Google DeepMind推出Gemini Decisions API

Google 深度思维（Google DeepMind）近日正式推出 Gemini Decisions API。该接口由全新的 Gemini Decision 1 模型驱动，旨在支持多模态内容的快速评估与决策。

据官方介绍，Gemini Decision 1 模型能够在单次处理流程中，对文本、图像、音频、视频及 PDF 文件中的最多 1,000 个问题进行并行评估。这些问题类型涵盖是非题、选择题以及基于评分标准的问题。

该 API 的核心功能在于计算多个问题的信心分数（confidence scores），从而帮助用户在文本和多媒体内容中快速进行概率选择。这种机制为定向查询、内容评分或政策规则检查提供了一种具备成本效益的解决方案。

开发者目前可通过 Google AI Studio 获取 API 密钥开始构建应用。官方文档已提供 Python、JavaScript 和 REST 接口的使用指南。

以下代码示例展示了如何使用 Python SDK 调用该 API，针对一张包含液体泄漏的图片执行多项判断任务：

from google import genai

client = genai.Client(http_options={"api_version": "v1beta"})

result = client.decisions.create(
    model="gemini-decision-1",
    input=[{
            "type": "image",
            "uri": "https://storage.googleapis.com/generativeai-downloads/images/spill.jpg",
            "mime_type": "image/jpeg",
        },
        {
            "type": "text",
            "text": "Breakroom counter check before the 9 AM client meeting.",
        },
    ],
    questions={
        "has_spill": {
            "type": "noul",
            "instructions": "Is there an uncleaned liquid spill on the counter?",
        },
        "next_action": {
            "type": "choice",
            "instructions": "Which cleanup action fits the scene?",
            "criteria": {
                "wipe_with_cloth": "Small counter spill with a cloth or towel already nearby.",
                "dispatch_janitorial": "Large floor hazard, broken glass, or active leak.",
                "ready_for_meeting": "Counter is clean and ready.",
            },
        },
        "severity": {
            "type": "score",
            "instructions": "Rate the severity of the counter mess.",
            "criteria": [
                "Clean and ready.",
                "Minor localized spill.",
                "Major spill or safety hazard.",
            ],
        },
    },
)