সক্রিয় দৃষ্টি

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)

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)

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)

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)

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)