はてなブックマーク

We're excited to introduce EmbeddingGemma, a new open embedding model that delivers best-in-class performance for its size. Designed specifically for on-device AI, its highly efficient 308 million parameter design enables you to build applications using techniques such as Retrieval Augmented Generation (RAG) and semantic search that run directly on your hardware. It delivers private, high-quality

Stop "vibe testing" your LLMs. It's time for real evals. If you’re building with LLMs, you know the drill. You tweak a prompt, run it a few times, and... the output feels better. But is it actually better? You're not sure. So you keep tweaking, caught in a loop of "vibe testing" that feels more like art than engineering. This uncertainty exists for a simple reason: unlike traditional software, AI

Starting today, the URL context tool is now ready for scaled production use and comes packed with new features. The tool enables developers to provide additional context to the models in the form of URLs, instead of manually uploading the content, unlocking more powerful and contextually-aware generative AI applications. By default, Gemini models have a static knowledge base and no direct internet

The last few months have been an exciting time for the Gemma family of open models. We introduced Gemma 3 and Gemma 3 QAT, delivering state-of-the-art performance for single cloud and desktop accelerators. Then, we announced the full release of Gemma 3n, a mobile-first architecture bringing powerful, real-time multimodal AI directly to edge devices. Our goal has been to provide useful tools for de

Next, define your extraction task. Provide a clear prompt and a high-quality "few-shot" example to guide the model. import textwrap import langextract as lx # 1. Define a concise prompt prompt = textwrap.dedent("""\ Extract characters, emotions, and relationships in order of appearance. Use exact text for extractions. Do not paraphrase or overlap entities. Provide meaningful attributes for each en

Introducing Opal: describe, create, and share your AI mini-apps It’s never been easier to harness the power of AI models, prompts, and tools into working AI applications. We’re excited to announce Opal, a new experimental tool from Google Labs that lets you build and share powerful AI mini apps that chain together prompts, models, and tools — all using simple natural language and visual editing. O

AI モデルやプロンプト、ツールの力を活用した、実用的な AI アプリの作成がこれまでになく簡単になります。このたび、Google Labs から新しい試験運用版ツール Opal をリリースいたしました。Opal は、自然言語とビジュアル編集だけで、プロンプト、モデル、ツールを組み合わせた強力な AI ミニアプリを構築、共有できるツールです。AI に関するアイデアやワークフローのプロトタイピングを高速化したり、機能的なアプリで概念実証を行ったり、業務の効率を高めるカスタム AI アプリを構築したりと、さまざまな用途に活用できます。本日より提供を開始いたします。Opal を活用してどんなアプリが生み出されるのかとても楽しみです。 公開ベータ版で利用可能Opal はまったく新しい試験運用版ツールです。新製品の開発は初期の段階からコミュニティと協力して進めることが最善であると考えているため、米国

Today, we’re releasing the stable version of Gemini 2.5 Flash-Lite, our fastest and lowest cost (0ドル.10 input per 1M, 0ドル.40 output per 1M) model in the Gemini 2.5 model family. We built 2.5 Flash-Lite to push the frontier of intelligence per dollar, with native reasoning capabilities that can be optionally toggled on for more demanding use cases. Building on the momentum of 2.5 Pro and 2.5 Flash, t

The way AI visually understands images has evolved tremendously. Initially, AI could tell us "where" an object was using bounding boxes. Then, segmentation models arrived, precisely outlining an object's shape. More recently, open-vocabulary models emerged, allowing us to segment objects using less common labels like "blue ski boot" or "xylophone" without needing a predefined list of categories. P

We’re excited to announce that our first Gemini Embedding text model (gemini-embedding-001) is now generally available to developers in the Gemini API and Vertex AI. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March. Surpassing both our previous text embedding models and external offe

Building sophisticated AI applications with Large Language Models (LLMs), especially those handling multimodal input and requiring real-time responsiveness, often feels like assembling a complex puzzle: you're stitching together diverse data processing steps, asynchronous API calls, and custom logic. As complexity grows, this can lead to brittle, hard-to-maintain code. Today, we're introducing Gen

The first Gemma model launched early last year and has since grown into a thriving Gemmaverse of over 160 million collective downloads. This ecosystem includes our family of over a dozen specialized models for everything from safeguarding to medical applications and, most inspiringly, the countless innovations from the community. From innovators like Roboflow building enterprise computer vision to

Today at Open Source Summit North America, the Linux Foundation announced the formation of the Agent2Agent project with Amazon Web Services, Cisco, Google, Microsoft, Salesforce, SAP, and ServiceNow. With the formation of this new, independent entity, the companies will collaborate closely on fostering an open and interoperable ecosystem for AI agents with the Agent2Agent (A2A) protocol and other

