Embedding

How it is used

Usually plural. You compute, store and compare embeddings, typically with cosine similarity. They power semantic search, recommendations, clustering and RAG systems, and are kept in vector databases.

Example sentences

1. We generate an embedding for every help article and store it in the vector database.

2. Search results improved after we switched to a multilingual embedding model.

Common collocations

• generate embeddings
• embedding model
• text embeddings
• embedding vector
• embedding space

Related terms

• vector databaseA database designed to store embeddings and quickly find the ones most similar to a query, which makes it a common part of semantic search and RAG systems.
• RAGShort for retrieval-augmented generation: a method in which a system first searches a document collection for relevant passages and then gives them to an LLM to write the answer.
• tokenA small unit of text that a language model reads and writes, often a whole word, part of a word or a punctuation mark. Model limits and prices are counted in tokens.
• clusteringAn unsupervised task that groups similar items together without predefined labels, for example sorting customers into segments by how they shop.

This word in other fields

The same English word can have a different meaning in another field:

• embedding · Software Engineering

More terms: Natural Language Processing

• natural language processing
• tokenizer
• sentiment analysis
• named entity recognition
• corpus