AgentServiceFactory#

class langchain_azure_ai.agents.agent_service.AgentServiceFactory[source]#

Bases: BaseModel

Factory to create and manage declarative chat agents in Azure AI Foundry.

Examples

To create a simple echo agent:

Agents can also be created with tools. For example, to create an agent that can perform arithmetic using a calculator tool:

You can also use the built-in tools in the Agent Service. Those tools only work with agents created in Azure AI Foundry. For example, to create an agent that can use Code Interpreter.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param api_version: str | None = None#

The API version to use with Azure. If None, the default version is used.

param client_kwargs: Dict[str, Any] = {}#

Additional keyword arguments to pass to the client.

param credential: TokenCredential | None = None#

The API key or credential to use to connect to the service. If using a project endpoint, this must be of type TokenCredential since only Microsoft EntraID is supported.

param project_endpoint: str | None = None#

The project endpoint associated with the AI project. If this is specified, then the endpoint parameter becomes optional and credential has to be of type TokenCredential.

create_declarative_chat_agent(
model: str,
name: str,
description: str | None = None,
tools: Sequence[AgentServiceBaseTool | BaseTool | Callable] | ToolNode | None = None,
instructions: SystemMessage | str | Callable[[StateSchema], PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | Runnable[StateSchema, PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | None = None,
temperature: float | None = None,
top_p: float | None = None,
response_format: Dict[str, Any] | None = None,
context_schema: Type[Any] | None = None,
checkpointer: None | bool | BaseCheckpointSaver = None,
store: BaseStore | None = None,
interrupt_before: list[str] | None = None,
interrupt_after: list[str] | None = None,
trace: bool = False,
debug: bool = False,
) → CompiledStateGraph[source]#

Create a declarative chat agent in Azure AI Foundry.

Parameters:

  • name (str) – The name of the agent.

  • description (str | None) – An optional description of the agent.

  • model (str) – The model to use for the agent.

  • tools (Sequence[AgentServiceBaseTool | BaseTool | Callable] | ToolNode | None) – The tools to use with the agent. This can be a list of BaseTools, callables, or tool definitions, or a ToolNode.

  • instructions (SystemMessage | str | Callable[[StateSchema], PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | Runnable[StateSchema, PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | None) – The prompt instructions to use for the agent.

  • temperature (float | None) – The temperature to use for the agent.

  • top_p (float | None) – The top_p to use for the agent.

  • response_format (Dict[str, Any] | None) – The response format to use for the agent.

  • context_schema (Type[Any] | None) – The schema for the context to pass to the agent.

  • checkpointer (None | bool | BaseCheckpointSaver) – The checkpointer to use for the agent.

  • store (BaseStore | None) – The store to use for the agent.

  • interrupt_before (list[str] | None) – A list of node names to interrupt before.

  • interrupt_after (list[str] | None) – A list of node names to interrupt after.

  • trace (bool) – Whether to enable tracing.

  • debug (bool) – Whether to enable debug mode.

Returns:

A CompiledStateGraph representing the agent workflow.

Return type:

CompiledStateGraph

create_declarative_chat_node(
name: str,
model: str,
description: str | None = None,
tools: Sequence[AgentServiceBaseTool | BaseTool | Callable] | ToolNode | None = None,
instructions: SystemMessage | str | Callable[[StateSchema], PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | Runnable[StateSchema, PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | None = None,
temperature: float | None = None,
top_p: float | None = None,
response_format: Dict[str, Any] | None = None,
trace: bool = False,
) → DeclarativeChatAgentNode[source]#

Create a declarative chat agent node in Azure AI Foundry.

Parameters:

  • name (str) – The name of the agent.

  • model (str) – The model to use for the agent.

  • description (str | None) – An optional description of the agent.

  • tools (Sequence[AgentServiceBaseTool | BaseTool | Callable] | ToolNode | None) – The tools to use with the agent. This can be a list of BaseTools callables, or tool definitions, or a ToolNode.

  • instructions (SystemMessage | str | Callable[[StateSchema], PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | Runnable[StateSchema, PromptValue | str | Sequence[BaseMessage | list[str] | tuple[str, str] | str | dict[str, Any]]] | None) – The prompt instructions to use for the agent.

  • temperature (float | None) – The temperature to use for the agent.

  • top_p (float | None) – The top_p to use for the agent.

  • response_format (Dict[str, Any] | None) – The response format to use for the agent.

  • trace (bool) – Whether to enable tracing.

Returns:

A DeclarativeChatAgentNode representing the agent.

Return type:

DeclarativeChatAgentNode

delete_agent(
agent: CompiledStateGraph | DeclarativeChatAgentNode,
) → None[source]#

Delete an agent created with create_declarative_chat_agent.

Parameters:

agent (CompiledStateGraph | DeclarativeChatAgentNode) – The CompiledStateGraph representing the agent to delete.

Raises:

ValueError – If the agent ID cannot be found in the graph metadata.

Return type:

None

get_declarative_agents_id_from_graph(
graph: CompiledStateGraph,
) → Set[str][source]#

Get the agents associated with a state graph.

Parameters:

graph (CompiledStateGraph)

Return type:

Set[str]