video_frames = extract_frames(video_path, num_frames=num_frames)

messages = [
    {
        "role": "system",
        "content": [{"type": "text", "text": "You are a helpful assistant."}]
    },
    {
        "role": "user",
        "content": [{"type": "text", "text": "Nsaba mufunze ebigenda mu maaso mu katambi kano"}]
    }
]


# Add frames to the messages structure.
for frame_data in video_frames:
    img, timestamp = frame_data
    messages[1]["content"].append({"type": "text", "text": f"Frame at {timestamp} seconds:"})
    img.save(f"/content/frames/frame_{timestamp}.png")
    messages[1]["content"].append({"type": "image", "url": f"/content/frames/frame_{timestamp}.png"})


inputs = processor.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=True,
    return_dict=True, return_tensors="pt"
).to(model.device)


input_length = inputs["input_ids"].shape[-1]

# Generate a response based on the inputs.
output = model.generate(**inputs, max_new_tokens=500, do_sample=False)
output = output[0][input_length:]
response = processor.decode(output, skip_special_tokens=True)

display(Markdown(response))

        __
        __