הבנת סרטונים

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="task_video.mp4")

prompt = """
At what timestamp (in seconds) does the task reach successful completion?
Return a JSON object: {"completion_time_seconds": <float>}.
If the task is not completed, return {"completion_time_seconds": null}.
"""

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

print(interaction.output_text)

from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="task_video.mp4")

prompt = """
Watch this video and classify the task progress level at the final frame.
Return a JSON object with the progress bracket:
{"progress_level": "0-20" | "20-40" | "40-60" | "60-80" | "80-100"}.
"""

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

print(interaction.output_text)