Agentic Vision

Gemini Robotics ER 模型可以编写和执行 Python 代码来处理图片，并在回答问题之前应用逻辑。本页介绍了代码执行示例：使用缩放和裁剪功能进行对象检测、乐器读数、液体测量、电路板读数和图片注释。

如需根据自己的使用情形调整这些示例，请将提示文本和上传的图片文件替换为您自己的内容。您还可以调整提示中请求的 JSON 架构，以匹配应用所需的输出结构，或者添加 system_instruction 来强制执行输出格式和精度。

如需查看完整的可运行代码，请参阅机器人技术食谱。

思考等级

您可以控制模型的思考水平，以牺牲延迟时间来换取准确性。对象检测等空间任务在低思维水平下表现良好。计数或重量估计等复杂任务需要更高的思维水平。

以下示例将复杂计数任务的思考水平设置为 high：

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="scene.jpeg")

interaction = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": "Identify and count all objects on the table."}
    ],
    generation_config={
        "thinking_level": "high"  # Use "minimal" or "low" for faster spatial tasks
    }
)

print(interaction.output_text)

如需了解详情，请参阅思考。

对象检测（缩放和裁剪）

以下示例使用代码执行功能来缩放和剪裁图片，以便在检测到对象并返回边界框时获得更清晰的视图。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="sorting.jpeg")

prompt = """
Return JSON in the format {label: val, y: val, x: val, y2: val, x2: val} for
the compostable objects in this scene. Please Zoom and crop the image for a
clearer view. Return an annotated image of the final result with the bounding
boxes drawn on it to the API caller as a part of your process.
"""

interaction = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": prompt}
    ],
    tools=[{"type": "code_execution"}]
)

print(interaction.output_text)

模型输出将类似于以下 JSON 响应：

[
  {"label": "compostable", "y": 256, "x": 482, "y2": 295, "x2": 546},
  {"label": "compostable", "y": 317, "x": 478, "y2": 350, "x2": 542},
  {"label": "compostable", "y": 586, "x": 556, "y2": 668, "x2": 595},
  {"label": "compostable", "y": 463, "x": 669, "y2": 511, "x2": 718},
  {"label": "compostable", "y": 178, "x": 565, "y2": 250, "x2": 609}
]

下图显示了模型返回的方框。

显示检测到的对象的边界框的示例

读取模拟仪表并应用逻辑

以下示例演示了如何使用该模型读取模拟表盘并执行时间计算。它使用系统指令来强制生成 JSON 输出。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="gauge.jpeg")

interaction = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    system_instruction="Be precise. When JSON is requested, reply with ONLY that JSON (no preface, no code block).",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": """Read the current value from this gauge. Then, calculate how long
        it will take at the current rate for the value to reach maximum.
        Reply in JSON: {"current_value": val, "max_value": val,
        "time_to_max_minutes": val}"""}
    ],
    tools=[{"type": "code_execution"}]
)

print(interaction.output_text)

测量容器中的液体

以下示例演示了如何使用代码执行来测量容器中的液体量。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="fluid.jpeg")

interaction = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    system_instruction="Be precise. When JSON is requested, reply with ONLY that JSON (no preface, no code block).",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": """Measure the amount of fluid in the container. Reply in JSON:
        {"fluid_level_ml": val, "container_capacity_ml": val,
        "percentage_full": val}"""}
    ],
    tools=[{"type": "code_execution"}]
)

print(interaction.output_text)

读取电路板上的标记

以下示例演示了如何使用代码执行功能读取电路板上的标记。

Python

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="circuit_board.jpeg")

interaction = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    system_instruction="Be precise. When JSON is requested, reply with ONLY that JSON (no preface, no code block).",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": """Read all visible component labels and markings on this circuit
        board. Reply in JSON: {"components": [{"label": val,
        "location": [y, x]}]}"""}
    ],
    tools=[{"type": "code_execution"}]
)

print(interaction.output_text)

显示电路板上标记的示例

图片注释

以下示例演示了如何使用代码执行功能来注释图片（例如，绘制箭头以指示处置说明），并返回修改后的图片。

Python

from google import genai

client = genai.Client()

# Load your image
uploaded_file = client.files.upload(file="sorting.jpeg")

prompt = """
Look at this image and return it as an annotated version using arrows of
different colors to represent which items should go in which bins for
disposal. You must return the final image to the API caller.
"""

interaction = client.interactions.create(
    model="gemini-robotics-er-2-preview",
    input=[
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        },
        {"type": "text", "text": prompt}
    ],
    tools=[{"type": "code_execution"}]
)

print(interaction.output_text)

以下是输入图片的示例。

显示时钟的示例

模型输出将类似如下所示：

  The annotated image shows the suggested disposal locations for the items on the table:
  - **Green bin (Compost/Organic)**: Green chili, red chili, grapes, and cherries.
  - **Blue bin (Recycling)**: Yellow crushed can and plastic container.
  - **Black bin (Trash)**: Chocolate bar wrapper, Welch's packet, and white tissue.

后续步骤