Gemini Search Tool icon

Gemini Search Tool

Use Google Gemini as a search tool

Overview

This node integrates with Google Gemini to perform search queries using various Gemini language models. It allows users to send a search query and receive a generated response based on the selected Gemini model, optionally restricting the search context or URLs. This node is useful for scenarios where you want to leverage advanced AI-powered search capabilities within an n8n workflow, such as retrieving summarized information, generating answers from web data, or augmenting data processing pipelines with contextual search results.

Practical examples include:

  • Automating research tasks by querying specific topics and extracting concise answers.
  • Enhancing customer support workflows by searching knowledge bases dynamically.
  • Filtering search results to specific domains or organizations for targeted insights.

Properties

Name Meaning
Query The search query text to execute with Gemini.
Model The Gemini model to use for the search. Options: Gemini 1.0 Pro, Gemini 1.5 Pro, Gemini 2.0 Flash, Gemini 2.5 Pro Preview, Gemini 2.5 Flash Preview.
Organization Context Optional organization name to provide additional context for the search.
Restrict Search to URLs Optional comma-separated list of URLs to restrict the search scope (e.g., example.com, docs.example.com).
Options Collection of optional parameters:
- Temperature Controls randomness in the response generation (range 0 to 1). Default is 0.6.
- Max Output Tokens Maximum number of tokens to generate in the response. Default is 2048.
- Custom System Instruction Override the default system instruction sent to the model.
- Return Full Response Boolean flag to return the full raw API response instead of just the processed result.
- Extract Source URL Boolean flag to extract the source URL from the response if available.

Output

The node outputs JSON data with the following structure:

  • result: The main textual response generated by the Gemini model based on the query.
  • query: The original search query string.
  • organization: The optional organization context used.
  • restrictedUrls: The optional restricted URLs used for the search.
  • sourceUrl (optional): If enabled, the extracted source URL from the response grounding metadata.
  • redirectedSourceUrl (optional): If enabled and applicable, the final redirected URL after following HTTP redirects.
  • fullResponse (optional): The complete raw response object from the Gemini API when requested.

The output does not include binary data.

Dependencies

  • Requires an API key credential for authenticating with the Gemini search API.
  • Uses the Axios library internally to handle HTTP requests, including fetching redirected URLs.
  • Requires proper configuration of the Gemini API credentials in n8n.

Troubleshooting

  • Common issues:

    • Missing or invalid API credentials will cause authentication failures.
    • Network timeouts or connectivity issues may prevent successful API calls.
    • Incorrectly formatted restricted URLs could lead to unexpected search results or errors.
    • Exceeding token limits or rate limits imposed by the Gemini API might cause errors.

  • Error messages:

    • Errors returned from the Gemini API are propagated; check the error message for details.
    • Timeout errors during URL redirection fetches are logged but do not block the main response.
    • If "continue on fail" is enabled, errors per item are returned in the output JSON under an error field.

To resolve errors:

  • Verify that the API key credential is correctly set up and valid.
  • Ensure network access to the Gemini API endpoints.
  • Validate input parameters, especially URLs and token limits.
  • Use the "Return Full Response" option to debug API responses.

Links and References

Discussion