This guide shows how you can create text embeddings using the Marengo video understanding model. For a list of available versions, complete specifications and input requirements for each version, see the Marengo page.

The Marengo video understanding model generates embeddings for all modalities in the same latent space. This shared space enables any-to-any searches across different types of content.

For details on how your usage is measured and billed, see the Pricing page.

Key concepts

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

• Embedding: Vector representation of your content.

Workflow

To create text embeddings, you provide text directly to the platform. The platform processes text synchronously, and the embeddings are available immediately.

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

Complete example

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

1
from twelvelabs import TwelveLabs, TextInputRequest
2
3
# 1. Initialize the client
4
client = TwelveLabs(api_key="<YOUR_API_KEY>")
5
6
# 3. Create text embeddings
7
response = client.embed.v_2.create(
8
    input_type="text",
9
    model_name="marengo3.0",
10
    text=TextInputRequest(
11
        input_text="<YOUR_TEXT>"
12
    )
13
)
14
15
# 4. Process the results
16
print(f"Number of embeddings: {len(response.data)}")
17
for embedding_data in response.data:
18
    print(f"Embedding dimensions: {len(embedding_data.embedding)}")
19
    print(f"First 10 values: {embedding_data.embedding[:10]}")

Code explanation