#embeddings

EmbeddingGemma 2: semantic search on a laptop in 20 lines

Google's new 740M multimodal embedding model runs on a CPU. Here's how to build a working semantic search over your own documents, and the prefixes that make it accurate.

google/embeddinggemma-2

Why your EmbeddingGemma 2 vectors are NaN (and the one-line fix)

Loading EmbeddingGemma 2 in float16 silently breaks it. Here's how to detect it and pick the right dtype for your hardware.

google/embeddinggemma-2

Matryoshka embeddings: how many dimensions do you actually need?

A practical rule of thumb for truncating embeddings to cut vector-DB cost, with the numbers from EmbeddingGemma 2.