AI Glossary · Last reviewed May 2026
Embeddings
Hand-written by a real person. Reviewed against current practice in May 2026.
"
Definition
Numeric fingerprints of text or images that let computers measure semantic similarity.
Full write-up coming soon
We are working on a detailed page for Embeddings - covering why it matters, how it works, related terms, and the tools that use it.
Related terms
From the glossaryFrequently asked questions
What is an embedding model?+
A model trained specifically to convert text into vectors that capture semantic meaning. Popular ones include OpenAI text-embedding-3 and open-source models like BGE and E5.
How are embeddings stored?+
In a vector database such as Pinecone, Weaviate, or pgvector. These databases are optimised for the nearest-neighbour search needed to find semantically similar vectors quickly.
Do embeddings work across languages?+
Multilingual embedding models exist that map text from different languages into the same vector space, so a query in English can match documents in French or Spanish.
Explore other terms
From the glossaryAI Agents
A program that takes goals and figures out the steps to reac...
API
The way one piece of software talks to another.
Chain of Thought
A prompting technique where the model reasons out loud, step...
Context Window
How much text a model can read at once.
Few-shot Learning
Showing a model two to five examples in the prompt so it fol...
Fine-tuning
Training a pre-built model further on your own data, to make...