AI Glossary

The most important terms around Artificial Intelligence, simply explained.

LLM

Large Language Model. An AI model trained on vast amounts of text to understand and generate human language.

RAG

Retrieval-Augmented Generation. A method where an LLM is enhanced with external, retrievable documents (e.g., internal company data) to provide more precise and factually correct answers.

Prompting

The art and science of formulating instructions (prompts) so that an AI model produces the desired output.

C2PA

Coalition for Content Provenance and Authenticity. A standard for tracing the origin and authenticity of digital content (e.g., images) to create transparency about AI-generated media.

JSON-RPC

A stateless, lightweight remote procedure call protocol that uses JSON as its data format. It is often used for API integrations (such as the Model Context Protocol).

Vector DB

Vector Database. A database system optimized to store high-dimensional vectors (embeddings) and efficiently find similar content (e.g., for RAG).

Hallucination

A phenomenon where an AI model presents plausible but incorrect or fabricated information as facts.

Fine-Tuning

The process of further training a pre-trained AI model with specific, targeted data to improve its performance on a particular task.

Token

The smallest unit of text processed by an LLM. These can be words, parts of words, or individual characters.

Context Window

The maximum amount of text (in tokens) that a model can process at once and consider when generating a response.