Embeddings & RAG
AI · Advanced
Definition
Embeddings turn text into vectors; RAG retrieves relevant documents by vector similarity and feeds them to an LLM.
Lets AI answer from your own data with fewer hallucinations.
Diagram
Flowchart
Example: Cosine similarity
import math
a, b = [1, 2], [2, 4]
dot = sum(x*y for x, y in zip(a, b))
print(round(dot / (math.hypot(*a) * math.hypot(*b)), 2))Output: 1.0
Key points
- Chunk size affects retrieval quality
- Cite retrieved sources
Interview questions
Why RAG instead of fine-tuning?
It is cheaper, updates instantly with new data and shows sources.