Skip to main content

Generate Batch Embeddings

Generate vector embeddings for multiple texts in a single batch request for improved efficiency.

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. Default: false.

Inputs​

  • Connection Id - Connection identifier from Connect node.
  • Texts - Array of texts to convert into embeddings.
  • Use Robomotion AI Credits - Use Robomotion credits instead of your own API key.

Options​

  • Model - Embedding model (text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002, Custom).
  • Custom Model - Custom model name (when Model is "Custom").
  • Dimensions - Output embedding dimensions for v3 models.
  • User - Unique end-user identifier.
  • Include Raw Response - Include usage info. Default: false.

Outputs​

  • Embeddings - Array of embedding vectors, one for each input text.
  • Raw Response - Full response with usage info (when enabled).

How It Works​

Processes multiple texts in a single API call:

  1. Validates connection and input array
  2. Sends all texts to embedding model
  3. Receives embeddings for all texts
  4. Returns array of embeddings

Usage Example​

Input:
- Texts: [
    "First document text",
    "Second document text",
    "Third document text"
  ]
- Model: text-embedding-3-small

Output:
- Embeddings: [
    [0.023, -0.015, ...],  // Embedding for first text
    [0.012, -0.034, ...],  // Embedding for second text
    [0.045, -0.021, ...]   // Embedding for third text
  ]

Requirements​

  • Connection Id from Connect node
  • Non-empty array of texts

Tips for RPA Developers​

  • Efficiency: Batch processing is faster and more cost-effective than individual calls
  • Timeout: Timeout increases automatically based on batch size (60 + 5 seconds per text, max 300)
  • Order: Embeddings are returned in the same order as input texts
  • Batch Size: Process up to hundreds of texts in a single call
  • Use Cases: Ideal for embedding entire documents, product catalogs, or knowledge bases

Common Errors​

"Texts array cannot be empty"

  • Provide at least one text in the array