Featherless icon

Featherless

Interact with Featherless API

Chat

AI-generated

Overview

This node integrates with the Featherless API to send chat messages to a specified language model. It allows users to interact with AI models by providing a system prompt and user message, then receiving generated responses. This is useful for building conversational agents, virtual assistants, or any application requiring natural language interaction.

Typical use cases include:

  • Creating chatbots that respond based on custom instructions.
  • Generating text completions or replies in workflows.
  • Experimenting with different AI models by specifying their IDs.

For example, you can set a system prompt like "You are a helpful assistant" and send user questions to get AI-generated answers.

Properties

Name Meaning
Model Name or ID The identifier of the AI model to use for generating chat completions. You can find available models at https://featherless.ai/models.
System Prompt A system-level message that sets the behavior or persona of the assistant (e.g., "You are a helpful assistant..."). This helps guide the AI's responses.
Message The actual user message or query to send to the chat model.
Temperature Controls randomness in the output. Higher values (e.g., 0.9) make output more diverse; lower values make it more focused and deterministic.
Additional Fields Optional parameters to fine-tune the generation:
- Frequency Penalty: Penalizes new tokens based on their existing frequency (-2.0 to 2.0).
- Max Tokens: Maximum number of tokens to generate.
- Presence Penalty: Penalizes new tokens based on whether they appear in the text so far (-2.0 to 2.0).
- Top P: Nucleus sampling parameter (alternative to temperature).

Output

The node outputs an array of items where each item contains a json field with the following structure:

{
  "response": "string"
}
  • response: The trimmed text content generated by the Featherless chat model in reply to the input message.

No binary data is produced by this node.

Dependencies

  • Requires an API key credential for authenticating with the Featherless API.
  • Makes HTTP POST requests to https://api.featherless.ai/v1/chat/completions.
  • The node expects the Featherless API to return a JSON response containing a choices array with message content.

Troubleshooting

  • Missing or invalid API key: The node will throw an error if no valid API key is provided. Ensure your API key credential is correctly configured.
  • Invalid response format: If the API response does not contain the expected message content, the node throws an error indicating an invalid response format. This could be due to API changes or network issues.
  • Network errors or timeouts: Standard HTTP request failures may occur; verify network connectivity and API availability.
  • Parameter validation: Make sure required fields like Model and Message are provided; missing these will cause errors.

If you want the node to continue processing other items after an error, enable the "Continue On Fail" option.

Links and References

Discussion