Actions20
- AI Scrape Actions
- Analyze Sentiment Actions
- Convert to SQL Actions
- Generate Embedding Actions
- HTML to Any Actions
- Image Generation Actions
- Make Prediction Actions
- NSFW Detection Actions
- Object Detection Actions
- Process Image Actions
- Profanity Detection Actions
- Search Web Actions
- Spam Detection Actions
- Speech to Text Actions
- Spell Check Actions
- Summary Actions
- Text to Speech Actions
- Translate Actions
- Translate Image Actions
- Web Suggestion Actions
Overview
The "Process Image" operation in this node allows users to analyze and extract information from images using a descriptive prompt. It supports processing images either by providing a direct URL or by referencing an image stored in a file storage system via a key. Additionally, it can handle multi-page documents by specifying a page range to process.
This node is beneficial in scenarios where automated image understanding or data extraction is needed, such as:
- Extracting textual or contextual information from images for indexing or search.
- Analyzing specific parts of multi-page scanned documents or PDFs.
- Automating metadata generation based on image content descriptions.
For example, a user might provide a prompt like "Describe the objects and text in the image" along with an image URL to get a detailed analysis of that image's contents.
Properties
| Name | Meaning |
|---|---|
| Prompt | The descriptive text or instructions used to guide the image processing or data extraction. |
| Image Source | Selects the source of the image: either an "Image URL" or a "File Store Key" referencing stored files. |
| Image URL | The web address of the image to be processed (required if Image Source is "Image URL"). |
| File Store Key | The identifier key for an image stored in Jigsawstack File Storage (required if Image Source is "File Store Key"). |
| Page Range | Specifies which pages to process in multi-page documents, with options for Start Page and End Page numbers. |
Output
The node outputs JSON data containing the results of the image processing based on the provided prompt. This typically includes extracted textual descriptions, recognized objects, or other analyzed data derived from the image content.
If the input image is multi-page, the output may include results segmented by page according to the specified page range.
No binary data output is indicated for this operation.
Dependencies
- Requires an API key credential for authenticating with the JigsawStack API.
- The node communicates with the JigsawStack API endpoint at
https://api.jigsawstack.com/v1. - For images stored in file storage, access to Jigsawstack File Storage is necessary.
Troubleshooting
- Invalid or missing API key: Ensure the API key credential is correctly configured in n8n; otherwise, authentication will fail.
- Incorrect image source selection: If "Image URL" is selected but no valid URL is provided, or if "File Store Key" is selected without a proper key, the node will error out.
- Page range errors: Specifying invalid page numbers (e.g., start page greater than end page) may cause unexpected behavior or errors.
- Network issues: Connectivity problems to the JigsawStack API endpoint will prevent successful execution.
- Unsupported image formats or corrupted images: The API might reject unsupported or damaged images, leading to errors.
Links and References
- JigsawStack API Documentation (for detailed API usage and capabilities)
- n8n Documentation on Creating Custom Nodes