KNOWLEDGE, EMBEDDINGS & RAG • 113 / 397
Teach models to look up relevant information before answering.

Semantic Similarity

Semantic similarity measures how close two items are in meaning rather than exact wording.

Think of it like

Think of Semantic Similarity like a library system: instead of memorizing every book, find the right shelf and bring only the useful pages to the desk.

Real life

Search engines and recommendation systems use ideas related to Semantic Similarity.

SRE lens

“OOM killed” and “out of memory termination” should be considered similar.

Remember thisSemantic similarity measures how close two items are in meaning rather than exact wording.
AIForSREJump to a concept
Search is optional. The main journey is simply ↓ Next.