API Reference
SDKsSample appsIntegrationsDiscordPlayground

Typical workflows

This page provides an overview of common workflows for using the Twelve Labs Video Understanding Platform. Each workflow consists of a series of steps, with links to detailed documentation for each step.

All workflows involving uploading video content to the platform require asynchronous processing. You must wait for the video processing to complete before proceeding with the subsequent steps.

Prerequisites

  • To use the platform, you need an API key.
    • If you already have an account:
      1. Go to the API Key page.
      2. Click the Copy icon next to your key.
    • If you don't have an account:
      1. Sign up for a free account.
      2. Follow the steps above to retrieve your API key.

Search

Follow the steps in this section to search through your video content and find specific moments, scenes, or information. For an interactive implementation using the Python SDK, see the Quickstart Search Jupyter notebook.

Steps:

  1. Create an index, enabling the Marengo video understanding engine.
  2. Upload videos and monitor the processing.
  3. Perform a search request, using text or images as queries.

Notes:

  • The search scope is an individual index.
  • Results support pagination, filtering, sorting, and grouping.

Generate text from videos

Follow the steps in this section to generate texts based on your videos. For an interactive implementation using the Python SDK, see the Quickstart Generate Jupyter notebook.

Steps:

  1. Create an index, enabling the Pegasus video understanding engine.
  2. Upload videos and monitor the processing.
  3. Depending on your use case, generate one of the following:

Notes:

  • When generating open-ended texts, the platform supports streaming responses.

Classify

Follow the steps in this section to organize your videos into manageable and useful categories, making them easier to find, access, and use. For an interactive implementation using the Python SDK, see the Quickstart Classify Jupyter notebook.

Steps:

  1. Create an index, enabling the Marengo video understanding engine
  2. Upload videos and monitor the processing.
  3. Classify a set of videos or all the videos within an index.

Notes:

  • Results support filtering and pagination.

Create text, image, and audio embeddings

This workflow guides you through creating embeddings for text.

Steps:

  1. Create text, image, and audio embeddings.

Notes:

  • Creating text embeddings is a synchronous process.

Create video embeddings

This workflow guides you through creating embeddings for videos. For an interactive implementation using the Python SDK, see the Quickstart Embed Jupyter notebook.

Steps:

  1. Upload a video and monitor the processing.
  2. Retrieve the embeddings.

Extract video data

Follow the steps in this guide to extract various types of data from your videos, such as transcriptions, on-screen text, logos, and thumbnails.

Steps:

  1. Create an index, enabling the Marengo video understanding engine.
  2. Upload videos and monitor the processing.
  3. Depending on your use case: