Embeddings as Vectors: Length, Normalisation & the L1 Norm
This lesson is part of the course
In this lesson
You treat six help-centre articles of Fernwick Outdoor, a fictional outdoor-gear shop, as tiny 5-dimensional embeddings: you measure each vector's length, normalise it to length 1 and compare the L1 norm.
Buy the course once for $9.99 to unlock every lesson and lab, the final exam and the certificate – lifetime access, no subscription.
Lessons in this course
- Embeddings as Vectors: Length, Normalisation & the L1 Norm Locked
- Dot Product vs Cosine Similarity with SUMPRODUCT Locked
- Top-k Retrieval: RANK.EQ, LARGE and INDEX/MATCH Locked
- Euclidean Distance vs Cosine: When Do the Rankings Disagree? Locked
- Chunking: Tokens per Chunk, Number of Chunks & Embedding Cost Locked
- Approximate Search: Recall@k vs Exact Search and the Speed Trade-off Locked
- Hybrid Search: Blending Keyword and Vector Scores Locked
- RAG Retrieval Evaluation: Hit Rate@k, MRR & a Chart Locked