With the rise of Open-Source LLMs like Llama, Mistral, Gemma, and more, it has become apparent that LLMs might also be useful even when run locally. In this talk, we will see how to deploy an Agentic Retrieval Augmented Generation (RAG) setup using Ollama, with Milvus as the vector database on your laptop. That way, you can also avoid being Rate Limited by OpenAI like I have been in the past.