Embeddings

Generates embeddings for text content using Google's Gemini API with various task types.

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 obtained from the Connect node.
• Content - The text content to generate embeddings for.
• Compare Text - For Semantic Similarity task only - the text to compare against the Content.

Options

• Title - Title for RETRIEVAL_DOCUMENT task type.
• TaskType - The type of task for which the embeddings will be used. Options include:
  • Retrieval Query
  • Retrieval Document
  • Semantic Similarity
  • Classification
  • Clustering
  • Question Answering
  • Fact Verification
• Embedding Model - The model to use for generating embeddings. Default is "text-embedding-004".
• Output Dimensionality - Reduced dimension count (e.g., 256, 512, 768).
• Include Statistics - Whether to include token count and truncation information. Default is false.

Output

• Response - The generated embeddings or similarity score with associated metadata.

How It Works

The Embeddings node generates embeddings for text content using Google's Gemini API. When executed, the node:

1. Validates the provided connection ID and content
2. Configures the embedding model (defaults to "text-embedding-004" if not specified)
3. Sets optional parameters like task type, title, and output dimensionality
4. For Semantic Similarity task:
   • Generates embeddings for both Content and Compare Text
   • Calculates cosine similarity between the two embeddings
   • Returns the similarity score and optionally the embeddings themselves
5. For other task types:
   • Generates a single embedding for the Content
   • Returns the embedding values with metadata
6. Includes statistics if requested and available from the API

Requirements

• A valid Google Gemini API key
• Connection ID from a successful Connect node execution
• Text content to generate embeddings for

Error Handling

The node will return specific errors in the following cases:

• Empty or invalid Connection ID
• Empty Content
• Empty Compare Text (for Semantic Similarity task)
• Invalid output dimensionality value
• Title provided for non-RETRIEVAL_DOCUMENT task type
• API errors from Google's Gemini service

Usage Notes

• The Title option is only supported for RETRIEVAL_DOCUMENT task type
• Output dimensionality should be one of the common values: 256, 512, or 768
• For Semantic Similarity task, both Content and Compare Text are required
• Statistics include token count and truncation information when available
• The default embedding model is "text-embedding-004"
• Cosine similarity is used for Semantic Similarity calculations