# Upload Data to Rapid

To get started with Roboflow Rapid, you first need to upload either:

* A short video that contains objects you want to identify, or;
* A few images that contain objects you want to identify.

You can upload data from your desktop, or use your webcam to capture a photo or record a short video directly in the browser.

If you upload a video to Rapid, you will be asked to clip its length to 10 seconds.

If you upload images, we recommend uploading at least five, although you can get started and build a prototype Rapid model with as few as one image.

### How to Upload Data to Rapid

To upload data, go to Roboflow Rapid and drag either your video or image into the web interface. Your files will then be processed and uploaded. This may take a few moments depending on the size of the files you upload. All popular image and video formats are supported (i.e. JPEG, PNG, HEIC/HEIF for images, and mp4 and mov for videos).

The data you upload will then be displayed in the Rapid interface:

<figure><img src="/files/XvEKK7q46GLPTBEOo6I7" alt=""><figcaption></figcaption></figure>

Once you upload data, you will be asked what objects you are looking for. This is where you should type in labels for objects you want to identify. For example, if you want to find trucks in an image, type "truck". Rapid will also suggest a few classes relevant to the data you upload in the "Try these" section on the page.

To specify multiple classes, separate each class with a comma, like "truck, car".

Once you have set one or more classes to identify, click "Find My Objects" to start building your Rapid model.


---

# 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://docs.roboflow.com/rapid/upload-data-to-rapid.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.