Skip to main content

Intent Branch

Uses large language models to analyze input content and determine workflow branches based on intent recognition.

1. Overview​

  • Intent branching relies on LLMs for intent recognition, defaulting to using the previous node's output as the basis for intent judgment, with options to select outputs from other previous nodes
  • Supports setting multiple branches with natural language descriptions of different intents to configure rules for each branch
  • Supports configuring intent recognition branch nodes to carry workflow input-output records as contextual memory

2. Configuration​

  1. Node Input: The input for determining branch direction. Defaults to the previous node's output, can be manually changed to other previous nodes or multiple previous node outputs, and add custom text to combine as input. Note: This node must be directly or indirectly connected to the start node to select previous node output parameters.
  2. Model Selection: Choose the LLM for executing intent recognition judgment tasks. Options include linkai-3.5, linkai-4o, linkai-4o-mini, kimi
  3. Memory: Use workflow input-output records as context to help the model make better reasoning decisions or responses based on historical conversation context. You can choose whether to enable memory and set the number of workflow memory rounds this node retains, supporting up to 10 rounds of memory.
Note

  1. Each round of memory refers to the start node input content and end node output content generated from one complete workflow run (excluding intermediate process content).

  2. Workflow memory content may have been processed through multiple nodes unrelated to this node, so please choose whether to enable memory functionality based on actual needs.

  3. Current memory is retained for 30 minutes by default

  1. Branches:
  • Add Branch: Add different branches and write branch names and descriptions for each (more detailed descriptions lead to more precise selection). Branch selection will be based on intent defined in branch descriptions to determine which branch the input satisfies.
  • Default Branch: When input doesn't satisfy any configured branch intents, the default branch process will be selected.