Back to Projects
Completed Project

PRANAG AI – Web Platform

End-to-end AI livestock management platform with Prompt Parser, PINN models, prediction services, and connected dashboards. Built responsive React frontend, scalable FastAPI backend with RESTful APIs, and structured PostgreSQL database architecture from scratch. Includes auth, data management modules, and deployment-ready scalable architecture.

|
PRANAG AI – Web Platform
RoleFull Stack & AI Systems Architect
TimelineApr 2026 - Jun 2026
TeamInternship Project / R&D Team
Tech Stack8 Technologies

Mission Brief

PRANAG AI Web Platform is a comprehensive livestock health analytics and disease intelligence platform. It features an advanced natural language Prompt Parser, Physics-Informed Neural Network (PINN) models for bovine metabolic tracking, and real-time disease risk forecasting dashboards. Built from the ground up with a responsive React.js frontend, an asynchronous FastAPI REST backend, and PostgreSQL with optimized relational schemas. The system empowers veterinarians and dairy farm managers with predictive cattle health insights.

Key Features

AI & Physics-Informed Neural Networks

  • Prompt Parser: Natural language query engine translating clinical vet inquiries into structured telemetry filters
  • PINN Cattle Models: Physics-Informed Neural Networks modeling bovine metabolic trajectories and feed efficiency
  • Disease Risk Matrix: Multi-factor epidemiological risk scoring for early herd outbreak warnings

Backend & Database Architecture

  • FastAPI Microservices: Asynchronous non-blocking Python backend delivering sub-40ms API responses
  • PostgreSQL Schema: Optimized relational schema for millions of telemetry time-series and diagnostic records
  • JWT Authentication: Role-based security tiers separating Veterinarians, Farm Managers, and Field Staff

Frontend & Visualization

  • Real-Time Dashboards: Interactive Chart.js and Tailwind dashboards for biometric telemetry
  • Export & Reports: Instant PDF and CSV clinical diagnostic report generation
  • Responsive UI: Fully fluid layout adapting seamlessly across tablets and workstations

Engineering Chronicles

High latency when computing complex Physics-Informed Neural Network (PINN) inference queries on large herd datasets.

SolutionDesigned an asynchronous task queue with background model workers and Redis caching for recurring parameter lookups, reducing response latency by 72%.

Complex multi-tenant permissions needed across dairy farms, research institutions, and visiting veterinarians.

SolutionImplemented hierarchical Role-Based Access Control (RBAC) in FastAPI middleware with granular scoped JWT claims and PostgreSQL row-level indexing.

Installation Instructions

1. Clone the repository and setup environment
$git clone https://github.com/KartikSharma4448/pranag-ai-web.git
$cd pranag-ai-web
2. Backend Setup (FastAPI)
$cd backend
$python -m venv venv
$source venv/bin/activate # Or venv\Scripts\activate on Windows
$pip install -r requirements.txt
$uvicorn app.main:app --reload --port 8000
3. Frontend Setup (React)
$cd frontend
$npm install
$npm run dev

Project Access

Live DemoSource Code

Technologies

React.js
FastAPI
PostgreSQL
Python
TensorFlow
PINN Models
Tailwind CSS
REST API

Table of Contents

  • • Mission Brief
  • • Key Features
  • • Engineering Chronicles
  • • Visual Gallery
  • • Installation Instructions
Back to Projects

More Projects

AI Livestock Diagnostic Mobile App
Completed

AI Livestock Diagnostic Mobile App

Flutter • Mobile & On-Device AI

VCC ERP – Coaching Institute Management
Completed

VCC ERP – Coaching Institute Management

Flutter 3.41 • Full Stack & ERP Ecosystem

Rajasthali – Travel & Fleet Management System
Completed

Rajasthali – Travel & Fleet Management System

Flutter 3.7+ • Fleet & Mobile Logistics

CVCraft v2 – AI-Powered ATS Resume Builder
Completed

CVCraft v2 – AI-Powered ATS Resume Builder

FastAPI • AI & Full Stack Web App

Aegis Care – Blockchain Healthcare System
Completed

Aegis Care – Blockchain Healthcare System

Algorand • Web3 & Blockchain