Embeddings and retrieval

2 stories about Embeddings and retrieval, newest first. Each one links to its primary source.

1. Oct 9

   Google releases EmbeddingGemma 2, an open 740M-parameter embedding model for text, images, video and audio

   Google DeepMind's EmbeddingGemma 2 maps text, code, images, video and audio into one 768-dimension embedding space. It has 740 million parameters in total, is released under Apache 2.0, and its encoders can be loaded selectively. The benchmark scores are Google's own.

   Models, Open weights, Embeddings 1 source

2. Oct 9

   Perplexity releases pplx-embed-v2-late, 9B and 0.6B late-interaction embedding models for text and images

   On 7 October 2026 Perplexity published two ColBERT-style late-interaction embedding models, pplx-embed-v2-late-9B and 0.6B, for text and image retrieval with a shared embedding space. Both are on Hugging Face; the post names no license or price. Benchmark numbers are Perplexity's own.

   Models, Embeddings, Retrieval 1 source