AI Application Development Projects in LahoreAI Application Development Projects in Lahore
Projects
People
Cover image for SnapAI is a mobile-first AI
SnapAI is a mobile-first AI photo and video editing application designed for users who want studio-quality content without complex editing skills. Built for both iOS and Android, the platform combines powerful AI-driven editing tools into a clean, fast, and modern experience tailored for social media creators. The app allows users to retouch selfies, generate AI avatars, apply age and gender transformations, remove or replace backgrounds, and edit short-form videos directly from a single dashboard. We designed an intuitive editing workflow with real-time previews, adjustable intensity controls, before/after comparisons, AI effect panels, beat-sync video editing, and seamless sharing to platforms like Instagram, TikTok, and WhatsApp. The design system focuses on a premium dark-space aesthetic inspired by modern creator tools such as Lensa and CapCut, using neon violet and coral gradients to create a futuristic yet minimal interface. A freemium monetization model was also integrated, including daily credits, watermark restrictions, and a Pro subscription flow with Apple Pay and Google Pay support. SnapAI was designed as a high-performance MVP with a strong focus on usability, speed, and creator engagement.
0
45
Cover image for French Legal AI Assistant &
French Legal AI Assistant & Agentic RAG System Overview I designed, built, and deployed a specialized Legal AI Assistant for French lawyers using agentic RAG, legal data pipelines, vector search, reranking, open-source LLMs, and citation-grounded answer generation. The system allowed lawyers to ask legal questions and receive answers grounded in French law articles, legal references, and relevant judicial cases. Problem / Challenge Legal data is very different from normal document data. A generic RAG pipeline using fixed-size chunks often breaks legal meaning, misses important context, or retrieves incomplete references. The main challenges were: 🔹 Legal documents had different structures and lengths 🔹 Articles and laws could not be randomly split into fixed-size chunks 🔹 Each answer needed traceable legal references 🔹 Retrieval had to understand legal scope, not just semantic similarity 🔹 The system needed to reduce hallucinations for legal users 🔹 Deployment had to respect privacy and regulatory requirements My Expertise I worked as the Lead AI Engineer / Agentic RAG Developer responsible for the complete system design and implementation. My responsibilities included: 🔹 Legal data pipeline architecture 🔹 Document parsing and preprocessing 🔹 Custom legal chunking strategy 🔹 Vector database design 🔹 Agentic RAG workflow development 🔹 Retrieval optimization and reranking 🔹 Open-source LLM deployment 🔹 Backend API development with FastAPI 🔹 Secure Azure cloud deployment 🔹 Multi-tenant system support French Legal Data Engineering Pipeline I built an automated ETL pipeline to process thousands of French legal documents, articles, and judicial cases. The pipeline handled: 🔹 Raw legal document ingestion 🔹 Text cleaning and normalization 🔹 Legal article extraction 🔹 Section-aware document structuring 🔹 Custom chunk generation 🔹 Metadata extraction for article number, article title, section, source, and reference 🔹 Embedding generation 🔹 Vector database ingestion 🔹 Repeatable updates for future legal data expansion The chunking strategy was designed so legal articles were not cut in the middle or separated from their meaning. Agentic RAG Workflow Instead of using a simple one-step vector search, I built a LangGraph-based agentic RAG workflow. The workflow included: 🔹 User query understanding 🔹 Legal intent detection 🔹 Legal domain and scope identification 🔹 Generation of 2–5 targeted legal search queries 🔹 Retrieval of relevant chunks for each query 🔹 Deduplication of repeated results 🔹 Reranking of retrieved legal evidence 🔹 Source-grounded answer generation This improved tested retrieval accuracy from around 50% to 95%+. Retrieval, Citations & Case Law The retrieval system was designed to make answers transparent and verifiable. I implemented: 🔹 Vector search for semantic legal retrieval 🔹 Reranking to improve relevance 🔹 Metadata-based source traceability 🔹 Citation-backed answer generation 🔹 Article-level legal references 🔹 Typesense-based retrieval for French judicial cases 🔹 Supporting case law returned with legal answers This allowed lawyers to verify the exact legal source behind each generated response. Open-Source LLM & Cloud Deployment I evaluated and deployed open-source LLM infrastructure for private legal AI usage. The deployment included: 🔹 Qwen2.5:14B for French legal reasoning 🔹 Ollama and vLLM for model serving 🔹 Embedding and reranker models on a private Azure GPU VM 🔹 NVIDIA T4 16GB GPU optimization 🔹 Python/FastAPI backend APIs 🔹 Secure Azure deployment in the France region 🔹 Multi-tenant isolated access 🔹 GitHub CI/CD and Linux server management The system was designed for privacy, reliability, and regulatory compliance. Technologies Used 🔹 Python 🔹 FastAPI 🔹 LangChain 🔹 LangGraph 🔹 LangSmith 🔹 Ollama 🔹 vLLM 🔹 Qwen2.5:14B 🔹 ChromaDB 🔹 Typesense 🔹 Vector Databases 🔹 Reranking Models 🔹 Embedding Models 🔹 Azure Cloud 🔹 Linux 🔹 GitHub CI/CD Impact 🔹 Built a production-ready legal AI assistant for lawyers 🔹 Improved retrieval accuracy from ~50% to 95%+ in tested scenarios 🔹 Reduced hallucinations through citation-grounded generation 🔹 Enabled lawyers to verify answers using article and case references 🔹 Created a scalable legal data pipeline for thousands of documents 🔹 Deployed private open-source LLM infrastructure for legal compliance 🔹 Delivered a strong foundation for future legal AI workflows
0
49
Cover image for Jingle – Technical and Functional
Jingle – Technical and Functional Overview Jingle is a smart, family-focused marketplace built on the MERN stack (MongoDB, Express.js, React, Node.js) that empowers parents to buy, sell, or exchange baby and kids’ products using a points-based system instead of money. The platform ensures safety, quality, and sustainability in every transaction. Key Features User-Friendly Onboarding: Personalized welcome screens with guided setup for creating parent and child profiles. Product Management: Upload, organize, and manage baby and kids’ items, with automated verification for safety and quality. Points-Based Transactions: Earn points for uploaded items and redeem them for other products within the marketplace. Multi-Section Interface: Intuitive dashboard for uploaded products, shop browsing, child profiles, and points tracking. Secure Account Creation: Sign up easily using email, Google, or Apple accounts with secure authentication. Real-Time Updates: Receive notifications for product verification, agent visits, and point redemptions. Tech Stack Overview Core Platform Backend: Node.js with Express.js for API handling, product management, and points processing. Database: MongoDB for storing user profiles, child profiles, product listings, and point balances. Frontend React: Dynamic, responsive interface for mobile and web with optimized product browsing and uploads. Media Handling Product Uploads: Secure image and document handling for product listings. -UI Rendering: Optimized layout for both parents and children sections. Security & Performance -Secure Data Handling: Encrypted storage of personal, child, and product information. -Performance Optimization: Fast loading, real-time notifications, and smooth marketplace interactions. -Scalability: Supports multiple users with efficient data and points management. Summary Jingle makes sustainable parenting simple by enabling parents to share, save, and exchange baby and kids’ products through a secure, AI-enhanced, points-based marketplace. The MERN stack-based platform ensures quality verification, personalized recommendations, and a seamless family-focused shopping experience.
0
106