from pydantic import BaseModel, Fieldfrom langchain.agents import create_agentclass ContactInfo(BaseModel): """Contact information for a person.""" name: str = Field(description="The name of the person") email: str = Field(description="The email address of the person") phone: str = Field(description="The phone number of the person")agent = create_agent( model="gpt-5.4", response_format=ContactInfo # Auto-selects ProviderStrategy)result = agent.invoke({ "messages": [{"role": "user", "content": "Extract contact info from: John Doe, john@example.com, (555) 123-4567"}]})print(result["structured_response"])# ContactInfo(name='John Doe', email='john@example.com', phone='(555) 123-4567')
from pydantic import BaseModel, Fieldfrom typing import Literalfrom langchain.agents import create_agentfrom langchain.agents.structured_output import ToolStrategyclass MeetingAction(BaseModel): """Action items extracted from a meeting transcript.""" task: str = Field(description="The specific task to be completed") assignee: str = Field(description="Person responsible for the task") priority: Literal["low", "medium", "high"] = Field(description="Priority level")agent = create_agent( model="gpt-5.4", tools=[], response_format=ToolStrategy( schema=MeetingAction, tool_message_content="Action item captured and added to meeting notes!" ))agent.invoke({ "messages": [{"role": "user", "content": "From our meeting: Sarah needs to update the project timeline as soon as possible"}]})
================================ Human Message =================================From our meeting: Sarah needs to update the project timeline as soon as possible================================== Ai Message ==================================Tool Calls: MeetingAction (call_1) Call ID: call_1 Args: task: Update the project timeline assignee: Sarah priority: high================================= Tool Message =================================Name: MeetingActionAction item captured and added to meeting notes!
from pydantic import BaseModel, Fieldfrom typing import Unionfrom langchain.agents import create_agentfrom langchain.agents.structured_output import ToolStrategyclass ContactInfo(BaseModel): name: str = Field(description="Person's name") email: str = Field(description="Email address")class EventDetails(BaseModel): event_name: str = Field(description="Name of the event") date: str = Field(description="Event date")agent = create_agent( model="gpt-5.4", tools=[], response_format=ToolStrategy(Union[ContactInfo, EventDetails]) # Default: handle_errors=True)agent.invoke({ "messages": [{"role": "user", "content": "Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th"}]})
================================ Human Message =================================Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15thNone================================== Ai Message ==================================Tool Calls: ContactInfo (call_1) Call ID: call_1 Args: name: John Doe email: john@email.com EventDetails (call_2) Call ID: call_2 Args: event_name: Tech Conference date: March 15th================================= Tool Message =================================Name: ContactInfoError: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected. Please fix your mistakes.================================= Tool Message =================================Name: EventDetailsError: Model incorrectly returned multiple structured responses (ContactInfo, EventDetails) when only one is expected. Please fix your mistakes.================================== Ai Message ==================================Tool Calls: ContactInfo (call_3) Call ID: call_3 Args: name: John Doe email: john@email.com================================= Tool Message =================================Name: ContactInfoReturning structured response: {'name': 'John Doe', 'email': 'john@email.com'}
from pydantic import BaseModel, Fieldfrom langchain.agents import create_agentfrom langchain.agents.structured_output import ToolStrategyclass ProductRating(BaseModel): rating: int | None = Field(description="Rating from 1-5", ge=1, le=5) comment: str = Field(description="Review comment")agent = create_agent( model="gpt-5.4", tools=[], response_format=ToolStrategy(ProductRating), # Default: handle_errors=True system_prompt="You are a helpful assistant that parses product reviews. Do not make any field or value up.")agent.invoke({ "messages": [{"role": "user", "content": "Parse this: Amazing product, 10/10!"}]})
================================ Human Message =================================Parse this: Amazing product, 10/10!================================== Ai Message ==================================Tool Calls: ProductRating (call_1) Call ID: call_1 Args: rating: 10 comment: Amazing product================================= Tool Message =================================Name: ProductRatingError: Failed to parse structured output for tool 'ProductRating': 1 validation error for ProductRating.rating Input should be less than or equal to 5 [type=less_than_equal, input_value=10, input_type=int]. Please fix your mistakes.================================== Ai Message ==================================Tool Calls: ProductRating (call_2) Call ID: call_2 Args: rating: 5 comment: Amazing product================================= Tool Message =================================Name: ProductRatingReturning structured response: {'rating': 5, 'comment': 'Amazing product'}
================================= Tool Message =================================Name: ProductRatingPlease provide a valid rating between 1-5 and include a comment.
仅处理特定异常：
ToolStrategy( schema=ProductRating, handle_errors=ValueError # Only retry on ValueError, raise others)
from langchain.agents.structured_output import StructuredOutputValidationErrorfrom langchain.agents.structured_output import MultipleStructuredOutputsErrordef custom_error_handler(error: Exception) -> str: if isinstance(error, StructuredOutputValidationError): return "There was an issue with the format. Try again." elif isinstance(error, MultipleStructuredOutputsError): return "Multiple structured outputs were returned. Pick the most relevant one." else: return f"Error: {str(error)}"agent = create_agent( model="gpt-5.4", tools=[], response_format=ToolStrategy( schema=Union[ContactInfo, EventDetails], handle_errors=custom_error_handler ) # Default: handle_errors=True)result = agent.invoke({ "messages": [{"role": "user", "content": "Extract info: John Doe (john@email.com) is organizing Tech Conference on March 15th"}]})for msg in result['messages']: # If message is actually a ToolMessage object (not a dict), check its class name if type(msg).__name__ == "ToolMessage": print(msg.content) # If message is a dictionary or you want a fallback elif isinstance(msg, dict) and msg.get('tool_call_id'): print(msg['content'])
遇到 StructuredOutputValidationError 时：
================================= Tool Message =================================Name: ToolStrategyThere was an issue with the format. Try again.
遇到 MultipleStructuredOutputsError 时：
================================= Tool Message =================================Name: ToolStrategyMultiple structured outputs were returned. Pick the most relevant one.
