Class●Since v1.0Deprecated

PromptBasedAgentNode

PromptBasedAgentNode(
  self,
  client: AgentsClient,
  agent: Agent,
  name: str,
  polling_interval: int

Bases

RunnableCallable

Constructors

Attributes

Methods

View source on GitHub

Parameters

Name	Type	Description
`client`*	`AgentsClient`	The AgentsClient instance to use.
`agent`*	`Agent`	An existing agent retrieved from Azure AI Foundry. Use :meth:`~langchain_azure_ai.agents.v1.AgentServiceFactory.create_prompt_agent_node` to create a new agent and receive a pre-populated node.
`name`*	`str`	The display name for this LangGraph node.
`polling_interval`	`int`	Default:`1` The interval (in seconds) to poll for updates on the agent's status. Defaults to 1 second.
`tags`	`Optional[Sequence[str]]`	Default:`None`
`trace`	`bool`	Default:`True`

Name	Type
client	AgentsClient
agent	Agent
name	str
polling_interval	int
tags	Optional[Sequence[str]]
trace	bool

A LangGraph node that represents a prompt-based agent in Azure AI Foundry.

You can use this node to create complex graphs that involve interactions with an Azure AI Foundry agent.

You can also use langchain_azure_ai.agents.AgentServiceFactory to create instances of this node.

Example:

from azure.identity import DefaultAzureCredential
from langchain_azure_ai.agents import AgentServiceFactory

factory = AgentServiceFactory(
    project_endpoint=(
        "https://resource.services.ai.azure.com/api/projects/demo-project",
    ),
    credential=DefaultAzureCredential()
)

coder = factory.create_prompt_agent_node(
    name="code-interpreter-agent",
    model="gpt-4.1",
    instructions="You are a helpful assistant that can run Python code.",
    tools=[func1, func2],
)