Extracting Information
Extracting Information actions in Lleverage allow you to pull content from various sources and make it available for use in your workflow. These specialized actions help transform data from websites, documents, and images into usable text that can be processed by other actions.
Extracting Information Actions in Lleverage
Extracting Information actions in Lleverage allow you to pull content from various sources and make it available for use in your workflow. These specialized actions help transform data from websites, documents, and images into usable text that can be processed by other actions.
Key Features
Multiple source options including websites, documents, and images
Automatic text extraction from various file formats
Document conversion capabilities for processing complex content
OCR functionality for images containing text
Seamless integration with other workflow actions
How to Add Extracting Information Actions
Open the Add Action menu using one of three methods:
Click the "Add Action" button in the top left corner
Click on a connection circle on an existing action card
Click and drag from one action to create a connection
Select "Extracting Information" from the categories
Choose one of the four extraction actions:
Scrape Website
Extract Text from Document
Convert Document to Images
Extract Text from Images
Click on your chosen action to add it to your canvas
💡 All extraction actions share a similar card structure with a title, icon, variable output, and configuration area.
How to Configure Extraction Actions
How to Use Scrape Website
Provide a URL in the input field
Set the extraction depth:
Single page: Extracts content from only the specified URL
Direct links: Extracts content from the specified URL and pages directly linked from it
Links of links: Performs a deeper crawl, including pages linked from direct links
⚠️ Be cautious when testing this action with larger websites, as it may not be as fast as expected for extensive crawling. Consider using an integration action for more complex website crawling if necessary.
How to Use Extract Text from Document
Specify the file input in the configuration area
This can be a URL or a file input from a trigger action (using a variable)
Supports multiple file types including PDF, Word, Excel, and CSV
💡 This action automatically extracts readable text content from the specified document.
How to Use Convert Document to Images
Specify the file input in the configuration area
This can be a URL or a file input from a trigger action (using a variable)
The action will convert document pages to image format
💡 This is particularly useful when you need to process document content as images rather than text.
How to Use Extract Text from Images
Provide an image URL or specify a file input variable
The action will use OCR technology to extract any text present in the image
💡 This action is ideal for processing screenshots, photos of documents, or any images containing text.
Important Considerations
All extraction actions require their respective input fields to be filled
Each extraction action has only one required configuration field
File uploads are handled through variables from trigger actions, not direct uploads
The extraction results can be referenced using the variable output of each action
These actions are specifically built by Lleverage for pulling information that can be used within workflows
⚠️ For optimal performance, ensure you're using the appropriate extraction action for your specific content type.
How Extraction Actions Work in Your Workflow
Add the appropriate extraction action based on your source material
Configure the action with the required input source
Connect the action to subsequent actions that will process the extracted information
When the workflow runs, the extraction action will pull content from the specified source
The extracted content becomes available as a variable for other actions to use
💡 Extraction actions are often used early in a workflow to gather information for AI processing in subsequent steps.
Last updated