Variable Extractor Node

Definition

This node utilizes a large language model to analyze and interpret natural language input, extracting user-defined variable parameters in a structured format.

How to Configure

Add the Variable Extractor node to the canvas, and click the node to configure it in the right panel. You can configure the Model, Input Variable, Extraction Parameters, and Example.

1. Model

Select the desired large language model from the dropdown. You can adjust the "temperature" to control the randomness of the model's output. A higher value (closer to 1) produces more diverse and creative content but may reduce accuracy and consistency. A lower value (closer to 0) generates focused, predictable results with limited randomness, suitable for tasks needing precise and stable outputs.

Details are as follows:

2. Input Variable (Required)

The input variable is the prerequisite variable for the Variable Extractor node and the source of natural language data. It includes:

• The default {x}Query from the start node of the workflow.
• The output variable from the previous node.

3. Extraction Parameters

Click "+" to add and configure "Extraction Parameters". Each parameter requires filling in 3 fields: "Extraction Prompt", defined "Name", and output parameter "Type".

• Extraction Prompt: Guides the Variable Extractor to extract specific content from the input text. Provide a clear extraction target description, supported by specific examples (e.g., extract order number, extract email address, extract phone number).
• Name: Define a custom name for the extracted data for later node reference (e.g., customer-phone).
• Type: Specify the data type of the output variable. Select this based on the overall workflow and the variable type requirements of subsequent nodes (e.g., string, Array[String]).

Sample input text: "I have 2 orders to check, the order numbers are: DDH2025042301, DDH2025042302."

The "Extraction Prompt" is "Order number". Based on the selected "Type", the output is as follows:

[
        "DDH2025042301",
        "DDH2025042302"
      ]

4. Example (Optional)

Example content provides optional extraction guidance and serves as part of the Variable Extractor's prompt. It explains how to select, ignore, normalize, or disambiguate variable values. It can include specific examples or use other formats.

It usually applies to these scenarios:

• The input text does not follow a fixed expression format.
• Multiple fields require simultaneous extraction.
• Fields easily confuse with one another.
• Rules are necessary for missing fields, multiple values, date formats, enum values, etc.

You can write the example content as natural language rules or use a "sample input + expected output" format. We recommend the following format:

Extract the following fields from the input text:
- Order_Number: The order number, usually starting with DDH
- Email: The user's email address
- Phone: The contact phone number
- Delivery_Date: The expected delivery date

Sample input:
Hello, I would like to check order DDH12345678. My email is xxxxxx@example.com, my phone number is 12345678, and I hope it can be delivered on May 1.

Expected output:
{
  "Order_Number": "DDH12345678",
  "Email": "xxxxxx@example.com",
  "Phone": "12345678",
  "Delivery_Date": "2026-05-01"
}

Rules:
If a field does not appear in the input, return an empty value for it.
If the same field appears multiple times, return a string or array based on the field type.

If extracting only one field, the Example can contain a single simple rule or sample. If extracting multiple fields, provide a complete sample input and state the expected output results for all fields.

Use Case

Sample input:

Hello, I would like to check order DDH12345678. My email is xxxxxx@example.com, and my phone number is 12345678.

Extraction parameters:
- Extraction prompt: Order number; Name: Order_Number; Type: String
- Extraction prompt: Email address; Name: Email; Type: String
- Extraction prompt: Phone number; Name: Phone; Type: String

Example:
Please extract the order number, email address, and phone number from the user input.
The order number usually starts with DDH.
If a field is not mentioned, return an empty value for that field.

This outputs the following results, successfully converting the user's natural language into structured parameters for subsequent workflow nodes.

{
  "Outputs": [
    {
      "Name": "$AllFound",
      "Type": "bool",
      "Value": true
    },
    {
      "Name": "Order_Number",
      "Type": "string",
      "Value": "DDH12345678"
    },
    {
      "Name": "Email",
      "Type": "string",
      "Value": "xxxxxx@example.com"
    },
    {
      "Name": "Phone",
      "Type": "string",
      "Value": "12345678"
    }
  ]
}