The Generative AI hype cycle has led to a new wave of terminology to understand. In this post, we’ll use basic programming language to explain and explore the concepts of “chains” of LLMs and retrieval-augmented generation (RAG) approaches to working with data.
Connect to the data and load a table into a variable.
Calls and computations
When an AI platform’s large language model API is called, it returns text as the result of some computation on input text. See the LLM concept article for details.
Calls
A call is just that – a call to something. In Python, this is typically always something else in Python, that itself may make calls to other programming languages or external services.
A deterministic, human-authored function that calls the AI function.
Computations
A computation is just that – a computation of something. In general, a computation is represented by a system that takes an input and returns an output.
Comparison to MLOps and DevOps
Summary
Next steps
You can get involved with Ibis Birdbrain, our open-source data & AI project for building next-generation natural language interfaces to data.