Glossary
LLM (Large Language Model)
A type of AI system trained on vast amounts of text to understand and generate human-like language. In Ethora, LLMs power the AI agents and chat bots that businesses use to serve their customers.
General definition
An LLM, or Large Language Model, is a neural network trained on vast amounts of text data so it can understand and generate human-like language. These models contain billions or even trillions of parameters and handle tasks like text generation, translation, summarization and code writing.
ChatGPT popularized LLMs for mainstream users by demonstrating conversational AI at scale. It’s worth distinguishing an LLM from a broader AI agent: while an LLM excels at predicting text, true agents add external capabilities — web search, calculations and live data — to overcome LLM limitations such as fixed knowledge cutoff dates.
LLMs in the Ethora ecosystem
Within Ethora, LLMs power AI agent chat bots designed to help businesses serve customers — summarizing information, researching topics, providing education and holding natural conversations. A built-in AI bot, powered by OpenAI by default, deploys with no code required.
The AI SDK includes a no-code AI Agent builder for context-aware bots, a self-hosted LLM option if you’d rather not use OpenAI, and RAG integration — a website crawler and document indexer — so your model can be trained on business-specific knowledge.
