Search

17 results

Clear filters
  • JULY 16, 2025 / AI

    Unlock Gemini’s reasoning: A step-by-step guide to logprobs on Vertex AI

    The `logprobs` feature has been officially introduced in the Gemini API on Vertex AI, provides insight into the model's decision-making by showing probability scores for chosen and alternative tokens. This step-by-step guide will walk you through how to enable and interpret this feature and apply it to powerful use cases such as confident classification, dynamic autocomplete, and quantitative RAG evaluation.

    logprobs_meta
  • JUNE 24, 2025 / Kaggle

    Using KerasHub for easy end-to-end machine learning workflows with Hugging Face

    KerasHub enables users to mix and match model architectures and weights across different machine learning frameworks, allowing checkpoints from sources like Hugging Face Hub (including those created with PyTorch) to be loaded into Keras models for use with JAX, PyTorch, or TensorFlow. This flexibility means you can leverage a vast array of community fine-tuned models while maintaining full control over your chosen backend framework.

    How to load model weights from SafeTensors into KerasHub for multi-framework machine learning
  • JAN. 15, 2025 / AI

    Vertex AI RAG Engine: A developers tool

    Vertex AI RAG Engine, a managed orchestration service, streamlines the process of retrieving and feeding relevant information to Large Language Models. This enables developers to build robust, grounded generative AI apps that ensure responses are factually grounded.

    Cloud-Vertex-AI-Sequence-Light
  • DEC. 23, 2024 / AI

    Gemini 2.0: Level Up Your Apps with Real-Time Multimodal Interactions

    The Multimodal Live API for Gemini 2.0 enables real-time multimodal interactions between humans and computers, and can be used to build real-time virtual assistants and adaptive educational tools.

    Stream-meta
  • DEC. 23, 2024 / AI

    See the Similarity: Personalizing Visual Search with Multimodal Embeddings

    Learn how to build a visual search tool using Google's Multimodal Embeddings API and explore how to apply this technology for searching images, slides, and more.

    Multimodal-Embeddings-Creative-Lab-Feature
  • DEC. 18, 2024 / Gemini

    Dive Deep into Gemini: Explore Starter Apps in AI Studio

    Explore three Gemini starter apps that provide developers with production ready tools to build AI-powered projects with open source functionalities like spatial analysis, and video interactions.

    Starter apps
  • DEC. 18, 2024 / Gemini

    Build Go applications using Project IDX and the Gemini API

    Learn how to build Go applications using Project IDX, an AI-assisted workspace for full-stack app development.

    Project IDX-Go-Gemini API
  • DEC. 9, 2024 / Web

    Unlocking the Potential of Quantum Computing

    A free Coursera course on quantum error correction, developed by Google Quantum AI, explains the importance of error correction in quantum computing and provides an overview of quantum errors.

    Gemini x Coursera
  • NOV. 19, 2024 / Firebase

    Learn to build and run AI powered apps at Firebase Demo Day ‘24

    Explore Firebase's new AI-powered app development tools and resources, including demos, documentation, and best practices at Firebase Demo Day 2024.

    Firebase Demo Day
  • NOV. 8, 2024 / Gemini

    Gemini is now accessible from the OpenAI Library

    Developers can now access and build with the latest Gemini models through the OpenAI Library and REST API. Update your code with three lines and get started.

    Gemini-Social-2