Vector Databases & Embeddings

4 Interactive Sessions

Short, interactive sessions: watch it work, try it, then build it yourself. You can go deeper at any time in the written chapters.

1. 1

   Finding things by meaning

   An embedding turns text into a point on a map of meaning. Similar things land close together, and searching by meaning means finding the nearest points.

2. 2

   How text becomes a list of numbers

   An embedding model turns any text into one vector in three steps: split it into tokens, read each token in context, and combine them into one point. You choose which model to use.

3. 3

   Searching millions of vectors quickly

   With millions of vectors you cannot check every one. An index finds the nearest ones quickly by giving up a little recall, and a database stores and serves them.

4. 4

   Making retrieval work, then designing your own

   Plain nearest-neighbour search is not enough. Top-K, hybrid search, re-ranking, MMR and measurement make it good. Then you design a real pipeline and choose where it runs.

How this certificate is scored

Your certificate shows how many of your written answers met the rubric below, checked by an AI grader. Anyone who checks your certificate sees it.

• You answer 6 short questions, one for each module, in your own words (at least 40 words each).
• An AI grader checks each answer against what its module asks for: it must answer the question, use the course's practice case specifically, and be correct.
• To pass, at least 5 of the 6 answers must meet that bar. The certificate says the answers were graded by AI.

The rubric

1. Module 1, What Are Embeddings?: Understanding of vectors, similarity, and distance metrics.
2. Module 2, How Embedding Models Work: Tokenize-encode-pool pipeline and model selection.
3. Module 3, Vector Database Fundamentals: ANN indexes, trade-offs, and tuning parameters.
4. Module 4, The Vector DB Landscape: Database comparison and cost modeling.
5. Module 5, Search & Retrieval Patterns: Hybrid search, re-ranking, MMR, and evaluation.
6. Module 6, Your First Vector Pipeline: End-to-end pipeline design with decision memo.

What you walk away with