Overview
This node sends images along with a user prompt to the Claude AI model for analysis. It is useful for scenarios where you want to get descriptive or analytical responses about images, such as image content description, object recognition, or contextual analysis. For example, you can provide URLs of images and ask Claude to describe what is seen or interpret the images in a specific language.
Use Case Examples
- Analyzing product images to generate descriptions for e-commerce listings.
- Interpreting visual content in images for accessibility purposes.
- Generating captions or insights about images for social media content.
Properties
| Name | Meaning |
|---|---|
| Model | Selects the Claude AI model variant to use for image analysis. |
| System Prompt | A system-level instruction or context to guide the AI's responses, e.g., language or style instructions. |
| User Prompt | The main question or instruction to send to Claude about the images. This is required. |
| Image URLs | Comma separated list of image URLs to be analyzed by Claude. |
Output
JSON
json- The JSON response from the Claude API containing the analysis or description of the images based on the user prompt.
Dependencies
- Requires an API key credential for the Claude API (referred to as claudeApi).
Troubleshooting
- Ensure the API token is valid and has the necessary permissions to access the Claude API.
- Verify that the image URLs are accessible and publicly reachable by the Claude API service.
- Check that the user prompt is provided and not empty, as it is required for the request.
- If the API returns errors related to request format, verify that the image URLs are correctly formatted and separated by commas.
- Network issues or API downtime can cause request failures; retry or check service status if errors persist.