🌱 Building Full-Stack Applications • 💡 AI Systems & Search Technologies • 🤝 Open Source Contributor
- 💼 Software Developer passionate about building scalable and user-focused applications
- 🤖 Exploring Generative AI, LLMs, RAG Pipelines, and AI Voice Agents
- 🔍 Apache Lucene.NET Committer working on search, indexing, and performance improvements
- 🌐 Building modern applications using Angular, React, ASP.NET Core, and Python
- 📚 Currently learning production-grade AI architecture and distributed systems
- 🤝 Love contributing to Open Source and solving real-world engineering problems
📫 Email: pathannehan28@gmail.com
🌍 Portfolio: https://nehan-portfolio.netlify.app
- 🏅 Apache Lucene.NET Committer
- 🌟 Google Summer of Code 2025 Contributor
- 🚀 Contributed to Apache Lucene.NET with search, replication, and performance improvements
- 🌱 Successfully completed Hacktoberfest 2024
- 🏆 Building production-ready AI applications using modern LLM technologies
An AI-powered full-stack application that transforms uploaded photos into cinematic memory cards and digital keepsakes.
Highlights:
- 📸 Multi-photo upload with real-time progress tracking
- 🎬 AI-generated cinematic memory cards using OpenAI GPT-4o
- 🎨 Multiple storytelling themes (Nostalgic, Travel, Family)
- ⚡ Real-time streaming updates with Server-Sent Events
- 📱 Responsive React UI with dark mode
- 🔒 Production-ready architecture with FastAPI & PostgreSQL
Tech Stack: React 19, TypeScript, FastAPI, OpenAI GPT-4o, PostgreSQL, ImageKit, Tailwind CSS
Repository: https://github.com/NehanPathan/MemoraAi
An enterprise-grade Retrieval-Augmented Generation (RAG) platform designed for scalable, production-ready AI applications.
Highlights:
- 🔍 Hybrid Search (Vector + BM25)
- ⚖️ Reciprocal Rank Fusion (RRF) & Intelligent Reranking
- 🧠 Semantic Caching & Context Compression
- 📚 Citation Tracking & Streaming Responses
- 🏗️ Clean Architecture with Domain-Driven Design (DDD)
- 🚀 Optimized for large-scale document retrieval
Repository: https://github.com/NehanPathan/RAG-Pipeline-Production-Level-
Apache Lucene.NET Committer contributing to one of the world's leading search libraries by improving performance and search capabilities.
Highlights:
- 🚀 Search Performance Optimizations
- 📖 Smart Chinese Analyzer (SmartCN) Improvements
- ⚡ Dictionary Loading Enhancements
- 🔄 Replication Framework Contributions
- 🌐 ASP.NET Core Integration
- ✅ Unit Testing & Performance Improvements
Repositories:
Working with
- Large Language Models (LLMs)
- Retrieval-Augmented Generation (RAG)
- AI Agents
- Vector Databases
- Prompt Engineering
- Semantic Search
- AI Automation
https://linkedin.com/in/Nehan-Khan-Pathan
🌐 Portfolio
https://nehan-portfolio.netlify.app
🏅 Holopin
https://holopin.me/nehanpathan
⭐ Building software that combines Search, AI, and Open Source to solve real-world problems.