Exam · Embeddings and vector search from first principles

Take the exam and earn your certificate.

A real, server-scored exam for this course. Score strictly above 80% to pass and get a genuine, verifiable certificate.

Before you start

We ask for your name and email first, the same as a PDF download, so we know you are here and your certificate can carry the right name.

We privately record your name, email and request IP for this exam request. Read the privacy notice and retention policy.

Visit Mickai on LinkedIn

Complete the security check before submitting.

Cloudflare Turnstile helps prevent automated submissions. How this check uses data.

You can retake the exam any time. Each attempt draws a fresh set of questions.

Written practice, ungraded

Write your response in your own notes, then compare it with the sample answer. This practice is separate from the scored exam and does not affect your certificate.

Practice 1

Choose one failure from chapter 4. Use one printed example to explain why a high word-match score can still be a poor answer.

Compare with a sample answer

The “Other pets” pair scores 0.88 even though “not allowed” changes the meaning. Shared words can dominate the count-based score, so the result needs inspection.

Separate ungraded paper practice. Connect a demonstrated failure to its evidence.

Practice 2

Explain why the Saturday query can return two similar hours notes near the top, and name one source-supported way to handle near-duplicates.

Compare with a sample answer

The ordinary and summer hours notes are near-duplicates and take the top two places. Keep one current version or filter by date.

The source identifies the near-duplicate pattern and suggests keeping one current version or filtering by date.

Practice 3

Describe how a changed TF-IDF collection affects the existing representation and what rebuilding step the chapter calls for.

Compare with a sample answer

IDF depends on the whole collection, so adding a note changes word weights and new words are unknown until refitting. Refit the vectorizer and rebuild the index.

Checks the stated collection-wide IDF dependency and rebuild consequence.

Practice 4

Compare exact search with the one-group and two-group cluster-pruning results using both recall and score count.

Compare with a sample answer

Exact search scores 10,000 documents. One group averages 255 scores and recall 0.76; two groups average 335 and recall 0.94. The example trades more work for better recall.

These figures come from the chapter’s synthetic comparison and may differ on another collection.

Practice 5

What does the high-dimension example suggest, and what caution does the chapter add before applying it to text search?

Compare with a sample answer

The random-point farthest-to-nearest ratio approaches one as dimensions increase. The chapter cautions that this does not make high-dimensional search meaningless and that text vectors are not uniform random points.

Preserves both the numeric observation and the source’s stated limitations.

Practice 6

Write a short handling rule for vectors made from personal text, using the chapter’s privacy discussion and its scope limitation.

Compare with a sample answer

Treat vectors of personal text as personal data and apply the same access control, retention and deletion. The course labels this a working rule, not legal advice, and notes the ICO guidance is under review.

Educational prompt only; it does not establish legal advice or current professional acceptance.

About this exam

Is this exam graded?

Yes. Every question is scored on our server, never in your browser, and you need a score strictly above 80% to pass. The questions are a real, reviewed bank for this course, drawn fresh for each attempt.

Is it only multiple choice?

Yes. This is a multiple-choice knowledge assessment, with at least one question from each chapter in every attempt. Written exercises are separate practice and are not automatically scored. Passing does not establish practical professional competence or independently verify identity.

Is there a time limit?

Yes, 30 minutes, shown as a countdown once you start. If time runs out, whatever you have answered is submitted automatically.

Do I need to download the PDF first?

No. This course's full text is on its own page, so you can read it online and come straight here when you feel ready.

What do you do with my name and email?

We privately record your name, email, request IP, course and privacy acknowledgement for this request. Newsletter consent is separate and optional. See /privacy.html for storage and retention. A passed exam creates a server-stored named certificate. An email confirmation is not identity assurance.

Can I retake it if I fail?

Yes, straight away. Each attempt draws a fresh set of questions and shuffles the answer order, so it will not be identical to your last attempt, and an attempt can only be submitted once.

Is the certificate real?

It is a genuine, server-issued certificate with its own verification page and a unique ID, not a self-declared one. It records that you passed this course's exam on this date. It is not an accredited qualification, a professional licence or proof of employment.