Liquid Templating
An introduction to our powerful templating language
Last updated
Was this helpful?
An introduction to our powerful templating language
Last updated
Was this helpful?
is a templating language created by Shopify and used extensively by others to create dynamic content. It's useful for referencing variables, modifying text (for example truncating) and for creating basic logic (if statements, for loops etc).
Liquid can be used in most areas throughout our product, including:
Input Fields in Workflows
LLM Prompts
Text Steps
Knowledge Base Search Steps
JSON Steps
This section will walk through how to reference your pre-defined input variables.
Ensure that you have
If you did not enter a separate variable name, use the default variable name to reference the input value
Click the purple Variable Selector to see a list of your available inputs and select the desired input
In the example below, we walk through using our input variable value, and referencing it in our LLM Step using Liquid syntax.
Just like with inputs, you can reference the outputs of any prior step of your Workflow in any subsequent step.
Currently, step names are automatically defined incrementally, e.g. step_1 ,step_2 , step_3 , etc.
To reference the output of a step, simply click the step_number pill or manually type it in in the format {{step_12.output}} . If that step outputs JSON, then you can reference any of the sub-keys.
In the example below, we walk through how you can view the full list of available variables and use the proper syntax to call them within your Workflow.
One of the more useful applications for Liquid syntax is combining it with our Text Step to perform additional formatting and ensure your output looks exactly the way you desire.
The screenshot below showcases how we reference the output of previous steps (even pulling specific array elements as variables) to format our "step_2" into a more readable and organized output.
Liquid templating provides powerful capabilities for handling complex data structures in your Workflows. Below are advanced techniques for working with iterators, arrays, and structured data.
When working with the Iteration Step, you can use Liquid's for loops to process the output array elements. This pattern is commonly used to consolidate information from multiple iterations into a single output:
Basic Content Extraction
Extract and format content from search results or Knowledge Base searches:
Metadata Handling
Access and format metadata from Knowledge Base search results:
By mastering these advanced Liquid templating techniques, you can transform complex data structures into well-formatted outputs that serve as perfect inputs for subsequent steps in your Workflow.
For additional information regarding Liquid, we recommend reviewing .
