An AI Programming Interface (AIPI) functions like a traditional API, but instead of executing static server-side code, it facilitates interactions with Large Language Models (LLMs) through hosted prompts, producing non-deterministic outcomes.
AIPIs server as abstraction layers over general LLM APIs, where every endpoint is tailored for a specific task. While they usually accept user input, that doesn't always have to be the case.
In its simplest form, an AIPI endpoint can simply merge input data into a predefined one-shot prompts, complete it with a call to an LLM API, and return the result. In more complex scenarios, an endpoint might retrieve data from external sources, vector stores, etc., and trigger one or more AI agents to generate a response.
The LLM Knowledge Base is a collection of bite-sized explanations for commonly used terms and abbreviations related to Large Language Models and Generative AI.
It's an educational resource that helps you stay up-to-date with the latest developments in AI research and its applications.