Penelusuran

280 hasil

Hapus filter
  • 20 MEI 2025 / AI Edge

    On-device small language models with multimodality, RAG, and Function Calling

    Google AI Edge advancements, include new Gemma 3 models, broader model support, and features like on-device RAG and Function Calling to enhance on-device generative AI capabilities.

    Google AI Edge: Small Language Models with Multimodality, RAG, and Function Calling
  • 20 MEI 2025 / Cloud

    What's new with Agents: ADK, Agent Engine, and A2A Enhancements

    Updates to Google's agent technologies include the Agent Development Kit (ADK) with new Python and Java versions, an improved Agent Engine UI for management, and enhancements to the Agent2Agent (A2A) protocol for better agent communication and security.

    What's New with Agents ADK, Agent Engine, and A2A Enhancements- Google I/O
  • 20 MEI 2025 / Android

    What you should know from the Google I/O 2025 Developer keynote

    Top announcements from Google I/O 2025 focus on building across Google platforms and innovating with AI models from Google DeepMind, with key focus on new tools, APIs, and features designed to enhance developer productivity and create AI-powered experiences using Gemini, Android, Firebase, and web.

    What you should know from the Google I/O 2025 Developer keynote
  • 20 MEI 2025 / Gemini

    Building agents with Google Gemini and open source frameworks

    Google Gemini models offer several advantages when building AI agents, such as advanced reasoning, function calling, multimodality, and large context window capabilities. Open-source frameworks like LangGraph, CrewAI, LlamaIndex, and Composio can be used with Gemini for agent development.

    Building agents with Google Gemini and open source frameworks
  • 20 MEI 2025 / Gemini

    From idea to app: Introducing Stitch, a new way to design UIs

    Stitch, a new Google Labs experiment, uses AI to generate UI designs and frontend code from text prompts and images, aiming to streamline the design and development workflow, offering features like UI generation from natural language or images, rapid iteration, and seamless paste to Figma and front-end code.

    From idea to app: Introducing Stitch, a new way to design UIs
  • 20 MEI 2025 / Gemma

    Announcing Gemma 3n preview: powerful, efficient, mobile-first AI

    Gemma 3n is a cutting-edge open model designed for fast, multimodal AI on devices, featuring optimized performance, unique flexibility with a 2-in-1 model, and expanded multimodal understanding with audio, empowering developers to build live, interactive applications and sophisticated audio-centric experiences.

    Gemma 3n
  • 13 MEI 2025 / TensorFlow

    Membangun dan melatih sistem pemberi rekomendasi dalam 10 menit menggunakan Keras dan JAX

    Keras Recommenders (KerasRS) adalah library baru yang diumumkan untuk membantu developer membangun sistem rekomendasi menggunakan API dengan komponen penyusun untuk pemeringkatan dan pengambilan, serta dapat diinstal melalui pip dengan dukungan untuk JAX, TensorFlow, atau backend PyTorch.

    Build and train a Recommender System in 10 minutes using Keras and JAX
  • 12 MEI 2025 / Cloud

    Google Cloud mengumumkan ketersediaan umum APIM Operator untuk Apigee

    Apigee APIM Operator sekarang tersedia secara umum, menghadirkan kemampuan Manajemen dan Gateway API ke lingkungan GKE menggunakan konfigurasi YAML serupa Kubernetes, menyediakan peralatan native developer, mengurangi friksi, dan menawarkan manajemen kebijakan yang setara dengan Apigee Hybrid.

    Apigee-API-Hub-Feature
  • 9 MEI 2025 / Cloud

    Google AI untuk developer game

    Kunjungi lagi pengumuman dari Games Developer Conference (GDC) tahun ini. Jelajahi bagaimana model Gemma dan Gemini dapat membantu dalam membangun pengalaman AI dalam game dengan peluncuran Gemma 3, plugin Unity, aplikasinya dalam contoh game, dan penskalaan game dengan AI generatif di Google Cloud.

    Google AI for Game Developers
  • 9 MEI 2025 / DeepMind

    Memajukan batas pemahaman video dengan Gemini 2.5

    Gemini 2.5 menandai lompatan besar dalam pemahaman video, mencapai performa canggih pada tolok ukur pemahaman video penting dan mampu menggunakan informasi audio-visual dengan kode dan format data lainnya secara mulus.

    2.5Pro_Metadata_VideoUnderstanding