How do I configure the OpenAi function call agent node?#

An agent is used to extend the functionality of a Large Language Model or Chat Model with the use of additional nodes such as triggers, retrievers, loaders and output parsers. Agent nodes are distinct from Chain nodes in that they automatically determine the correct attached node to use for a given user input.

The OpenAi function call agent uses an OpenAi functions model passes prompts to an appropriate OpenAi function model.

Before you begin#

Step 1 - add the node#

Click + to open the nodes panel
Search for Agent in the node search field.
Click Ai Agent to open the node editor
Choose OpenAi function call agent from the Agent field.

Step 2 - choose how to handle prompts#

Prompt	Description	Additional information
Take from previous node automatically	Looks for `chatInput` parameter supplied by the preceding node	Execute previous nodes to load input data
Define below	Define JSON parameters that will be sent to a child node such as a Model, Operator, Memory or Tool. These should be defined based on the outputs from a preceding node in the pathway	Execute previous nodes to load input data

Step 3 - Add optional output parser#

Toggle Require specific output format so you can add an Output Parser node to the agent once you've completed initial configuration.

Step 4 - Add optional messages and steps#

Click Add option then choose from the following options:

Optional field	Description	Required
System message	Add or edit text used by the connected model to interpret and assemble output returned to the end user
Max iterations	Number of times the attached model should attempt to generate an answer to the user message
Return intermediate steps	Steps made by the attached model to generate output are sent to the Chat dialog for the user to check

Next step#

Then link to other optional nodes: * Learn about memory nodes * Learn about agent tool nodes * Learn about output parser nodes