دیدگاه عامل‌گرایانه

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)

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)