LLM Processing
The AI Agent will use LLMs to generate a text response based on the provided inputs and context.
Last updated
The AI Agent will use LLMs to generate a text response based on the provided inputs and context.
The LLM Processing action sends a prompt to a configured LLM at any point in the chat flow, returning the result for use in downstream actions.
Select an LLM Processing action from the tree to open its settings:
Input – the text prompt sent to the LLM. Supports chat variables.
Script – toggle to supply the input as a chat script expression instead.
Model – the LLM to use: DeepSeek V2 , GPT-4o , Qwen 2.5 , Llama 3.2
Temperature – controls response randomness. Range: 0.0–2.0. Default: 1.
System Prompt – prompt template used to provide instructions or context to the LLM when generating responses.
Script – toggle to supply the system prompt as a chat script expression instead.
Use Knowledge info to provide more context – toggles whether the LLM can access training sources from the LLM tab.
Resulting variable – the name of the chat variable that will store the LLM’s response.
Press Save to confirm edits.
The action branches into Success, Error, and Timeout outcomes. Nest subsequent actions under each branch as needed.
Last updated