For Heads-of · Practitioner
Embedding
A numerical representation of text, images, or other data in a high-dimensional space where similar items are positioned close together.
- embeddings
- vectors
- semantic search
- representations
Purpose
Embeddings convert raw data into numeric vectors that machine learning models can process. Semantically similar words or concepts have similar embeddings.
Example
In word embeddings, the vector for king minus man plus woman approximately equals queen, showing the model captures semantic relationships.
RAG and Search
Embeddings power retrieval-augmented generation (RAG) systems by enabling semantic similarity search; documents are converted to embeddings and retrieved based on query similarity.