This quickstart guide provides a simplified introduction to creating embeddings using the TwelveLabs Video Understanding Platform. It includes the following:

• A basic working example
• Minimal implementation details
• Core parameters for common use cases

For a comprehensive guide, see the Create embeddings section.

Key concepts

This section explains the key concepts and terminology used in this guide:

• Asset: Your uploaded content
• Embedding: Vector representation of your content.

Workflow

The platform generates embeddings for video, audio, image, text, and combined text and image content. For video, audio, and image embeddings, upload your files and create assets first. For text embeddings, provide your text directly. The platform processes your content and returns vector representations you can use for anomaly detection, diversity sorting, sentiment analysis, recommendations, building Retrieval-Augmented Generation (RAG) systems, or other tasks.

Prerequisites

• To use the platform, you need an API key:

  1

  If you don’t have an account, sign up for a free account.

  2

  Go to the API Keys page.

  3

  Select the Copy icon next to your key.

• Depending on the programming language you are using, install the TwelveLabs SDK by entering one of the following commands:

  PythonNode.js

  $
  pip install twelvelabs

• Your media files must meet the following requirements:

  • For this guide: Video and audio files up to 10 minutes, images up to 5 MB
  • Model capabilities: See the complete requirements for video files, audio files, and image files

  For other upload methods with different limits, see the Upload methods page.

Starter code

Copy and paste the code below, replacing the placeholders surrounded by <> with your values.

1
import time
2
from twelvelabs import TwelveLabs, VideoInputRequest, MediaSource
3
4
# 1. Initialize the client
5
client = TwelveLabs(api_key="<YOUR_API_KEY>")
6
7
# 2. Upload a video
8
asset = client.assets.create(
9
    method="url",
10
    url="<YOUR_VIDEO_URL>" # Use direct links to raw media files. Video hosting platforms and cloud storage sharing links are not supported
11
    # Or use method="direct" and file=open("<PATH_TO_VIDEO_FILE>", "rb") to upload a file from the local file system
12
)
13
print(f"Created asset: id={asset.id}")
14
15
# 3. Create video embeddings
16
response = client.embed.v_2.create(
17
    input_type="video",
18
    model_name="marengo3.0",
19
    video=VideoInputRequest(
20
        media_source=MediaSource(
21
            asset_id=asset.id,
22
        ),
23
    ),
24
)
25
26
# 4. Process the results
27
print(f"\n{'='*80}")
28
print(f"EMBEDDINGS SUMMARY: {len(response.data)} total embeddings")
29
print(f"{'='*80}\n")
30
31
for idx, embedding_data in enumerate(response.data, 1):
32
    print(f"[{idx}/{len(response.data)}] {embedding_data.embedding_option.upper()} | {embedding_data.embedding_scope.upper()}")
33
    print(f"├─ Time range: {embedding_data.start_sec}s - {embedding_data.end_sec}s")
34
    print(f"├─ Dimensions: {len(embedding_data.embedding)}")
35
    print(f"└─ First 10 values: {embedding_data.embedding[:10]}")
36
    print()

Code explanation