Why It Matters
Embeddings power semantic search and RAG. You will rarely see them directly, but they explain why modern tools can find a clause even when it uses different words from your search.
Related Terms
- Semantic search
- Search that matches meaning rather than exact keywords, so a question in plain English can find relevant documents that use different wording.
- RAG (retrieval-augmented generation)
- An AI technique that first looks up relevant documents, such as cases or your contracts, and then has the model answer from what it found.
- Vector database
- A database that stores embeddings and finds the closest matches by meaning rather than by exact words.
General information, not legal advice. Part of the Legal Tech Glossary, 173 terms in plain English.