For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Sample appsIntegrationsDiscordPlaygroundDevEx repo
GuidesSDK ReferenceAPI Reference
GuidesSDK ReferenceAPI Reference
  • Get Started
    • Introduction
    • Quickstart
    • Manage your plan
    • Rate limits
    • Release notes
    • Migration guide
  • Guides
    • Search
    • Analyze videos
    • Segment videos
    • Create embeddings
  • Concepts
    • Models
    • Upload and processing methods
    • Indexes
    • Modalities
    • Multimodal large language models
  • Cloud partner integrations
    • Amazon Bedrock
  • Advanced
    • Organizations
    • Fine-tuning
    • Webhooks
    • Metadata
    • Model context protocol
    • Claude Code Plugin
  • Resources
    • Platform overview
    • Playground
      • Upload and manage assets
      • Manage indexes
      • Search
        • Entity search
      • Analyze videos
      • Segment videos
      • Visualize embeddings
      • Examples
    • TwelveLabs SDKs
    • Frequently asked questions
    • Use cases
    • Sample applications
    • Partner integrations
    • From the community
LogoLogo
Sample appsIntegrationsDiscordPlaygroundDevEx repo
On this page
  • Procedure
  • View results
  • Visual tab
  • JSON tab
  • Work with search results
  • Play a specific moment
  • View a transcription
  • View all clips from a video
  • Analyze a video
  • View the code snippet
ResourcesPlayground

Search

Was this page helpful?
Previous

Entity search

Next
Built with

The Playground allows you to search using natural language queries. A natural language query refers to the ability to enter search requests using everyday language, instead of using specific keywords. For example, enter “Interviews with scientists discussing climate change” to find matching moments across your videos.

The page uses a two-panel layout. Enter your query and adjust parameters in the left panel. Results appear in the right panel.

Notes
  • This guide applies to indexes using the Marengo video understanding model.
  • You can search for specific persons in your videos. For instructions on setting up and using this feature, see the Entity search page.

Procedure

  1. Open the Indexes page.
  2. Select the index containing the videos you want to search.
  3. Select the Search tab.
  4. In the left panel, enter your query:
    • Text query: Type a natural language query in the search box and press Enter.
    • Image query: Select the image icon and upload an image.
  5. (Optional) Adjust the parameters under Advanced Settings. To reset all parameters to their default values, select the Reset button.
  6. Select the Search button.

View results

Results appear in the right panel. Select the Visual or JSON tab to switch between views.

Visual tab

The Visual tab shows results as video clips sorted by relevance. Each clip includes a video player, a thumbnail preview strip, a timestamp range, a transcription icon, and a See Full Video button.

JSON tab

The JSON tab shows the raw JSON response.

Work with search results

Play a specific moment

  1. Hover over the thumbnail preview strip to scrub through the clip.
  2. Select a frame to play that moment.

View a transcription

Select the transcription icon on a result clip. The transcription appears in a modal.

View all clips from a video

  1. Select See Full Video on any result clip. A side panel opens with the full video at the top and all matching clips listed below, sorted by rank:
  2. Select any clip to play it.

Analyze a video

If the Pegasus video understanding model is enabled for your index, select the Analyze button in the side panel to analyze your video and generate text based on its content.

View the code snippet

Select View code to see the request as cURL, Python, or JavaScript. Copy and paste the snippet into your application.