Venice AI

Use Venice AI for chat, image generation, embeddings, and more

Actions9

Overview

This node integrates with the Venice AI platform to create vector embeddings from text input. Embeddings are numerical representations of text that capture semantic meaning, useful for tasks like similarity search, clustering, recommendation systems, and natural language understanding.

Typical use cases include:

  • Generating embeddings for documents or sentences to enable semantic search.
  • Creating feature vectors for machine learning models.
  • Comparing text similarity by calculating distances between embeddings.

For example, you can input a product description and get its embedding vector to find similar products in a catalog.

Properties

Name Meaning
Model The ID of the embedding model to use (e.g., "text-embedding-bge-m3").
Input The text string for which to generate the embedding vector.
Encoding Format The format of the returned embedding: either as an array of floats ("float") or encoded as Base64 ("base64").

Output

The output is a JSON object containing the response from the Venice AI embeddings API. It typically includes the generated embedding vector corresponding to the input text.

  • If Encoding Format is set to "float", the embedding will be an array of floating-point numbers.
  • If set to "base64", the embedding will be a Base64-encoded string representing the vector.

No binary data output is produced for this operation.

Dependencies

  • Requires an active Venice AI API key credential configured in n8n.
  • The node makes HTTP POST requests to the /embeddings endpoint of the Venice AI API.
  • No additional environment variables are needed beyond the API authentication setup.

Troubleshooting

  • Missing or invalid API credentials: Ensure your Venice AI API key is correctly configured in n8n credentials.
  • Invalid model ID: Using a non-existent or unsupported embedding model ID will cause API errors. Verify the model name is correct.
  • Empty or invalid input text: The input text must be a non-empty string; otherwise, the API may return an error or empty embeddings.
  • API request failures: Network issues or API downtime can cause request failures. Check connectivity and Venice AI service status.
  • Unexpected response format: If the encoding format does not match expected values ("float" or "base64"), the output may be unusable.

Links and References

Discussion