Nodes

Nodes contain your agent logic. They process events, maintain conversation context, and generate responses from LLMs.

What is a Node?

Nodes are where the “thinking” happens in your agent system. It contain the business logic and LLM interactions.

Basic Example

1
from line.nodes import ReasoningNode
2
from line.events import AgentResponse
3
4
5
class ChatNode(ReasoningNode):
6
    def __init__(self, system_prompt, llm_client):
7
        super().__init__(system_prompt=system_prompt)
8
        self.llm_client = llm_client
9
10
    async def process_context(self, context):
11
        # Get conversation history and system prompt
12
        messages = self.format_for_llm(context.events)
13
14
        # Generate response from LLM
15
        response = await self.llm_client.generate(messages)
16
17
        # Yield response to be spoken to user
18
        yield AgentResponse(content=response)

Node Types

| Type | Description | |------|-------------| | Node | Base class for all nodes | | ReasoningNode | Template for conversational agents with automatic context management |

Key Features

• Event Processing: Receive and process events from bridges
• State Management: Maintain conversation history and context
• Response Generation: Yield events back through the system
• Lifecycle Hooks: start() method for async initialization

Nodes can work together in multi-agent systems. See Agent Patterns for coordination examples.