Gemini icon

Gemini

Interact with Google Gemini AI

Overview

The node integrates with Google Gemini AI to perform various AI-powered tasks. Specifically, the "Generate Text" operation allows users to generate text completions based on a prompt using different Gemini language models. This is useful for content creation, brainstorming, drafting emails, generating code snippets, or any scenario where AI-generated text can assist.

For example, you could input a prompt like "Write a professional email to schedule a meeting next week," and the node will return a generated email draft. The node supports customization of the model used, response format, temperature (randomness), and maximum output length.

Properties

Name Meaning
Model The Gemini model to use for text generation. Options include: Gemini 1.5 Flash, Gemini 2.0 Flash, Gemini 2.5 Pro Preview, etc.
Prompt The text prompt to send to Gemini for generating text.
System Prompt Optional system instructions to guide the AI's behavior (e.g., "You are a helpful assistant...").
Response Format The format of the response returned by Gemini. Options: Plain text (text/plain) or JSON (application/json).
Temperature Controls randomness in responses from 0 (deterministic) to 2 (very random).
Max Output Tokens Maximum number of tokens to generate in the response (range 1 to 8192).

Output

The node outputs a JSON object containing:

  • response: The generated text from Gemini based on the prompt.
  • model: The name of the Gemini model used.
  • prompt: The original prompt sent to Gemini.
  • Any additional input JSON data passed through from the previous node.

Example output JSON:

{
  "response": "Generated text based on your prompt...",
  "model": "gemini-2.5-flash-preview-05-20",
  "prompt": "Your input prompt here"
}

No binary data is produced for this operation.

Dependencies

  • Requires an API key credential for authenticating requests to the Google Gemini API.
  • The node makes HTTP POST requests to the Gemini API endpoints for text generation.
  • Proper n8n credential setup for the Gemini API is necessary.

Troubleshooting

  • No valid response received from Gemini API: This error indicates that the API did not return usable text. Check your prompt and model selection.
  • Gemini API Error: General errors from the API, possibly due to invalid credentials, network issues, or exceeding rate limits.
  • Required properties missing: Ensure all required fields like "Prompt" and "Model" are set.
  • If the node fails but "Continue On Fail" is enabled, it will output an error message per item instead of stopping execution.

Links and References

Discussion