easyAI Engineering

What are embeddings and what are they used for?

Q: What are embeddings and what are they used for?

**TL;DR.** An embedding is a **dense vector** representing text (or images/code) such that **similar meaning → nearby points**. Similarity becomes geometry, powering **semantic search, RAG, dedup, clustering, classification and recommendations**. vector space reset my password forgot login credentials pizza recipe <line class='d-edge-a

973 views

Understand the problem

Text as vectors: the geometry that powers semantic search, RAG, clustering and recommendations.

embeddingsvectorssemantic-search

Attempt it yourself

Sketch your approach before reading the solution — that's what interviews test.

Stuck? AI Nudge Available

Get a conceptual hint to guide your logic without spoiling the final implementation.

Study the solution

The solution is waiting

Give it an honest attempt first — then compare your thinking with the full walkthrough.

Read the code

Embed once, search by cosine

import numpy as np

def cosine(a, b):
    return float(np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)))

doc_vecs = embed_model.embed([d.text for d in docs])      # index time, stored
q = embed_model.embed(["how do I reset my password"])[0]  # query time

ranked = sorted(zip(docs, doc_vecs), key=lambda p: -cosine(q, p[1]))
top3 = [d.title for d, _ in ranked[:3]]

Join the discussion

Discussion (0)

No responses yet. Be the first to share what you think.

What is a Large Language Model and how does it generate text?

What belongs in the system prompt versus the user message?