Announcing Gemma 3n preview: powerful, efficient, mobile-first AI Following the exciting launches of Gemma 3 and Gemma 3 QAT, our family of state-of-the-art open models capable of running on a single cloud or desktop accelerator, we're pushing our vision for accessible AI even further. Gemma 3 delivered powerful capabilities for developers, and we're now extending that vision to highly capable, re

Based on the enthusiasm from developers, we are excited to announce that Image Generation capabilities are now available in preview with Gemini 2.0 Flash. Developers can start integrating conversational image generation and editing with higher rate limits via the Gemini API in Google AI Studio and Vertex AI today using the model name "gemini-2.0-flash-preview-image-generation". What's new in Gemin

Today we are rolling out an early version of Gemini 2.5 Flash in preview through the Gemini API via Google AI Studio and Vertex AI. Building upon the popular foundation of 2.0 Flash, this new version delivers a major upgrade in reasoning capabilities, while still prioritizing speed and cost. Gemini 2.5 Flash is our first fully hybrid reasoning model, giving developers the ability to turn thinking

Agent Development Kit: Making it easy to build multi-agent applications The world of AI is rapidly moving beyond single-purpose models towards intelligent, autonomous multi-agent systems. Building these multi-agent systems, however, presents new challenges. That is why today, we have introduced Agent Development Kit (ADK) at Google Cloud NEXT 2025, a new open-source framework from Google designed

A new era of Agent Interoperability AI agents offer a unique opportunity to help people be more productive by autonomously handling many daily recurring or complex tasks. Today, enterprises are increasingly building and deploying autonomous agents to help scale, automate and enhance processes throughout the workplace–from ordering new laptops, to aiding customer service representatives, to assisti

Data Science Agent automating analysis, from understanding the data to delivering insights in a working Colab notebook (Sequences shortened. Results for illustrative purposes. Data Science Agent may make mistakes.) Data Science Agent benefits Fully functional Colab notebooks: Not just code snippets, but complete, executable notebooks. Modifiable solutions: Easily customize and extend the generated

We're giving developers the power to build the future of AI with cutting-edge models, intelligent tools to write code faster, and seamless integration across platforms and devices. Since last December when we launched Gemini 1.0, millions of developers have used Google AI Studio and Vertex AI to build with Gemini across 109 languages. Today, we are announcing Gemini 2.0 Flash Experimental to enabl

Starting today, developers can access the latest Gemini models via the OpenAI Library and REST API, making it easier to get started with Gemini. We will initially support the Chat Completions API and Embeddings API, with plans for additional compatibility in the weeks and months to come. You can read more in the Gemini API docs, and if you aren't already using the OpenAI libraries, we recommend th

Updated production-ready Gemini models, reduced 1.5 Pro pricing, increased rate limits, and more Today, we’re releasing two updated production-ready Gemini models: Gemini-1.5-Pro-002 and Gemini-1.5-Flash-002 along with: >50% reduced price on 1.5 Pro (both input and output for prompts <128K)2x higher rate limits on 1.5 Flash and ~3x higher on 1.5 Pro2x faster output and 3x lower latencyUpdated defa

AI Edge Torch: High Performance Inference of PyTorch Models on Mobile Devices We are excited to announce Google AI Edge Torch - a direct path from PyTorch to the TensorFlow Lite (TFLite) runtime with great model coverage and CPU performance. TFLite already works with models written in Jax, Keras, and TensorFlow, and we are now adding PyTorch as part of a wider commitment to framework optionality.

Let’s try an experiment. We’ll show this picture to our multimodal model Gemini and ask it to describe what it sees: Tell me what you see Gemini: I see a person's right hand. The hand is open with the fingers spread apart.

These days, getting an app from zero to production – especially one that works well across mobile, web, and desktop platforms – can feel like building a Rube Goldberg machine. You’ve got to navigate an endless sea of complexity, duct-taping together a tech stack that'll help you bootstrap, compile, test, deploy, and monitor your apps. While Google’s been working on making multiplatform app develop

Upcoming security changes to Google's OAuth 2.0 authorization endpoint in embedded webviews Share Facebook Twitter LinkedIn Mail Posted by Badi Azad, Group Product Manager (@badiazad) The Google Identity team is continually working to improve Google Account security and create a safer and more secure experience for our users. As part of that work, we recently introduced a new secure browser policy

PaLM API & MakerSuite: an approachable way to start prototyping and building generative AI applications Share Facebook Twitter LinkedIn Mail Posted by Scott Huffman, Vice President, Engineering and Josh Woodward, Senior Director, Product Management We’re seeing a new wave of generative AI applications that are transforming the way people interact with technology – from games and dialog agents to c

Share Facebook Twitter LinkedIn Mail Noto emoji, a new black and white emoji font with less color, may gain us more in the long run Posted by Jennifer Daniel, Creative Director - Emoji & Expression In 1999 — back when Snake 🐍 was the best thing about your phone 📱 — there were three phone carriers in Japan 🗾 . On these phones were tiny, beautiful pictures called emoji (meaning "picture" and "cha