Embeddings · AI Beat

07 Oct 2026 · AI Beat Desk

One Vector Space to Rule Them All

Google released EmbeddingGemma 2, a 740M-parameter open model that maps text, code, images, audio, and video into the same embedding space. Built on Gemma 4, with Matryoshka support and 8K context. The interesting part is not the benchmarks — it's the cross-modal retrieval that becomes practical when audio and video share a space with text.

07 Jul 2026 · AI Beat Desk

Seven Megabytes of Semantic Search

Ternlight ships a sentence embedding model as a 7MB WASM bundle that runs on CPU in the browser — no API, no model download, no GPU required. Ternary weights are the key to the footprint; the result is semantic search you can include in an npm install.

31 Mar 2026 · AI Beat Desk

Microsoft's Harrier Embeds 32K Tokens at Once

Microsoft released Harrier-OSS-v1, a family of decoder-only multilingual embedding models (270M, 0.6B, 27B) with a 32,768-token context window — roughly 30–60x longer than the 512–1,024 token ceiling most practitioners hit today. The 27B model takes SOTA on Multilingual MTEB v2 at 74.3; all three variants are MIT licensed.