FeaturedLive & Operationalpersonal2025Solo project2025
LumiDoc — AI-Powered Document Q&A
LumiDoc is an AI-powered document intelligence platform that lets users "chat" with their files. Upload a PDF, Word doc, spreadsheet, slide deck, or scanned image, and ask questions in plain English — LumiDoc returns accurate answers with citations pointing back to the exact source in your documents. Built end-to-end as a solo project using a production-grade RAG (Retrieval-Augmented Generation) pipeline. Documents are processed asynchronously, split into semantic chunks, embedded as vectors, and retrieved using hybrid search (semantic + keyword). Answers stream in real time from Anthropic's Claude models. Tech stack: Next.js 15, TypeScript, Tailwind CSS, Supabase (PostgreSQL + pgvector), Anthropic Claude, and Voyage AI embeddings deployed on Vercel.
lumidoc.vercel.app
Overview
Project Overview
LumiDoc is an AI-powered document intelligence platform that lets users "chat" with their files. Upload a PDF, Word doc, spreadsheet, slide deck, or scanned image, and ask questions in plain English — LumiDoc returns accurate answers with citations pointing back to the exact source in your documents. Built end-to-end as a solo project using a production-grade RAG (Retrieval-Augmented Generation) pipeline. Documents are processed asynchronously, split into semantic chunks, embedded as vectors, and retrieved using hybrid search (semantic + keyword). Answers stream in real time from Anthropic's Claude models. Tech stack: Next.js 15, TypeScript, Tailwind CSS, Supabase (PostgreSQL + pgvector), Anthropic Claude, and Voyage AI embeddings deployed on Vercel.
Case Study
Problem → Solution
Problem
Professionals and teams sit on large volumes of documents — contracts, reports, research papers, financial spreadsheets — but finding a specific answer means manually scrolling through dozens of pages. Traditional keyword search returns matching files, not actual answers, and generic AI chatbots can't read private documents or cite where information came from. The result: hours lost to manual searching and no way to trust an AI's answer without verifying the source.
My Role
Solo developer responsible for product design, the end-to-end RAG architecture, document processing, hybrid retrieval, streamed Claude responses, authentication, storage, and deployment.
Solution
Built a full-stack RAG application where users upload documents that are processed through an asynchronous pipeline: text extraction per file type, semantic chunking (512 tokens), and vector embedding via Voyage AI stored in Supabase pgvector. At query time, a hybrid search engine combines 70% semantic vector similarity with 30% full-text search — enhanced by HyDE query expansion to retrieve the most relevant context. Answers are generated by Anthropic's Claude and streamed to the UI with inline source citations, so every response is verifiable. Auth, storage, and row-level security are handled through Supabase, with the whole system deployed serverlessly on Vercel.
Outcome
Document search time: Minutes → Seconds · Supported file formats: 6+
Results
Impact Metrics
MinutesSeconds
Document search time
6+
Supported file formats
Stack
Technologies Used
Frontend
Next.jsTypeScript
Database
SupabasePostgreSQLpgvector
AI
Anthropic ClaudeVoyage AI
Looking for this kind of engineering experience?
I am open to Software Developer opportunities worldwide and can join after a one-month notice period.
Available for workTypical response: <24h
Want something like LumiDoc — AI-Powered Document Q&A built for you? I take on freelance Next.js and TypeScript work on a written scope and a fixed price.
See services & pricing