Embeddings
Turning meaning into vectors you can compare mathematically.
- What are Embeddings?Beginner
Embeddings turn information into numerical vectors where similar meanings sit close together, so software can compare meaning with math.
- Similarity: Cosine, Dot Product & EuclideanIntermediate
Similarity metrics measure how close two embedding vectors are; cosine similarity compares direction, dot product adds magnitude, and Euclidean measures distance.
- Embedding Models & DimensionsIntermediate
An embedding model is the trained network that turns input into vectors; its dimensions, training, and quality determine how good your search and RAG will be.
- Dense vs Sparse EmbeddingsIntermediate
Dense embeddings capture meaning in a few hundred numbers; sparse vectors capture exact keywords across a huge vocabulary. Hybrid search combines both.
- What are Matryoshka Embeddings?Advanced
Matryoshka embeddings pack the most important information into the first dimensions, so you can shorten the vector to save space and speed with minimal quality loss.