344 hasil
11 SEP. 2025
The recent 0.2.0 release of Google’s Agent Development Kit (ADK) for Java adds an integration with t...
10 SEP. 2025 / AI
Batch API now supports Embeddings and OpenAI CompatibilityToday we are extending the Gemini Batch AP...
9 SEP. 2025 / AI
We are launching 1.0 stable release of Genkit Go, empowering Go developers to build performant, production-ready AI-powered applications with Genkit. Recent enhancements include support for integrating and building MCP tools, expanding third-party model provider support, and production AI monitoring with Firebase. Additionally, we are announcing a new feature in the Genkit CLI to provide AI development tools, like the Gemini CLI and Cursor, with the latest knowledge of Genkit - supercharging Genkit development experience when using AI assistance.
9 SEP. 2025 / AI
Ekstensi A2A menyediakan cara yang fleksibel untuk menambahkan fungsionalitas khusus pada komunikasi agen-ke-agen, melampaui protokol A2A inti. Ekstensi ini memungkinkan fitur khusus dan didefinisikan serta diimplementasikan secara terbuka.
9 SEP. 2025 / AI
Meskipun JAX terkenal sebagai framework populer untuk pengembangan model AI berskala besar, ia juga ...
8 SEP. 2025 / AI
Today, we’re launching three big Veo updates: support for vertical format outputs (9:16 aspect ratio...
5 SEP. 2025 / Mobile
Google AI Edge telah memperluas pratinjau Gemma 3n untuk menyertakan dukungan audio. Pengguna bisa mencobanya langsung di ponsel mereka sendiri menggunakan Google AI Edge Gallery, yang sekarang tersedia dalam versi Open Beta di Play Store.
4 SEP. 2025 / Gemma
Introducing EmbeddingGemma: a new embedding model designed for efficient on-device AI applications from Google. This open model is the highest-ranking text-only multilingual embedding model under 500M parameters on the MTEB benchmark, enabling powerful features like RAG and semantic search directly on mobile devices without an internet connection.
28 AGU 2025 / AI
Detailed prompting techniques and best practices for various applications, including photorealistic scenes, stylized illustrations, product mockups, and more using Google's newly released Gemini 2.5 Flash Image; a natively multimodal model capable of generating, editing, and composing images using text, supporting capabilities like text-to-image, image editing, style transfer, and multi-image composition.
28 AGU 2025 / AI
The world of AI is moving at a breakneck pace, and at the core of many modern applications like sema...