A small NumPy project explains normalization, cosine similarity, ranking, and why nearest does not automatically mean suitable.
Embedding demos often jump from text to a magical list of “similar” results. A tiny matcher makes the missing steps visible: normalize vectors, compute scores, rank candidates, and inspect failure cases.
This example uses fixed vectors so it runs without an API key.
import numpy as np
resume = np.array([0.8, 0.6, 0.1, 0.0])
projects = {
Building a RAG pipeline with pgvector, text-embedding-3-small, and Neon into a production Next.js SaaS — the numbers, the…
Real hackathon brief (Unstop). Paste your resume + a job description, get a 0-100 match score + the exact missing keywords. Zero…
I rewrote the embedding pipeline around a failure case I hit in production: a single blended embedding kept surfacing candidates…
What I Built A full-stack AI application that scores how well a resume matches a job...
TL;DR: Learn a very simple way to normalize, dedupe, and fuzzy-match records that refer to the same...
Testing Face Embedding Nearest Neighbor Search with OpenCV SFace Hello, everyone. Face...
