Workflow Node: Extract data

[nitrag]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• Pleas do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing?

Yes, the LLM node has a limitation

2. Describe the feature you'd like to see

I need the LLM node to interpret a user question and extract certain ideas into variables. For instance, determine the users topic of interest. Currently it seems I have to instruct the LLM to respond with JSON and parse that using custom script.
Example: "I'm interested in red shoes"
LLM: "Determine the topic or idea the user is referring to" -> Assign to variable: topic.
Variable: topic=shoes

Example 2: "show me car dealerships in chicago"
LLM: "Determine if the user provided a location, if you cannot determine one return null" -> Assign to variable: location.
Variable: location=chicago

3. How will this feature improve your workflow or experience?

In a single step I can determine a variable needed to append to API for more detailed responses. Example a users location.

4. Additional context or comments

No response

5. Can you help us with this feature?

• I am interested in contributing to this feature.