Overview
The Data Input node serves as the entry point for external data into your workflow. It provides multiple input methods to accommodate different data sources and types, making it a versatile component for workflow integration and automation.
Input Configuration Sections
Data Section
The Data section provides a text input area for receiving structured or unstructured data from external sources. This section features:
Expandable Interface: Click the arrow icon to expand or collapse this section for better workspace management
Information Icon: Provides contextual help and guidance about data input formatting
Text Input Field: A large text area where external data can be entered or received when the workflow is triggered via API calls
External Integration: This field automatically populates when your workflow is called from external sources, making it ideal for API-driven workflows
File Section
The File section handles external file references and links with advanced processing options:
Link Input Field: Contains placeholder text "Link goes here" where you can paste or specify URLs to external files
Upload Icon: The upload button (represented by an up arrow icon) allows you to reference or process files from external URLs
Settings Icon: Opens file processing configuration options
Information Icon: Offers help documentation specific to file link processing
File Processing Options
When you click the settings icon in the File section, a configuration modal appears with processing methods and OCR options:
File Processing Methods
Convert files to text
Extracts and processes the text content from the file
Ideal for documents, PDFs, and text-based files where you need the content processed
Automatically converts file content into readable text format for workflow processing
When selected, provides additional OCR Type options for optimal text extraction
Pass file URL (Default selection)
Sends the file URL without converting the contents
Useful when you need to reference the file location rather than process its contents
Maintains the original file format and simply passes the URL to subsequent workflow steps
OCR Type Options
When "Convert files to text" is selected, you can choose from three OCR (Optical Character Recognition) methods:
Mistral OCR (Default selection)
Standard OCR processing using Mistral technology
Balanced performance for most document types
Efficient processing for typical text extraction needs
Google OCR
Utilizes Google's advanced OCR technology
High accuracy for complex document layouts
Excellent for documents with varied formatting
Vision OCR
Advanced vision-based OCR processing
Recommended for more complex images and documents
Superior performance on challenging visual content, handwritten text, and complex layouts
Click "Save" to apply your selected file processing method and OCR type.
Uploaded Files Section
The Uploaded files section manages direct file uploads to your workflow:
File Management Interface: Click to open the uploaded files modal
Information Icon: Provides guidance on supported file types and upload procedures
Menu Icon: Additional options for file management and organization
Uploaded Files Modal
The uploaded files interface features:
Extract Text Mode: Shows "Extract Text" at the top, indicating the current processing mode
File Display Area: Shows uploaded files with management options
Copy and Link Icons: Allow you to copy file references or create shareable links
File Organization: Manage multiple uploaded files in a clean, organized interface
Node Identification
Unique Node ID
Each Data Input node includes a unique identifier displayed at the bottom:
ID Format: Shows as "ID: varInputNode_[timestamp]_[random]" (e.g., "varInputNode_1750354193025_0.2189")
Copy Function: Click the copy icon to copy the node ID for reference in API calls or workflow configurations
API Integration: This ID is used when making external API calls to trigger the workflow
Configuration Best Practices
Data Input Usage
Use the Data section for structured data like JSON, CSV content, or plain text
Configure appropriate data validation based on expected input formats
Consider data size limitations for optimal workflow performance
File Processing Selection
Choose "Convert files to text" when you need to analyze or process file contents
Select the appropriate OCR type based on your document complexity:
Mistral OCR: For standard documents and efficient processing
Google OCR: For complex layouts and high accuracy requirements
Vision OCR: For challenging images, handwritten text, and complex visual content
Select "Pass file URL" when other workflow components need direct file access
Consider file types and sizes when selecting processing methods
OCR Type Selection Guidelines
Standard Documents: Use Mistral OCR for typical PDFs, Word documents, and simple images
Complex Layouts: Use Google OCR for documents with tables, multiple columns, or varied formatting
Visual Content: Use Vision OCR for scanned documents, handwritten text, or images with complex visual elements
Performance Considerations: Mistral OCR offers faster processing, while Vision OCR provides highest accuracy for complex content
File Upload Management
Organize uploaded files with descriptive names for easier workflow management
Use the copy and link functions to reference files in other workflow components
Monitor file storage and cleanup unused files to maintain optimal performance
Integration Considerations
The Data Input node requires proper configuration for external API access. Ensure your workflow has the necessary authentication and permissions configured. The node's unique ID is essential for API integration, allowing external systems to trigger your workflow with specific data inputs.
This node serves as a critical bridge between external data sources and your workflow processing, providing flexible input options while maintaining data integrity and processing efficiency.