Text", lines=8, interactive=False)
                 json_out             = gr.JSON(label="📋 Extracted Structured Data (JSON)")
 
-                gr.Markdown("### 📨 Notify Investigating Officer")
+                gr.Markdown("### 📨 Notify Investigating Officer (WhatsApp)")
                 with gr.Row():
-                    manual_id_in = gr.Textbox(label="Telegram Chat ID", placeholder="Enter ID here...", scale=3)
-                    send_alert_btn = gr.Button("🚨 Send Telegram Alert", variant="secondary", scale=1)
-                alert_status_out = gr.HTML()
+                    io_dropdown = gr.Dropdown(label="Select Officer (from CSV)", choices=list(officers_db.keys()), scale=2)
+                    manual_phone_in = gr.Textbox(label="WhatsApp Mobile No.", placeholder="e.g. 919876543210", scale=2)
+                    send_wa_btn = gr.Button("💬 Send via WhatsApp", variant="secondary", scale=1)
+                wa_status_out = gr.HTML()
                 
-                bot_token_hidden = gr.Textbox(value=os.environ.get("TELEGRAM_BOT_TOKEN", ""), visible=False)
+                # Auto-fill phone when IO selected
+                def update_phone(officer_name):
+                    return officers_db.get(officer_name, "")
+                io_dropdown.change(fn=update_phone, inputs=[io_dropdown], outputs=[manual_phone_in])
 
             def _make_status_html(icon, message, color):
                 return (
@@ -662,45 +676,32 @@ with gr.Blocks(
                 outputs=[status_out, cloudinary_url_out, cloudinary_link_html, raw_ocr_out, json_out],
             )
 
-            js_code = """
-            async (chat_id, url, data, bot_token) => {
-                if (!chat_id) return "❌ Please enter a Chat ID.";
+            js_code_wa = """
+            (phone, url, data) => {
+                if (!phone) return "❌ Please enter a WhatsApp number.";
                 if (!url) return "❌ No document uploaded yet.";
-                if (!bot_token) return "❌ Bot token not configured in .env";
                 
                 let case_no = data && data["Case_FIR_Number"] ? data["Case_FIR_Number"] : "Unknown Case";
                 let court = data && data["Court_Name"] ? data["Court_Name"] : "Unknown Court";
                 
                 let text = `🚨 *New Warrant Uploaded*\\n*Case:* ${case_no}\\n*Court:* ${court}\\n*Document:* ${url}`;
-                let api_url = `https://api.telegram.org/bot${bot_token}/sendMessage`;
+                let encoded_text = encodeURIComponent(text);
                 
-                try {
-                    let res = await fetch(api_url, {
-                        method: "POST",
-                        headers: { "Content-Type": "application/json" },
-                        body: JSON.stringify({
-                            chat_id: chat_id.trim(),
-                            text: text,
-                            parse_mode: "Markdown"
-                        })
-                    });
-                    let out = await res.json();
-                    if (out.ok) {
-                        return `✅ Alert sent successfully to ${chat_id}!`;
-                    } else {
-                        return `❌ Failed: ${out.description}`;
-                    }
-                } catch (e) {
-                    return `❌ Error connecting to Telegram: ${e.message}`;
-                }
+                let clean_phone = phone.replace(/[^0-9]/g, '');
+                if (!clean_phone) return "❌ Invalid phone number.";
+                
+                let wa_url = `https://wa.me/${clean_phone}?text=${encoded_text}`;
+                window.open(wa_url, '_blank');
+                
+                return `✅ WhatsApp opened for ${phone}! Click Send in WhatsApp.`;
             }
             """
 
-            send_alert_btn.click(
+            send_wa_btn.click(
                 fn=None,
-                inputs=[manual_id_in, cloudinary_url_out, json_out, bot_token_hidden],
-                outputs=[alert_status_out],
-                js=js_code
+                inputs=[manual_phone_in, cloudinary_url_out, json_out],
+                outputs=[wa_status_out],
+                js=js_code_wa
             )
 
         with gr.Tab("👮 Live Police Dashboard"):

officers.csv

@@ -0,0 +1,6 @@
+Officer_Name,Phone_Number
+Insp. Lovnish Verma (101),+918894869371
+SI Amit Singh (102),+919876543211
+ASI Vikram Sharma (103),+919876543212
+HC Ramesh Chand (104),+919876543213
+SI Vikas Kumar (105),+919876543214

test_network.py

@@ -0,0 +1,12 @@
+import requests
+
+try:
+    print("Testing basic internet access...")
+    google_check = requests.get("https://www.google.com", timeout=10)
+    print(f"Google status: {google_check.status_code}")
+    
+    print("Testing Telegram endpoint access...")
+    telegram_check = requests.get("https://api.telegram.org", timeout=10)
+    print(f"Telegram status: {telegram_check.status_code}")
+except Exception as e:
+    print(f"❌ Network blocked: {e}")