This guide shows how you can create text embeddings.

The following table lists the available models for generating text embeddings and their key characteristics:

Model	Description	Dimensions	Max tokens	Similarity metric
Marengo 3.0	TEnhanced model with sports intelligence and extended content support. For a list of the new features, see the New in Marengo 3.0 section.	512	500	Cosine similarity
Marengo 2.7	Video embedding model for multimodal search.	1024	77	Cosine similarity

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.

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:

$ pip install twelvelabs

Complete example

This complete example shows how you can create text embeddings. Ensure you replace the placeholders surrounded by <> with your values.

1 from typing import List
2 
3 from twelvelabs import TwelveLabs
4 from twelvelabs.types import BaseSegment
5 
6 # 1. Initialize the client
7 client = TwelveLabs(api_key="<YOUR_API_KEY>")
8 
9 # 2. Create text embeddings
10 res = client.embed.create(
11     model_name="marengo3.0",
12     text="<YOUR_TEXT>",
13 )
14 
15 # 3. Process the results
16 def print_segments(segments: List[BaseSegment], max_elements: int = 5):
17     for segment in segments:
18         first_few = segment.float_[:max_elements]
19         print(
20             f"  embeddings: [{', '.join(str(x) for x in first_few)}...] (total: {len(segment.float_)} values)"
21         )
22 
23 print("Created text embedding")
24 if res.text_embedding is not None and res.text_embedding.segments is not None:
25     print_segments(res.text_embedding.segments)

Step-by-step guide

Python

Node.js

Import the SDK and initialize the client

Create a client instance to interact with the TwelveLabs Video Understanding Platform.
Function call: You call the constructor of the TwelveLabs class.
Parameters:

api_key: The API key to authenticate your requests to the platform.

Return value: An object of type TwelveLabs configured for making API calls.

Create text embeddings

Function call: You call the embed.create function.
Parameters:

model_name: The name of the model you want to use (example: “marengo3.0”).
text: The text for which you wish to create an embedding.
(Optional) text_truncate: A string that specifies how the platform handles text that exceeds token limits.

Available options by model version:

Marengo 3.0: This parameter is deprecated. The platform automatically truncates text exceeding 500 tokens from the end.

Marengo 2.7: Specifies truncation method for text exceeding 77 tokens:
- start: Removes tokens from the beginning
- end: Removes tokens from the end (default)
- none: Returns an error if the text is longer than the maximum token limit.

Return value: The response contains the following fields:

text_embedding: An object that contains the embedding data for your text. It includes the following fields:
- segments: An object that contains the following:
  - float_: An array of floats representing the embedding
- metadata: An object that contains metadata about the embedding.
model_name: The name of the video understanding model the platform has used to create this embedding.

Process the results

This example prints the results to the standard output.