What is Embedding?

Explained

An embedding is a vector (list of numbers) that represents the meaning of text, an image, or audio. Similar meanings produce similar vectors, enabling semantic search, clustering, and retrieval in RAG systems.

Decision guides that use this term

• RAG vs fine-tuning: which one does your enterprise use case need?

Further reading

• Vector Databases for RAG: Powering Semantic Search for LLMs

Related terms

• RAG Retrieve relevant documents and use them as context to generate the answer.
• Retrieval Search phase that fetches relevant documents or passages for a query.
• Semantic Search Search by meaning, not just exact words; uses embeddings.
• Vector Numerical representation; see Embedding.
• Agent Agenda The agent’s live plan: ordered steps, open subtasks, and checkpoints toward a goal.
• Agent Planner Component or prompt pattern that proposes multi-step plans before tools run.