/4 min
On-Device Semantic Search on iPhone with Core ML and EmbeddingGemma
Run semantic search fully on-device on iOS: convert EmbeddingGemma to Core ML, store vectors with SimilaritySearchKit, quantize to fit memory.
Topic
Embeddings & Semantic Search
Models, dimensions, caching, and fine-tuning the representations retrieval runs on.
/4 min/reference
Matryoshka Embeddings in Production: One Vector, Many Sizes
Matryoshka Representation Learning packs meaning into early dimensions so you can truncate one embedding to many sizes for fast, cheap retrieval.
/4 min
Hybrid Search: When Pure Vector Embeddings Aren't Enough
Add sparse/keyword search to dense embeddings only when your eval shows lexical misses on IDs, rare terms, acronyms, code, or names.
/4 min/reference
How to Choose an Embedding Model and Dimension for Your Vector Database
Pick an embedding model and dimension by trading MTEB quality against RAM, latency, and re-embedding cost — with a decision tree.
/4 min/reference
Cosine vs Dot Product vs Euclidean: Which Similarity Metric Should You Use?
On normalized embeddings all three metrics rank identically, so pick dot product for speed; magnitude only matters with unnormalized vectors.
/1 min/reference
RAG chunking strategies: a practical reference
The common chunking approaches for retrieval, when each one helps, and the tradeoffs — a quick reference you can come back to.