# VIDEO\_CAPTURE

`VideoFrameCaptureStep` is a pipeline step that configures how to extracts a single frame from a video each time inference is called. The video path is hard coded, mainly used for testing/demo purposes.

| Configs    | Descriptions                                                                                                                                                                                                                                                                                                                                     |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| filePath   | Location of the video file.                                                                                                                                                                                                                                                                                                                      |
| outputKey  | Name of the output key where the image frame will be located. Default name is `image`.                                                                                                                                                                                                                                                           |
| loop       | Loop the video when it reaches the end. Default is set to `true`.                                                                                                                                                                                                                                                                                |
| skipFrames | <p>Optional - Number of frames to skip between returned frames. If not set: No frames are skipped. For example:</p><p>Value 0: equivalent to no skipping.</p><p>Value 1: skip 1 frame between returned frames (i.e., return every 2nd frame).</p><p>Value 3: skip 2 frames between returned frames (i.e., return every 3rd frame) and so on.</p> |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://serving.konduit.ai/references/pipeline-steps/video_frame_capture.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.