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

# Search best practices

> Tips and tricks for getting the best search results in Jumper

## Use key terms, not conversational phrases

Jumper works best when you use direct, descriptive keywords rather than conversational language.

<CardGroup cols={2}>
  <Card horizontal title="❌ Avoid">
    "show me all the frames with a man holding a skateboard on a ramp"
  </Card>

  <Card horizontal title="✅ Better">
    "man holding a skateboard on a ramp"
  </Card>
</CardGroup>

The model focuses on the visual content described in your query, so extra words like "show me all the frames with" don't help and can sometimes reduce accuracy.

## Keep searches focused

When searching for multiple unrelated items, perform separate searches rather than combining them with "or".

<CardGroup cols={2}>
  <Card horizontal title="❌ Avoid">
    "a polar bear or a red car"
  </Card>

  <Card horizontal title="✅ Better">
    Search 1: "polar bear"<br />
    Search 2: "red car"
  </Card>
</CardGroup>

Separate searches give you better results because the model can focus on one concept at a time. You can always add both sets of results to your timeline if needed.

## Simplify searches

If a search doesn't return the results you're looking for, try simplifying it by removing specific actions or details.

<CardGroup cols={2}>
  <Card horizontal title="If this doesn't work...">
    "a couple kissing on bench"
  </Card>

  <Card horizontal title="...try this instead">
    "a couple sitting on bench"
  </Card>
</CardGroup>

Sometimes removing specific actions (like "kissing") and using more general terms (like "sitting") can help the model find what you're looking for. You can always refine your search after getting initial results.

## Add shot and scene details

You can include cinematographic details and scene characteristics in your search queries to find specific types of shots or settings. The model will often recognize these cues and return more relevant results.

**Examples:**

<Columns cols={2}>
  <div>
    * "red car **close-up**"
    * "red car **wide shot**"
    * "person **medium shot**"
    * "building **drone shot**"
  </div>

  <div>
    * "city street **at night**"
    * "beach **sunrise**"
    * "forest **daytime**"
    * "interior **daylight**"
    * "mountain landscape **dusk**"
  </div>
</Columns>

## Search for text in footage

Jumper's models have OCR-like capabilities, meaning they can read text that appears in your footage.

You can search for signs, labels, text overlays, or any written content visible in your video. For example, searching for "STOP" might find traffic signs, or searching for a product name might find shots where that text appears on screen.

It might help to add "text" or "sign" to your search to help the model find what you're looking for.

<Columns cols={2}>
  <Card horizontal>
    "Acmecorp text"
  </Card>

  <Card horizontal>
    "Acmecorp sign"
  </Card>
</Columns>

<Info>
  There's no guarantee that the model will find all occurrences of text in your footage.
</Info>

## Exclude what you don't want

Don't put negation in your search query. Words like "not" are unreliable in the main search box.

Use [Exclude search terms](/interface/search-tab#exclude-search-terms) in the Visual search tab instead. Keep your query focused on what you want. Add unwanted concepts in the exclude dropdown.

<CardGroup cols={2}>
  <Card horizontal title="❌ Avoid">
    "people talking not in a meeting room"
  </Card>

  <Card horizontal title="✅ Better">
    Query: "people talking"<br />
    Exclude: "meeting room"
  </Card>
</CardGroup>

If results still include too many false positives, increase the exclude bias with the slider or [narrow the search context](/interface/search-tab#context-picker).

## Narrow the search context

The models can struggle if you are searching in large amounts of media. If you experience degraded accuracy, you might want to use the [context picker](/interface/search-tab#context-picker) to narrow down the search context.

<Info>
  If you know what files or bins you want to search in, it's recommended to search in that specific context instead of everything.
</Info>

## Temporarily hide results

You can shift-click a thumbnail in the search results to temporarily remove it from view. This is especially handy when you want to add all results to the timeline except for one or a few false positives.