Run in Colab
Step through this example interactively
question() helper accepts a video() node alongside a natural-language prompt and returns a textual answer. Combine with reasoning=True for step-by-step analysis of long-horizon episodes — assembly walkthroughs, training videos, customer-session recordings, and other content where the answer depends on watching what happens over time.
Basic usage
Returns:
PerceiveResult object:
text(str): The answer to your question.reasoning(str | None): The model’s chain-of-thought whenreasoning=True.clips,points,boxes,polygons(list | None): Populated when the correspondingexpectsis requested.
Example: Robot assembly walkthrough
In this example we download a short robot-assembly clip, ask Perceptron Mk1 to identify the overall goal and the sub-goals it observes, and let it think through the episode before answering.Best practices
- Reach for
expects="clip"when you need timestamps: If the answer needs to point at when something happens in the video, switch to the Video Clipping workflow instead. - Asking several questions about the same clip? Use the Multilook endpoint to send up to 16 prompts over one shared video in a single call. The video is prefilled once and reused, and the reused tokens are billed at the reduced cache-read rate.
Run through the full Jupyter notebook here. Reach out to Perceptron support if you have questions.