| Name | Type | Description |
|---|---|---|
name* | str | The name of the agent. |
description | Optional[str] | Default: NoneAn optional description of the agent. |
model* | str | The model to use for the agent. |
tools | Optional[Union[Sequence[Union[AgentServiceBaseTool, BaseTool, Callable]], ToolNode]] | Default: None |
instructions | Optional[Prompt] | Default: None |
temperature | Optional[float] | Default: None |
top_p | Optional[float] | Default: None |
response_format | Optional[Dict[str, Any]] | Default: None |
state_schema | Optional[StateSchemaType] | Default: None |
context_schema | Optional[Type[Any]] | Default: None |
checkpointer | Optional[Checkpointer] | Default: None |
store | Optional[BaseStore] | Default: None |
interrupt_before | Optional[list[str]] | Default: None |
interrupt_after | Optional[list[str]] | Default: None |
trace | bool | Default: False |
debug | bool | Default: False |
Create a prompt-based agent in Azure AI Foundry.
The tools to use with the agent. This can be a list of BaseTools, callables, or tool definitions, or a ToolNode.
The prompt instructions to use for the agent.
The temperature to use for the agent.
The top_p to use for the agent.
The response format to use for the agent.
The schema for the state to pass to the agent. If None, AgentStateWithStructuredResponse is used if response_format is specified, otherwise AgentState is used.
The schema for the context to pass to the agent.
The checkpointer to use for the agent.
The store to use for the agent.
A list of node names to interrupt before.
A list of node names to interrupt after.
Whether to enable tracing. When enabled, an OpenTelemetry tracer will be created using the project endpoint and credential provided to the factory.
Whether to enable debug mode.