Groq icon

Groq

Use Groq models via the AI SDK
Join our community

Actions2

Overview

This node integrates with the Groq AI SDK to generate text completions or structured objects using Groq models. It supports two main input modes: a simple single prompt or a conversation-style input with multiple messages, allowing flexible interaction styles with the AI model.

Common scenarios include:

  • Generating natural language text based on a prompt (e.g., writing assistance, content generation).
  • Conducting multi-turn conversations by providing message histories.
  • Producing structured data outputs conforming to a JSON schema (not covered here as the operation is "Generate Text").

Practical examples:

  • Using a single prompt like "Write a summary of today's news" to get a concise text output.
  • Providing a chat history with system, user, and assistant roles to simulate conversational AI responses.
  • Adjusting generation parameters such as max tokens and temperature to control output length and creativity.

Properties

Name Meaning
Model Name or ID Select a Groq model from a dynamically loaded list or specify an ID via expression. Examples include "gemma2-9b-it" or "llama-3.1-8b-instant".
Input Type Choose how to provide input:
• Simple Prompt: Use a single text prompt.
• Messages: Provide a conversation with multiple messages.
System (Shown if Input Type is Simple Prompt) A system prompt that guides the model's behavior, e.g., "You are a helpful assistant." Optional but recommended for context setting.
Prompt (Shown if Input Type is Simple Prompt) The single text prompt to generate a completion for. Can use expressions to pull data from previous nodes.
Messages (Shown if Input Type is Messages and "Messages as JSON" is false) A collection of messages forming a conversation. Each message has a role (System, User, Assistant) and corresponding content.
Messages as JSON (Shown if Input Type is Messages) Boolean flag to input messages as a raw JSON array instead of UI fields.
Messages (JSON) (Shown if Input Type is Messages and "Messages as JSON" is true) JSON string representing an array of message objects, each with role and content. Must be valid JSON.
Options Collection of optional parameters:
• Max Tokens: Maximum number of tokens to generate (default 2048).
• Temperature: Controls randomness; higher values produce more creative outputs (default 0.7).
• Include Request Body: Whether to include the full request body in the output for debugging or logging purposes.

Output

The node outputs a JSON object per input item containing detailed information about the generated text completion:

  • text: The generated text result, with any internal <think> tags removed.
  • reasoning: Extracted reasoning text if present inside <think> tags in the response.
  • finishReason: Reason why the generation finished (e.g., length limit reached).
  • usage: Token usage statistics including prompt tokens, completion tokens, total tokens, and cache hit/miss metrics.
  • response: Metadata about the API response such as response ID, model ID, timestamp, and headers.
  • warnings: Any warnings returned by the API.
  • Optionally, if enabled, the original request body sent to the API is included under request.body.

No binary data output is produced by this node.

Dependencies

  • Requires an active Groq API key credential configured in n8n.
  • Uses the Groq AI SDK (@ai-sdk/groq) and OpenAI-compatible client libraries internally.
  • Network access to https://api.groq.com for model listing and generation requests.

Troubleshooting

  • Missing API Key: If no API key is provided in credentials, the node throws an error "No API key provided in Groq credentials". Ensure the API key credential is set up correctly.
  • Invalid JSON in Messages (JSON): When using JSON input for messages, invalid JSON syntax will cause an error indicating the problem. Validate JSON format before running.
  • Invalid Message Structure: Messages must be an array of objects with role (system/user/assistant) and content strings. Incorrect structure triggers validation errors.
  • Schema Errors: Not applicable for "Generate Text" operation, but for other operations, invalid JSON schemas cause errors.
  • API Errors: Any errors from the Groq API during generation are surfaced. Enabling "Continue On Fail" allows processing subsequent items despite errors.
  • Token Limits: Setting maxTokens too high may cause API rejections or long wait times. Adjust according to model limits.

Links and References

Discussion