What job does the embedding model do in a search pipeline, and what does it ultimately decide?
LLM & AILevel: IntermediateRAG (Retrieval-Augmented Generation)
What job does the embedding model do in a search pipeline, and what does it ultimately decide?
Hints
- What does closeness mean in this representation and metric?
- Check normalization, exact versus approximate search and alignment with the training objective.
Answer
The embedding model reads each piece of text and outputs a fixed-length vector that captures its meaning, placing similar-meaning texts close together. At query time you embed the question and return the nearest chunks, so the embedding model rather than the search box decides what counts as a match.
Source and licence: Skillumen — Awesome AI Engineer Interview Questions · CC0-1.0