Using AI
AI Filter
Using AI
AI Filter
This document explains the AI Filter node, which uses natural language conditions and AI to filter data by comparing two inputs.
Node Inputs
Required Fields
-
Filter By: Main content to filter
-
Value: The output you want to pass if the condition is met
-
Condition: Natural language comparison rule
Example: “Is the provided text in Spanish”
Optional Fields
- Output Blank Value: Return blanks for non-matches
- Temperature: Controls decision consistency (0-1)
- Cache Response: Save responses for reuse
Show As Input Options
You can expose these fields as inputs:
- Condition
- Temperature
Node Output
- Filtered Output: Values that meet your condition
Node Functionality
The AI Filter node:
- Compares paired values
- Uses natural language rules
- Evaluates matching criteria
Available AI Models
- Claude 3.5 Sonnet
- Claude 3 Haiku
- OpenAI o1
- OpenAI o1 mini
- GPT-4o
- GPT-4o Mini
- Gemini 1.5 Pro/Flash
- And more
Important Considerations
- Expert models (OpenAI o1) cost 30 credits, advanced models (GPT-4o & Claude 3.5) cost 20 credits, and standard models cost 2 credits per run
- You can drop the credit cost to 1 by providing your own API key under the credentials page
- Values and Filter By lists must match in length
- Write clear comparison conditions for accurate outputs
In summary, the AI Filter node helps you filter content by comparing pairs of values using natural language rules, perfect for complex matching and filtering tasks.