Zendesk
Freshdesk
Gorgias
Front
Shopify
Stripe
Slack
Notion
Google Workspace
Confluence
Embeddings
Definition
Embeddings are numeric vector representations of text (or images, code, etc.) that capture meaning, so that pieces of content with similar meaning sit close together in a high-dimensional space.
How it works
An embedding model converts a chunk of text into a list of numbers — a vector, often hundreds or thousands of dimensions long. The model is trained so that semantically similar text ("reset my password" and "I forgot my login") produces vectors that are near each other, while unrelated text lands far apart.
You measure closeness with a similarity metric like cosine similarity. That's what makes embeddings the backbone of semantic search, RAG, and clustering: instead of matching keywords, you compare meaning.
Why it matters for support
Embeddings are how an AI support agent finds the right help-center article even when the customer's wording doesn't match your docs. When you connect knowledge sources, they're typically embedded and stored in a vector database so the agent can retrieve the most relevant passages to ground its answer.
Frequently asked
What is the difference between embeddings and tokens?
Tokens are the small text units a model reads. An embedding is the numeric vector that represents a token, phrase, or document's meaning. Tokenization comes first; embedding turns those tokens into meaning-carrying vectors.
Why are embeddings used in support AI?
They let an agent match a customer's question to relevant knowledge by meaning rather than exact keywords, which powers semantic search and retrieval-augmented generation.
Related terms
Vector Database
A vector database is a database built to store and search embeddings — high-dimensional vectors — by similarity, so you can quickly find the content whose meaning is closest to a query..
Semantic Search
Semantic search is a search technique that matches content by meaning rather than by exact keywords, using embeddings to find results that are conceptually related to the query even when they share no words with it..
Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation (RAG) is a technique where an AI model retrieves relevant information from your own knowledge sources at query time and uses it to ground its answer, instead of relying only on what it memorized during training..
Large Language Model (LLM)
A large language model (LLM) is a neural network trained on vast amounts of text to predict and generate language, enabling it to understand questions, summarize, classify, and write human-like responses..
Transformer Model
A transformer model is a neural network architecture that processes an entire sequence of text at once using an attention mechanism to weigh how much each word relates to every other word, and it's the foundation of nearly every modern large language model..
Put these ideas to work
Macha is an AI agent layer that sits on top of the help desk you already run — Zendesk, Freshdesk, Front, Intercom, or Gorgias.
Start Trial