> ## Documentation Index
> Fetch the complete documentation index at: https://docs.generalrobotics.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# VideoLLaVA 

The `VideoLLaVA` class provides a wrapper for the Video-LLaVA model, which answers questions
about visual media (videos).

<ResponseField name="class VideoLLaVA()">
  <ResponseField name="use_local" type="boolean" default="True">
    If True, inference call is run on the local VM, else offloaded onto GRID-Cortex. Defaults to True.
  </ResponseField>
</ResponseField>

<ResponseField name="def run()">
  <ResponseField name="image" type="np.ndarray">
    The input RGB image of shape $(M,N,3)$.
  </ResponseField>

  <ResponseField name="video" type="str">
    The path to the input video.
  </ResponseField>

  <ResponseField name="prompt" type="str" required="True">
    The question to answer about the media.
  </ResponseField>
</ResponseField>

<ResponseField name="Returns" type="str">
  The response to the prompt.
</ResponseField>

<RequestExample>
  ```python Inference Call theme={null}
  from grid.model.perception.vlm.video_llava import VideoLLaVA
  car = AirGenCar()

  # We will be capturing an image from the AirGen simulator 
  # and run model inference on it.

  img =  car.getImage("front_center", "rgb").data

  model = VideoLLaVA(use_local = True)
  result = model.run(rgbimage=img, prompt=<prompt>)
  print(result)
  ```
</RequestExample>

<Tabs>
  <Tab title="License">
    This code is licensed under the Apache 2.0 License.
  </Tab>

  <Tab title="Source">
    [https://github.com/PKU-YuanGroup/Video-LLaVA](https://github.com/PKU-YuanGroup/Video-LLaVA)
  </Tab>
</Tabs>