Venice AI

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

Actions9

Overview

The node integrates with Venice AI services, providing access to various AI-powered functionalities such as chat completions, image generation and editing, audio text-to-speech conversion, embeddings creation, and model information retrieval. Specifically, for the Model - List operation, it fetches a list of available AI models filtered by type (e.g., text, image, embedding).

This node is beneficial when you want to dynamically retrieve and work with different AI models supported by Venice AI within your n8n workflows. For example, you might want to list all text-based models to select one for generating chat completions or list image models for generating images.

Properties

Name Meaning
Model Type Filter models by type. Options: All, Text, Image, Embedding, TTS (Text-to-Speech), Upscale

Output

  • The output is an array of JSON objects representing the models retrieved from Venice AI.
  • Each item in the output json contains details about a model, such as its ID, type, and other metadata as provided by the Venice AI API.
  • No binary data is produced for this operation.

Example output structure (simplified):

[
  {
    "id": "venice-uncensored",
    "type": "text",
    "name": "Venice Uncensored",
    "description": "A powerful text generation model"
  },
  {
    "id": "hidream",
    "type": "image",
    "name": "HiDream",
    "description": "Image generation model"
  }
]

Dependencies

  • Requires an API key credential for Venice AI service authentication.
  • The node makes HTTP requests to Venice AI endpoints to fetch model data.
  • No additional environment variables are explicitly required beyond the API credential.

Troubleshooting

  • Common issues:

    • If the API key is missing or invalid, the node will fail to authenticate and return an error.
    • Network connectivity problems can cause request failures.
    • Selecting an unsupported model type may result in empty responses.

  • Error messages:

    • Errors returned from the Venice AI API will be propagated. For example, unauthorized errors indicate credential issues.
    • If the node encounters unexpected response formats, it may throw parsing errors.

  • Resolution tips:

    • Ensure the API key credential is correctly configured and has necessary permissions.
    • Verify network access to Venice AI endpoints.
    • Use valid model types as per the property options.

Links and References

Discussion