HQAI Engineering HQ
Search
Checking sign-in...
← Learning paths

Embeddings & retrieval

Explain how vector-based retrieval works and explore its trade-offs through interactive examples.

11 stepsAbout 85 minSelf-paced

Your learning sequence

  1. 01

    Embeddings and vector representations

    Explain how embeddings turn text and other data into vectors

    Concept8 minbeginner
  2. 02

    Explore embeddings

    Build intuition for what embeddings actually do by playing with a small vector space you can see and measure.

    Playground6 minbeginner
  3. 03

    Vector representations for AI systems

    Explain how vectors represent meaning in AI applications

    Concept9 minbeginner
  4. 04

    Explore vector search

    Watch a query become a vector, compare it with stored documents, and see how the nearest results are selected.

    Playground7 minbeginner
  5. 05

    Vector distance and similarity metrics

    Explain what cosine, Euclidean, Manhattan, and dot product comparisons measure

    Concept8 minintermediate
  6. 06

    Cosine similarity

    Explain cosine similarity as a comparison of vector direction

    Concept9 minintermediate
  7. 07

    Explore cosine similarity

    Select word vectors, inspect the calculation, and see why direction matters more than length.

    Playground7 minintermediate
  8. 08

    kNN and ANN nearest neighbor search

    Explain how exact k-nearest neighbors (kNN) search works and why it gets slow on large collections

    Concept8 minintermediate
  9. 09

    Semantic search in a support inbox

    Compare a typed customer query against ten saved support tickets and watch the nearest semantic match rise to the top.

    Playground6 minbeginner
  10. 10

    Hybrid search

    Explain why keyword search and vector search each miss results the other finds

    Concept9 minintermediate
  11. 11

    Semantic cache

    Explain how a semantic cache answers similar prompts by comparing embeddings instead of exact text

    Concept8 minintermediate

Reading is a starting point, not a proficiency score. Revisit any step whenever it helps.