Cat RAG: Retrieval-Augmented Generation for Feline Knowledge

This project implements a lightweight RAG pipeline using Ollama for answering cat-related questions (health, breeds, behavior).

• Curates and embeds a corpus of cat knowledge.
• Uses a vector store for fast semantic retrieval.
• Combines retrieved context with local LLM generation via Ollama.
• Optimized for low-latency, context-aware responses.