Artificial Intelligence
Embeddings
Also known as: Vector embeddings & Text embeddings
Plain English
Turning glossaryDataData is raw, uninterpreted information collected and stored so it can be analysed, processed, or used to inform decisions. On its own it carries no meaning; context and interpretation are what make it useful.Open glossary term into numbers that capture meaning.
Definition
guideEmbeddingsWhat embeddings do, how they let AI understand meaning rather than match words, and what product teams need to know when working with semantic search or RAG.Open guide are numerical representations of glossaryDataData is raw, uninterpreted information collected and stored so it can be analysed, processed, or used to inform decisions. On its own it carries no meaning; context and interpretation are what make it useful.Open glossary term, such as text or images, that capture meaning and relationships.
In practice
Used in glossarySearchSearch is the functionality that allows users to find content or information by entering queries. It relies on indexing, metadata, and relevance algorithms to return useful results.Open glossary term, recommendation glossarySystemA system is a collection of interconnected components that work together to achieve a specific function or outcome.Open glossary term, and similarity matching.
In context
They are what let a glossarySearchSearch is the functionality that allows users to find content or information by entering queries. It relies on indexing, metadata, and relevance algorithms to return useful results.Open glossary term for cancel my subscription find a page titled ending your membership. The match is on meaning rather than words.
The reality
guideEmbeddingsWhat embeddings do, how they let AI understand meaning rather than match words, and what product teams need to know when working with semantic search or RAG.Open guide simplify complex glossaryDataData is raw, uninterpreted information collected and stored so it can be analysed, processed, or used to inform decisions. On its own it carries no meaning; context and interpretation are what make it useful.Open glossary term but can lose nuance or glossaryContextContext is the set of surrounding conditions that shape how someone behaves and decides, including their goal, their environment, their time pressure, and what happened immediately before. The same action can mean different things in different contexts.Open glossary term.
Compared with
Embeddings vs Keywords
Keyword matching finds documents containing the words used. guideEmbeddingsWhat embeddings do, how they let AI understand meaning rather than match words, and what product teams need to know when working with semantic search or RAG.Open guide find documents close in meaning, catching synonyms and paraphrase. Keywords are precise on exact terms; embeddings are better on glossarySearch IntentSearch intent is the underlying goal or purpose behind a user’s query, such as finding information, making a purchase, or navigating to a specific site.Open glossary term.
FAQ
Common questions
A few practical answers to the questions that usually come up around this term.
What are embeddings?
They are numerical representations of glossaryDataData is raw, uninterpreted information collected and stored so it can be analysed, processed, or used to inform decisions. On its own it carries no meaning; context and interpretation are what make it useful.Open glossary term that capture meaning.
Why are embeddings important?
They enable glossarySystemA system is a collection of interconnected components that work together to achieve a specific function or outcome.Open glossary term to compare and understand glossaryDataData is raw, uninterpreted information collected and stored so it can be analysed, processed, or used to inform decisions. On its own it carries no meaning; context and interpretation are what make it useful.Open glossary term.
Where are embeddings used?
In glossarySearchSearch is the functionality that allows users to find content or information by entering queries. It relies on indexing, metadata, and relevance algorithms to return useful results.Open glossary term, recommendations, and glossaryModelA model is a system or representation used to process data and generate outputs, often trained to perform specific tasks.Open glossary term.
Do embeddings capture full meaning?
Not always, some nuance can be lost.
Related Services
Related Guides
Related Terms
