Description of the bug:

Invalid operation: The response.parts quick accessor requires a single candidate, but none were returned. Please check the response.prompt_feedback to determine if the prompt was blocked.

Actual vs expected behavior:

I am calling the llm using image and video like this

response = model.generate_content(
[prompt, video_file],
request_options={"timeout": 600},
safety_settings=safety_settings,
)

Any other information you'd like to share?

No response