Portfolio RAG Chatbot
Python · FastAPI · FAISS · Groq · sentence-transformers · Docker · Render
RAG chatbot with FastAPI and FAISS, embedding 40 content chunks for sub-second semantic retrieval. Streams responses via SSE using Groq's Llama 3.1 with ~200ms first-token latency, LRU caching, similarity threshold gating, and a hardened system prompt to prevent hallucination and prompt injection.
Private