langchain.chains.structured_output.base
.create_structured_output_runnable¶
- langchain.chains.structured_output.base.create_structured_output_runnable(output_schema: Union[Dict[str, Any], Type[BaseModel]], llm: Runnable, prompt: Optional[BasePromptTemplate] = None, *, output_parser: Optional[Union[BaseOutputParser, BaseGenerationOutputParser]] = None, enforce_function_usage: bool = True, return_single: bool = True, mode: Literal['openai-functions', 'openai-tools', 'openai-json'] = 'openai-functions', **kwargs: Any) Runnable [source]¶
Create a runnable for extracting structured outputs.
- Parameters
output_schema (Union[Dict[str, Any], Type[BaseModel]]) â Either a dictionary or pydantic.BaseModel class. If a dictionary is passed in, itâs assumed to already be a valid JsonSchema. For best results, pydantic.BaseModels should have docstrings describing what the schema represents and descriptions for the parameters.
llm (Runnable) â Language model to use. Assumed to support the OpenAI function-calling API if mode is âopenai-functionâ. Assumed to support OpenAI response_format parameter if mode is âopenai-jsonâ.
prompt (Optional[BasePromptTemplate]) â BasePromptTemplate to pass to the model. If mode is âopenai-jsonâ and prompt has input variable âoutput_schemaâ then the given output_schema will be converted to a JsonSchema and inserted in the prompt.
output_parser (Optional[Union[BaseOutputParser, BaseGenerationOutputParser]]) â Output parser to use for parsing model outputs. By default will be inferred from the function types. If pydantic.BaseModel is passed in, then the OutputParser will try to parse outputs using the pydantic class. Otherwise model outputs will be parsed as JSON.
mode (Literal['openai-functions', 'openai-tools', 'openai-json']) â How structured outputs are extracted from the model. If âopenai-functionsâ then OpenAI function calling is used with the deprecated âfunctionsâ, âfunction_callâ schema. If âopenai-toolsâ then OpenAI function calling with the latest âtoolsâ, âtool_choiceâ schema is used. This is recommended over âopenai-functionsâ. If âopenai-jsonâ then OpenAI model with response_format set to JSON is used.
enforce_function_usage (bool) â Only applies when mode is âopenai-toolsâ or âopenai-functionsâ. If True, then the model will be forced to use the given output schema. If False, then the model can elect whether to use the output schema.
return_single (bool) â Only applies when mode is âopenai-toolsâ. Whether to a list of structured outputs or a single one. If True and model does not return any structured outputs then chain output is None. If False and model does not return any structured outputs then chain output is an empty list.
**kwargs (Any) â Additional named arguments.
- Returns
- A runnable sequence that will return a structured output(s) matching the given
output_schema.
- Return type
- OpenAI tools example with Pydantic schema (mode=âopenai-toolsâ):
from typing import Optional from langchain.chains import create_structured_output_runnable from langchain_openai import ChatOpenAI from langchain_core.pydantic_v1 import BaseModel, Field class RecordDog(BaseModel): '''Record some identifying information about a dog.''' name: str = Field(..., description="The dog's name") color: str = Field(..., description="The dog's color") fav_food: Optional[str] = Field(None, description="The dog's favorite food") llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0) prompt = ChatPromptTemplate.from_messages( [ ("system", "You are an extraction algorithm. Please extract every possible instance"), ('human', '{input}') ] ) structured_llm = create_structured_output_runnable( RecordDog, llm, mode="openai-tools", enforce_function_usage=True, return_single=True ) structured_llm.invoke({"input": "Harry was a chubby brown beagle who loved chicken"}) # -> RecordDog(name="Harry", color="brown", fav_food="chicken")
- OpenAI tools example with dict schema (mode=âopenai-toolsâ):
from typing import Optional from langchain.chains import create_structured_output_runnable from langchain_openai import ChatOpenAI dog_schema = { "type": "function", "function": { "name": "record_dog", "description": "Record some identifying information about a dog.", "parameters": { "type": "object", "properties": { "name": { "description": "The dog's name", "type": "string" }, "color": { "description": "The dog's color", "type": "string" }, "fav_food": { "description": "The dog's favorite food", "type": "string" } }, "required": ["name", "color"] } } } llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0) structured_llm = create_structured_output_runnable( doc_schema, llm, mode="openai-tools", enforce_function_usage=True, return_single=True ) structured_llm.invoke("Harry was a chubby brown beagle who loved chicken") # -> {'name': 'Harry', 'color': 'brown', 'fav_food': 'chicken'}
- OpenAI functions example (mode=âopenai-functionsâ):
from typing import Optional from langchain.chains import create_structured_output_runnable from langchain_openai import ChatOpenAI from langchain_core.pydantic_v1 import BaseModel, Field class Dog(BaseModel): '''Identifying information about a dog.''' name: str = Field(..., description="The dog's name") color: str = Field(..., description="The dog's color") fav_food: Optional[str] = Field(None, description="The dog's favorite food") llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0) structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-functions") structured_llm.invoke("Harry was a chubby brown beagle who loved chicken") # -> Dog(name="Harry", color="brown", fav_food="chicken")
- OpenAI functions with prompt example:
from typing import Optional from langchain.chains import create_structured_output_runnable from langchain_openai import ChatOpenAI from langchain_core.prompts import ChatPromptTemplate from langchain_core.pydantic_v1 import BaseModel, Field class Dog(BaseModel): '''Identifying information about a dog.''' name: str = Field(..., description="The dog's name") color: str = Field(..., description="The dog's color") fav_food: Optional[str] = Field(None, description="The dog's favorite food") llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0) structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-functions") system = '''Extract information about any dogs mentioned in the user input.''' prompt = ChatPromptTemplate.from_messages( [("system", system), ("human", "{input}"),] ) chain = prompt | structured_llm chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"}) # -> Dog(name="Harry", color="brown", fav_food="chicken")
- OpenAI json response format example (mode=âopenai-jsonâ):
from typing import Optional from langchain.chains import create_structured_output_runnable from langchain_openai import ChatOpenAI from langchain_core.prompts import ChatPromptTemplate from langchain_core.pydantic_v1 import BaseModel, Field class Dog(BaseModel): '''Identifying information about a dog.''' name: str = Field(..., description="The dog's name") color: str = Field(..., description="The dog's color") fav_food: Optional[str] = Field(None, description="The dog's favorite food") llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0) structured_llm = create_structured_output_runnable(Dog, llm, mode="openai-json") system = '''You are a world class assistant for extracting information in structured JSON formats. Extract a valid JSON blob from the user input that matches the following JSON Schema: {output_schema}''' prompt = ChatPromptTemplate.from_messages( [("system", system), ("human", "{input}"),] ) chain = prompt | structured_llm chain.invoke({"input": "Harry was a chubby brown beagle who loved chicken"})