Actions132
- AI Actions
- Extract Text From Document
- Check Content Policy
- Detect Adult Content
- Detect Brand
- Detect Color
- Detect Email Type
- Detect Faces
- Extract Entities
- Extract Contact Information
- Extract Customizable Information From Text
- Fuzzy Text Matcher
- Generate Image
- Generate JavaScript Code
- Generate Python Code
- Detect Language
- Detect Mood
- Extract Text From PDF
- Recognize Objects in Image
- Extract Text From Image
- Redact Sensitive Information From PDF
- Remove Background Image
- Summarize Text
- Transcribe
- Translate Text
- Image Actions
- Business Actions
- Convert Actions
- Generate Actions
- Crypto Actions
- Operator Actions
- Storage Actions
- Scheduler Actions
- Text Actions
- Chart Actions
- Code Actions
- Calculate Actions
- Date and Time Actions
- PDF Actions
- Compress PDF File
- Count PDF Pages
- Create Empty PDF
- Decrypt PDF
- Convert DOCX to PDF
- Draw Image on PDF
- Draw Text on PDF
- Encrypt PDF
- Convert HTML to PDF
- Convert Markdown to PDF
- Manage PDF Metadata
- Merge PDF Files
- Add PDF Pages
- Remove PDF Pages
- Resize PDF Pages
- Rotate PDF Pages
- Convert PDF to Base64
- Convert PDF to Image
- Split PDF File
- Add Image Watermark to PDF
- Add Text Watermark to PDF
- Shortened URL Actions
AI → Extract Text From Image
AI-generatedOverview
The node provides a utility to extract text from images using an AI-powered service. It is designed to analyze an image accessible via a URL and return the textual content found within that image. This functionality is useful in scenarios such as digitizing printed documents, extracting information from screenshots, or automating data entry from images.
For example, you could use this node to:
- Extract text from scanned receipts for expense tracking.
- Convert text in photos of signs or menus into editable text.
- Automate reading of text from images shared in workflows.
Properties
| Name | Meaning |
|---|---|
| Image URL | The URL of the image to analyze for text extraction. Example: https://example.com/image.jpg |
Output
The node outputs JSON data containing the extracted text from the provided image. The exact structure depends on the underlying AI service response but generally includes the recognized text content.
If the node supports binary data output (not explicitly shown here), it would typically represent the image or processed data in binary form, but this node focuses on returning textual data extracted from the image.
Dependencies
- Requires an API key credential for authentication with the external AI service at
https://prod.0codekit.com. - The node sends a POST request to the
/ai/picturetextrecognitionendpoint with the image URL in the request body. - Proper network access to the image URL must be ensured for successful text extraction.
Troubleshooting
- Invalid or inaccessible Image URL: Ensure the image URL is publicly accessible or accessible from the node's environment. Private or protected URLs may cause failures.
- Authentication errors: Verify that the API key credential is correctly configured and has necessary permissions.
- Empty or incorrect text output: The image quality or content might not be suitable for text recognition; try using clearer images or different formats.
- Network issues: Check connectivity to both the image URL and the external AI service endpoint.
Links and References
- Optical Character Recognition (OCR) Overview
- 0CodeKit API Documentation (if available) (hypothetical link based on baseURL)