Iteration
Last updated
Last updated
Sequentially performs the same operations on array elements until all results are outputted, functioning as a task batch processor. Iteration nodes typically work in conjunction with array variables.
For example, when processing long text translations, inputting all content directly into an LLM node may reach the single conversation limit. To address the issue, upstream nodes first split the long text into multiple chunks, then use iteration nodes to perform batch translations, thus avoiding the message limit of a single LLM conversation.
Using iteration nodes requires input values to be formatted as list objects. The node sequentially processes all elements in the array variable from the iteration start node, applying identical processing steps to each element. Each processing cycle is called an iteration, culminating in the final output.
An iteration node consists of three core components: Input Variables, Iteration Workflow, and Output Variables.
Input Variables: Accepts only Array type data. For more details about array variables, take refer to Extended Reading: What is an Arrays Variable?.
Iteration Workflow: Supports multiple workflow nodes to orchestrate task sequences within the iteration node.
Output Variables: Outputs only array variables (Array[List]). For other output formats, take refer to Extended Reading: Array to Text Conversion.
Enter the story title and outline in the Start Node.
Use a Generate Subtitles and Outlines Node to use LLM to generate the complete content from user input.
Use a Extract Subtitles and Outlines Node to convert the complete content into an array format.
Use an Iteration Node to wrap an LLM Node and generate content for each chapter through multiple iterations.
Add a Direct Answer Node inside the iteration node to achieve streaming output after each iteration.
Detailed Configuration Steps
Configure the story title (title) and outline (outline) in the Start Node.
Use a Generate Subtitles and Outlines Node to convert the story title and outline into complete text.
Use a Extract Subtitles and Outlines Node to convert the story text into an array (Array) structure. The parameter to extract is sections, and the parameter type is Array[Object].
The effectiveness of parameter extraction is influenced by the model's inference capability and the instructions given. Using a model with stronger inference capabilities and adding examples in the instructions can improve the parameter extraction results.
Use the array-formatted story outline as the input for the iteration node and process it within the iteration node using an LLM Node.
Configure the input variables GenerateOverallOutline/output and Iteration/item in the LLM Node.
Built-in variables for iteration: items[object] and index[number].
items[object] represents the input item for each iteration;
index[number] represents the current iteration round;
Configure a Direct Reply Node inside the iteration node to achieve streaming output after each iteration.
Complete debugging and preview.
Enter the story title and outline in the Start Node.
Use an LLM Node to generate subheadings and corresponding content for the article.
Use a Code Node to convert the complete content into an array format.
Use an Iteration Node to wrap an LLM Node and generate content for each chapter through multiple iterations.
Use a Template Conversion Node to convert the string array output from the iteration node back to a string.
Finally, add a Direct Reply Node to directly output the converted string.
The iteration node supports parallel processing, improving execution efficiency when enabled.
Below illustrates the comparison between parallel and sequential execution in the iteration node.
Parallel mode supports up to 10 concurrent iterations. When processing more than 10 tasks, the first 10 elements execute simultaneously, with remaining tasks processed after the completion of the initial batch.
Avoid placing Direct Answer, Variable Assignment, or Tool nodes within the iteration node to prevent potential errors.
Error response method
Iteration nodes process multiple tasks and may encounter errors during element processing. To prevent a single error from interrupting all tasks, configure the Error Response Method:
Terminated: Terminates the iteration node and outputs error messages when an exception is detected.
Continue on error: Ignores error messages and continues processing remaining elements. The output contains successful results with null values for errors.
Remove abnormal output: Ignores error messages and continues processing remaining elements. The output contains only successful results.
Input and output variables maintain a one-to-one correspondence. For example:
Input: [1, 2, 3]
Output: [result-1, result-2, result-3]
Error handling examples:
With Continue on error: [result-1, null, result-3]
With Remove abnormal output: [result-1, result-3]
Array variables can be generated via the following nodes as iteration node inputs:
The output variable of the iteration node is in array format and cannot be directly output. You can use a simple step to convert the array back to text.
Convert Using a Code Node
CODE Example:
Convert Using a Template Node
CODE Example:
