







EmbeddingGemma: Powerful and Lightweight Text Representations
We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research.


Embeddings: What they are and why they matter
Embeddings are a really neat trick that often come wrapped in a pile of intimidating jargon. If you can make it through that jargon, they unlock powerful and exciting techniques …

Fast Embeddings on GPUs
Fast and accurate search is vital to all of Perplexity, from Search and Computer to our API Platform. Behind the scenes, the heavy lifting is done by embedding

Google for Developers Blog - News about Web, Mobile, AI and Cloud
EmbeddingGemma 2 is a compact, open-source multimodal embedding model that maps text, code, images, video, and audio into a unified 768-dimensional space. Developers can use the sentence-transformers library to selectively load modular modality encoders—ranging from 270M to 740M parameters—to optimize memory usage. Additionally, Matryoshka Representation Learning enables dynamic dimension truncation down to 128d, significantly reducing vector database storage requirements while maintaining high retrieval performance.

Google for Developers Blog - News about Web, Mobile, AI and Cloud
Discover EmbeddingGemma, Google's new on-device embedding model designed for efficient on-device AI, enabling features like RAG and semantic search.

Embeddings: What they are and why they matter
The New API Definition Abstraction Layer Over At Apiary
I was on the road last week, so I didn’t maintain my usual barrage of API analysis. As I go through my monitoring for the week, I’d say the biggest news of t...
Translating Embeddings for Modeling Multi-relational Data
We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose, TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assumption proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.
Embedding at the Speed of Light - Qdrant
How static embedding models turn tokenization into the only bottleneck, how we embedded 32.9M passages in 35 minutes on a laptop CPU with FastEmbed, and what you give up in recall.

Token Pooling-Aware Training for Multi-Vector Embedding Models
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Introducing the Next Generation of Communication Using APIs
APIs are everywhere. The number of public APIs available on ProgrammableWeb are growing at a dizzying pace, with current count being at 7,207. The number of ...

We Need an Open Abstraction Layer to Help Us Better Define and Design Our APIs
I walked around San Francisco with Jakub Nesetril (@jakubnesetril), the CEO of Apiary, Wednesday evening, talking about the API space. Eventually we sat down...
The Five Month Journey Toward A Stable APIs.json Discovery Format
I published the story last night on finalizing the most recent version of the API discovery format APIs.json, and the support for it in the open source API s...

Email triage with an embedding-based classifier · Adam Wiggins
I built a machine learning pipeline for email triage. Includes a hand-labeled golden set, training the model in the browser, and evals. Plus options for local vs cloud embeddings.
