Skip to main content

Get Multimodal Embeddings

Generates embeddings for text and images using Google Vertex AI's multimodal embedding models.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.
info

If the ContinueOnError property is true, no error is caught when the project is executed, even if a Catch node is used.

Inputs​

  • Connection Id - The unique identifier of the connection to Vertex AI, typically obtained from the Connect node.
  • Text - The text for which to generate embeddings.
  • Target Image Path - The file path to the image for which to generate embeddings.

Options​

  • Model - The embedding model to use. Default is "multimodalembedding@001".
  • Locations - Google Cloud region for the service. Default is "us-central1".
  • Publishers - Publisher of the model. Default is "google".

Output​

  • Response - The generated embeddings from the Vertex AI model as an object.

How It Works​

The Get Multimodal Embeddings node generates embeddings for text, images, or both using Vertex AI's multimodal embedding models. When executed, the node:

  1. Validates the connection ID and retrieves the authentication token
  2. Validates that either text or image path (or both) are provided
  3. Reads the image file if an image path is provided
  4. Encodes the image in base64 format
  5. Constructs a request with the text and/or image data
  6. Sends the request to the Vertex AI multimodal embedding model endpoint
  7. Processes the response and returns it

Requirements​

  • A valid connection to Vertex AI established with the Connect node
  • Valid Google Cloud credentials with appropriate permissions
  • A properly configured Vertex AI multimodal embedding model
  • Either text input, image file path, or both
  • Access to the image file if an image path is provided

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection ID
  • Both text and image path are empty
  • Invalid image file path
  • File read errors
  • Invalid parameter values
  • Missing required parameters
  • Invalid model selection
  • Network connectivity issues
  • Vertex AI service errors
  • Authentication failures

Usage Notes​

  • The Connection ID must be obtained from a successful Connect node execution
  • Either text, image path, or both must be provided
  • For text-only embeddings, it's recommended to use the Get Text Embeddings node instead
  • The image file must be accessible from the specified path
  • The model generates embeddings that can be used for similarity comparisons
  • The Locations parameter should match where your Vertex AI resources are deployed
  • Embeddings are numerical representations useful for machine learning tasks
  • The response contains embedding vectors that can be used for semantic search, clustering, or classification