Actions10
- Audio Actions
- Document Actions
- File Actions
- Image Actions
- Text Actions
- Video Actions
Overview
This node integrates with the Google Gemini generative language API to analyze documents. It supports analyzing documents provided either as URLs or as binary files. The node sends the document content to a specified Google Gemini model and retrieves an analysis response, which can be optionally simplified for easier consumption.
Common scenarios where this node is beneficial include:
- Extracting summaries or insights from PDF or text documents hosted online.
- Processing uploaded document files within an automation workflow to generate descriptions or extract key information.
- Integrating Google Gemini's advanced language understanding capabilities into document processing pipelines.
For example, a user could provide URLs of multiple PDFs to get concise summaries or upload scanned documents as binary data to extract textual insights.
Properties
| Name | Meaning |
|---|---|
| Server URL | The base URL of the Google Gemini API endpoint (default: https://generativelanguage.googleapis.com). |
| API Key | The API key credential used to authenticate requests to the Google Gemini API. |
| Model | The specific Google Gemini model to use for document analysis. Can be selected from a list or entered by ID. |
| Text Input | The prompt or question to guide the analysis, e.g., "What's in this document?". |
| Input Type | Specifies whether the input documents are provided as URLs (Document URL(s)) or as binary files (Binary File(s)). |
| URL(s) | One or more URLs pointing to the documents to analyze, separated by commas. Used if Input Type is URL. |
| Input Data Field Name(s) | The name(s) of the binary fields containing the document files to analyze, separated by commas. Used if Input Type is binary. |
| Simplify Output | Boolean flag indicating whether to simplify the API response for easier consumption (default: true). |
| Options | Additional options for the analysis request. Currently supports: |
| - Length of Description (Max Tokens) | Maximum number of tokens for the output description; fewer tokens produce shorter, less detailed results (default: 300). |
Output
The node outputs JSON data representing the analysis result returned by the Google Gemini API. If simplification is enabled, the output will be a more concise and user-friendly summary or description of the document content.
If binary input is used, the node processes the binary file data but does not output binary data itself; the output focuses on the textual analysis results.
Dependencies
- Requires access to the Google Gemini generative language API.
- An API key credential for authenticating requests to the Google Gemini API must be configured.
- The node expects the server URL and model ID to be correctly set according to the user's Google Gemini environment.
Troubleshooting
- Invalid API Key or Authentication Errors: Ensure the API key is valid, active, and has permissions to access the Google Gemini API.
- Incorrect Model ID: Verify that the model ID corresponds to an available and supported Google Gemini model.
- Malformed Document URLs: When using URLs, ensure they are accessible and point directly to the document files.
- Binary Field Names Not Found: When using binary input, confirm that the specified binary property names exist in the incoming data.
- Exceeded Token Limits: If the output is truncated or incomplete, try increasing the max output tokens option.
- Network or API Endpoint Issues: Confirm the server URL is reachable and correct.