Detailed explanation
Examples
Frequently asked questions
What is the difference between an embedding and a keyword?
A keyword matches exact words. An embedding matches meaning — 'car' and 'vehicle' are close in embedding space even though they share no letters.
Which embedding model should I choose?
For most use cases, start with OpenAI text-embedding-3-small or an open model like BGE-M3. Test on your own data to confirm the choice.
Related terms
Machine Learning
A branch of AI where models learn patterns from data instead of following explicit rules.
Token
A unit of text (often a word fragment) that a language model consumes and produces.
NLP (Natural Language Processing)
The branch of AI dedicated to understanding and generating human language.
Vector Database
A database specialized in storing and searching embeddings by semantic similarity.
RAG (Retrieval-Augmented Generation)
RAG is a technique that combines an LLM with a search engine over your own documents: the model retrieves the relevant information first, then generates an answer grounded in that information.
Last updated: 7/15/2026