Skip to main content

Create Embeddings

Generates vector embeddings from text using OpenAI's 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 connection ID for the OpenAI service.
  • Input Text - The text to generate embeddings for.

Options​

  • Model - The OpenAI model to use for embeddings. Options include:
    • Custom Model
    • text-embedding-ada-002
  • Custom Model - Specify a custom model name if "Custom Model" is selected.
  • Encoding Format - The format of the embeddings output. Options are "float" or "base64".
  • User - A unique identifier representing your end-user.

Output​

  • Embedding Vector - The generated embedding vector as a JSON object.

How It Works​

The Create Embeddings node uses OpenAI's embedding models to convert text into high-dimensional vectors that capture semantic meaning. When executed, the node:

  1. Validates the provided Connection Id
  2. Prepares the embedding request with the specified input text
  3. Configures all specified options for the model
  4. Sends the request to the selected OpenAI embedding model
  5. Processes the response and returns the embedding vector

Requirements​

  • A valid OpenAI API key (Robomotion Credits cannot be used with this node)
  • An active OpenAI connection
  • Input text to convert to embeddings

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection Id
  • Empty or invalid Input Text
  • Invalid model selection
  • OpenAI API errors

Usage Notes​

  • This node does not support Robomotion Credits, only direct OpenAI API keys
  • The default model is text-embedding-ada-002 which is optimized for text embeddings
  • Embeddings capture semantic meaning and can be used for similarity comparisons
  • The encoding format can be set to "base64" for more compact representation
  • Embeddings are commonly used in search, clustering, and recommendation systems
  • The user parameter can be used to track usage by end-user