RAG Workspace — Multi-Tenant Document Q&A Platform Built a full-stack retrieval-augmented generation (RAG) platform enabling teams to query uploaded documents with source-grounded, cited answers. Designed FastAPI backend with JWT authentication, role-based access control (RBAC), and strict multi-tenant workspace isolation for multiple concurrent organisations. Implemented semantic search using ChromaDB vector database alongside MongoDB, reducing document query response time significantly vs. keyword search. Integrated multiple LLM backends including Ollama (self-hosted) and OpenAI-compatible APIs, enabling flexible model switching without code changes. Tech: FastAPI, React, ChromaDB, MongoDB.