Encyclopedia

AI Glossary

Context Window

The total amount of information (in tokens) an AI model can process in a single request, including input and history.

Technical

Mixture of Experts (MoE)

A machine learning technique where different specialized sub-networks (experts) are used for different parts of an input.

Architecture

Parameters

The weights and biases that a model learns during training, roughly correlating to its complexity and capacity.

Technical

Retrieval-Augmented Generation (RAG)

A framework for retrieving data from external sources to ground LLM responses in factual information.

Architecture

Tokens

The basic units of text processed by an LLM, representing sequences of characters, words, or sub-words.

Technical