In this tutorial, we will introduce a unified architecture for Batch, Real-Time, and LLM AI Systems based around three independent ML pipelines

• A feature pipeline to create feature data,
• A training pipeline to train your model,
• And an inference pipeline to make predictions with new data on your trained model.

We will use this FTI architecture to walk through a tutorial of building a LLM system that uses RAG and function calling to access structured data and a model.

Register here

---