natively builder

Smart RAG PDF Reader is an intelligent document assistant designed to transform static PDF files into interactive conversational workspaces. Built for the AI Factory Hackathon using native.builder, the application solves the problem of document overload by eliminating manual reading and unreliable keyword searches. Powered by a Retrieval-Augmented Generation (RAG) architecture, the system extracts text from uploaded PDFs, chunks it semantically, and stores vector embeddings in Supabase using the pgvector extension. When a user asks a question, query embeddings are compared via Cosine Similarity to retrieve the most relevant text chunks. Grounded prompts are then passed to Groq API (Llama-3) for sub-second inference and Google Gemini API for multimodal reasoning. Key Features & Technologies: • native.builder: Core app scaffolding, glassmorphism UI components, and cloud deployment. • RAG Engine: PDF text chunking, embedding generation, and zero-hallucination grounded prompts. • Supabase Vector Storage: High-performance PostgreSQL vector indexing with pgvector. • Ultra-Fast Inference: Sub-second response times powered by Groq LPUs alongside Gemini API.