Overview
The Agent Node is a versatile component that allows you to run a single AI agent with specific tools and capabilities. This node enables:- Execution of complex queries with customizable tools
- Integration with other workflows and nodes
- Flexible configuration of model parameters and system prompts
- Detailed conversation tracking and output management
Configuration Parameters
The Agent Node requires configuration of the agent’s behavior, tools, and model settings to effectively process queries.Node Configuration
- Query: Define the task or question for the agent to handle.
-
Tools
Select tools that the agent can use to accomplish its tasks. Tools can be of two types:
- Workflow Tools: Existing workflows that the agent can execute
- Node Tools: Individual nodes that the agent can utilize
Advanced Settings
Advanced Settings
- System Prompt: Define the agent’s persona and behavior guidelines with a custom system prompt.
- Model: Select the language model to power the agent. Note that the model must support function calling.
- Max Steps: Configure the maximum number of steps (1-50) the agent can take to complete the task.
Expected Inputs and Outputs
-
Inputs:
- The node accepts input data that can be referenced in the query using format strings.
-
Outputs:
- output: The final result produced by the agent
- conversation: A detailed log of the agent’s thought process and actions taken
Use Case Examples
- Web Search: Configure the node with Google Search tool and Web Content Extraction tool. Prompt the agent to do research anything from company information to finding contact information from name.
- Workflow Orchastrator: Setup an agent that has access to your workflows as tools so that it launches workflow to complete tasks given by the user.
Error Handling and Troubleshooting
- Model Compatibility: Ensure the selected model supports function calling. If you receive a compatibility error, switch to a supported model.
- Tool Configuration: Verify that all configured workflow and node tools exist and are accessible to the agent.
- Max Steps Limitation: If the agent isn’t completing tasks, consider increasing the max_steps parameter (up to 50) or breaking down the task into smaller components.