Definition:
This Variable Extractor node utilizes a "large language model" to analyze and interpret natural language input, extracting the user-defined variable parameters in a structured format.
How to configure
Model:
From the model dropdown, select the large language model you wish to use. You can adjust the "temperature" of the language model, which dictate the degree of divergence (or randomness) of the model. Higher values lead to a more creative and varied response, while lower value generates a more focused output.
Detailed explanation is as follows:
| Configuration Options | Status | Description |
|---|---|---|
| Temperature Switch | Off | The model’s output follows a fixed probability distribution, resulting in more stable and deterministic outputs. This is suitable for tasks requiring high accuracy and consistency, such as parameter extraction and factual queries. |
| Temperature Switch | on | Enables control over output diversity and randomness, as the model's probability distribution depends on the selected temperature value. |
| Temperature Value | Higher (approaching 1) | Produces more diverse and creative content with greater variability. It is suitable for brainstorming or open-ended task, though it may reduce accuracy and consistency. |
| Temperature Value | Lower (approaching 0) | The model output is less divergent, generating more focused and predictable results with limited randomness. It is suitable for tasks requiring precise and stable outputs, such as data extraction. |
Input Variable:
This refers to the source of the natural language data input, which can be either:
- The default {x}Query from the start node in the workflow
- The output variable from the previous node
Extraction Parameters:
Click "+" to add and configure "extraction parameters." Each parameter requires you to fill in 3 variables: "extraction prompt," "name," and "type."
- Extraction Prompt: Provide a clear description of the content to be extracted, with a specific name (e.g., Extract the phone number).
- Name: Define a custom name or identifier for the extracted data (e.g., customer-phone).
- Type: Mention the data type of the output variable (e.g., string, Array[String]).
An example of Input text is: "My phone number is 123456, email is xxxxxx@airdroid.com, and order number is 987654." Here:
| Type | Output |
|---|---|
| String | “123456，xxxxxx@airdroid.com，987654” |
| Array[String] | [ "123456", "xxxxxx@airdroid.com", "987654" ] |
Example display
It’s recommended to provide additional prompts to help the model extract complex variables more accurately and precisely.
Simple Case - Complete Example
Use Case (Goal): Extract important or relevant information from user input.
Start Node:
Variable Extractor: Set extraction parameters with:
- Extraction Prompt: Order number, email
- Name: order_infos
- Type: string
Example user input: "I want to check if my order has been shipped, but I can't find any information about the product. My order number is 12345678, and my email is xxxxxx@airdroid.com. Please help me find it."
Response Output:
- "Name": "order_infos"
- "Type": "string"
- "Value": "12345678, xxxxxx@airdroid.com"
Leave a Reply.