Book a call

Daniel & Friends / Glossary / Semantic search

AI and automation

Semantic search

Semantic search finds results by the meaning of a query instead of matching individual words. The query and the documents are turned into embeddings, and the closest ones are returned. It finds an answer even when the author used different wording.

Daniel Votruba ·


In practice

It works well in a company knowledge base or an online shop. Exact codes and product names are often handled better by classic search, so the two approaches are combined.

Related terms

  • Embedding: An embedding is a numerical representation of text, an image or other data as a vector, where similar meaning means a nearby position.
  • Vector database: A vector database stores embeddings and quickly finds those closest to a given query.
  • RAG (retrieval-augmented generation): RAG is a method in which a model first retrieves relevant documents, for example company knowledge, and answers from them.
  • Keyword: A keyword is a word or phrase people type into a search engine.

More terms in the group AI and automation

Shadow AI · RPA (robotic process automation) · Small language model (SLM) · Reasoning model · Speech-to-text · System prompt · Prompt injection · Temperature · Prompt engineering · Text-to-image · Prompt · Text-to-speech (TTS) · Predictive analytics · Text-to-video · Open-weight model · Token · No-code and low-code · NLP (natural language processing) · Vibe coding · Neural network · Voice cloning · Multimodal model · Agentic AI · Multi-agent system

Full glossary (590 terms)

Terms in practice

Need help putting them to work?

Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.

Book a call

Enjoyed the article? Share it with friends.