Learn · AI fundamentals

What is an embedding, in plain terms?

An embedding turns a piece of text (or an image) into a list of numbers that captures its meaning, so a computer can measure how similar two things are. Content about close ideas ends up with similar numbers. It's the math that powers semantic search and recommendations.

This is what lets a search understand that "laptop won't turn on" and "my computer is dead" mean the same thing, even with no shared words. The system compares embeddings, not exact text, and finds the closest matches by meaning.

Embeddings are the backbone of RAG. Your documents get embedded and stored, and when a question comes in, the system finds the most relevant chunks by similarity and feeds them to the model. You rarely see embeddings directly, but they're doing the retrieval work behind good AI features.

Updated July 2026

Learning Center More on ai fundamentals

What is the difference between RAG and fine-tuning?
RAG (retrieval-augmented generation) feeds a model your data at question time, so it answers from your documents without changing the model. Fine-tuning retrains a model on your examples so it internalizes a style or task. RAG is for knowledge, fine-tuning is for behavior.
How does an AI model actually generate text?
An AI model breaks your input into tokens (word pieces), then predicts the most likely next token, adds it, and repeats, one token at a time, until the answer is complete. Every word it produces is a probability-weighted guess informed by patterns it learned during training.
What is a large language model?
A large language model (LLM) is an AI system trained on huge amounts of text to predict what words come next. That simple mechanism, scaled up, lets it write, summarize, translate, answer questions, and reason through problems. ChatGPT, Claude, and Gemini are all interfaces to LLMs.
What are tokens and why do they matter?
Tokens are the chunks of text an AI model reads and writes. A token is roughly three-quarters of a word in English, so 1,000 tokens is about 750 words. They matter because AI pricing and limits are measured in tokens, not words or characters.
What is a context window?
A context window is the maximum amount of text an AI model can hold in mind at once, counted in tokens. It includes your prompt, any documents you attach, the conversation so far, and the answer being written. Once you exceed it, the model loses track of the earliest content.
Why do AI models make things up?
AI models hallucinate because they generate the most plausible-sounding next words, not verified facts. When they don't know something, they don't stay silent. They produce a confident guess that fits the pattern of a real answer, which is why a made-up citation or statistic can look entirely legitimate.

Want this built, not just explained?

Start the conversation

What is an embedding, in plain terms?

What is the difference between RAG and fine-tuning?

How does an AI model actually generate text?

What is a large language model?

What are tokens and why do they matter?

What is a context window?

Why do AI models make things up?

Want this built, not just explained?