Muhammad Noman Ijaz
AWS Cloud Developer & MERN Stack Full-Stack Developer
New to Contra
Muhammad Noman is ready for their next project!
Noman Portfolio
0
7
☁️✨ Introducing Conflux Weather App — Your Gateway to Real-Time Weather Insights! ✨🌍
I recently built Conflux Weather App, a modern and responsive web application designed to deliver accurate weather updates with a smooth user experience.
🚀 Tech Stack Highlights:
🌐 Frontend: JavaScript, HTML, CSS
⚙️ Backend: Express.js
🔗 API: OpenWeather for real-time data
🌎 Deployment: Vercel
💡 What It Offers:
✔️ Search weather by city or auto-detect location
✔️ Live updates on temperature, humidity, and wind speed
✔️ Clean and responsive design for mobile & desktop
✔️ Seamless frontend–backend integration
This project was a great step in strengthening my full-stack development skills, especially in API integration and backend development with Express.js.
I’d love to hear your thoughts, suggestions, or ideas for future improvements! 🙌
0
11
Conflux – Frontend Design Showcase (MERN Stack Web Application)
I’m pleased to share the frontend design of Conflux, a real-time communication web application built using the MERN stack, with an integrated AI assistant named Conflux AI.
This stage of the project is focused exclusively on frontend architecture, UI/UX design, and component structuring. The objective is to establish a scalable, intuitive, and production-ready interface before initiating backend development.
🔹 Frontend Design Highlights
Clean and modern real-time chat interface optimized for desktop web
Structured conversation list with user previews and timestamps
Dedicated AI assistant interface (Conflux AI) designed for future intelligent interactions
Dark-themed, professional UI for enhanced usability and focus
Modular and reusable React components prepared for backend integration
Responsive layout ensuring consistency across screen sizes
⚠️ Current Status:
All features shown are part of the frontend design layer only. Messaging, authentication, and AI responses are currently represented at the UI level.
🔹 Upcoming Development (Backend – Step by Step)
Secure user authentication (login & registration)
Messaging between registered users
Real-time communication using Socket.io
(http://Socket.io)Database integration with MongoDB
AI-powered features via Conflux AI
Voice and video calling functionality
This design-first approach ensures a strong technical foundation, allowing backend features to be integrated efficiently and at scale.
Looking forward to transforming Conflux into a fully functional, real-time communication platform.
Feedback, suggestions, and professional connections are always welcome.
0
11
Conflux AI is a full-stack intelligent chatbot built with Python FastAPI backend and a custom vanilla HTML/CSS/JS frontend — designed to feel like a conversation with someone who actually listens.
AI & Models: Groq API runs LLaMA 3.1 8B for fast responses and LLaMA 3.3 70B for complex reasoning. Google Gemini 2.0 Flash handles image analysis via REST API with automatic fallback to Gemini 1.5 Flash and 1.5 Pro.
Agent Layer: LangChain + LangGraph power ReAct agents that decide whether to search the web, read a document, or answer from memory before responding.
Real-Time Data: A custom Apify service delivers live news, crypto prices, and trending topics — bypassing the LLM entirely for fresh, hallucination-free data.
Document & Image Intelligence: PDFs are ingested via PyPDFLoader with auto-summarization. Images can be uploaded, attached, or pasted from clipboard and analyzed through Gemini Vision. ReportLab generates downloadable PDF exports of any response.
Auth: Firebase Admin SDK verifies JWT tokens server-side with full Google and email sign-in support.
Frontend: Three-panel dark UI with a complete CSS animation system — messages fade up on entry, AI responses render character-by-character via a custom typewriter engine, and dynamic follow-up suggestions update after every response with staggered cascade animations.
Emotional Intelligence: A fully custom keyword-based engine detects 10+ emotions in real-time — happy, sad, anxious, angry, curious, and more — adapting the AI's tone, language, and empathy level with every single message. Mood history is tracked per authenticated user with trend analytics.
Stack: FastAPI · LangChain · LangGraph · Groq · Gemini · Firebase · Apify · ReportLab · highlight.js · Vanilla JS
Conflux AI v5.1 — Built by Muhammad Noman Ijaz, Lead Engineer at Conflux. March 2026.
0
14