Skip to contentSkip to stories

Updated

#RAG

#RAG

Items with an AI score under 20 are hidden. Show low-relevance items

Oct 8

Oct 8Thu
  1. Sakana AIOfficialAI score36

    Sakana AI's technology powers Iris's physician evidence search tool

    AIIris Inc.'s medical evidence search tool Evidence Finder has adopted Sakana AI's technology for answering physicians' questions. The system searches the literature and generates answers that cite their sources, handling literature comparison, synthesis, and answer generation.

    Image from @SakanaAILabs's post
  2. Google Cloud TechOfficialAI score40

    Google Cloud's borderless Lakehouse lets Gemini query multicloud data directly

    AIGoogle Cloud's borderless Lakehouse lets Gemini query data on AWS and Azure without variable egress fees. It reads directly from Salesforce Data 360, SAP, ServiceNow, and Workday without copying data. It also federates open Apache Iceberg tables across Databricks Unity, Snowflake Horizon, and AWS Glue.

    Video from @GoogleCloudTech's post

Oct 6

Oct 6Tue
  1. Google DeepMindOfficialAI score67

    Google DeepMind releases EmbeddingGemma 2, an open multimodal embedding model for on-device use

    AIGoogle DeepMind has released EmbeddingGemma 2, an open 740 million parameter model that maps text, images, audio, and video into one embedding space. It is built on the Gemma 4 architecture under an Apache 2.0 license and supports an 8K token context window. The company reports a code benchmark gain from 68.76 to 78.68 on MTEB Code and says the model can run on-device with about 567MB of active RAM for the full multimodal version on a Google Pixel 11 Pro.

    Why it matters: The release shows how a 740M-parameter embedding model can cover text, code, images, audio, and video on local hardware, with memory and storage figures to compare against other on-device options.

Oct 5

Oct 5Mon
  1. Google Developers BlogOfficialAI score62

    EmbeddingGemma 2 releases multimodal embeddings with modular encoder loading

    AIGoogle released EmbeddingGemma 2, an open embedding model under the Apache 2.0 license that maps text, code, images, video, and audio into a shared 768-dimensional space. Developers can load a 270M-parameter text and code setup, or add vision and audio encoders up to a 740M-parameter full multimodal model. Matryoshka truncation to 256 or 128 dimensions reduces vector storage, with the guide noting quality losses on image, video, and speech retrieval at lower dimensions.

    Why it matters: The guide gives concrete encoder sizes and dimension-storage tradeoffs, showing how to choose a configuration for text, code, image, video, and audio retrieval.