Text as vectors: the geometry that powers semantic search, RAG, clustering and recommendations.
Skip to solutionKEEP THE
easyAI Engineering
What are embeddings and what are they used for?
974 views
01
Understand the problem
embeddingsvectorssemantic-search
02
Attempt it yourself
Sketch your approach before reading the solution — that's what interviews test.
Nudge consolestandby
Stuck? Beam a request up — the console returns a conceptual nudge that guides your logic without spoiling the implementation.
03
Study the solution
An embedding is a dense vector (hundreds to thousands of floats) produced by a model such that semantically similar texts map to nearby points. Because similarity becomes geometry, embeddings power semantic search (query vs document vectors), RAG retrieval, deduplication, clustering, classification and recommendations.
Solution ready — 2 min read
Classified // press E to declassify
04
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]]05
Join the discussion
Discussion (0)
Sign in to join the discussion.
No responses yet. Be the first to share what you think.
Transmission complete // awaiting log
KEEP THE
STREAK ALIVE.
Dossier 2 of 80 decoded in the AI Engineering track. One more won't hurt.