ym88659208ym87991671
OpenAI Functions | Документация для разработчиков

OpenAI Functions

Обновлено 27 февраля 2024

These output parsers use OpenAI function calling to structure its outputs. This means they are only usable with models that support function calling. There are a few different variants:

  • JsonOutputFunctionsParser: Returns the arguments of the function call as JSON
  • PydanticOutputFunctionsParser: Returns the arguments of the function call as a Pydantic Model
  • JsonKeyOutputFunctionsParser: Returns the value of specific key in the function call as JSON
  • PydanticAttrOutputFunctionsParser: Returns the value of specific key in the function call as a Pydantic Model
from langchain_community.utils.openai_functions import (
convert_pydantic_to_openai_function,
)
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.pydantic_v1 import BaseModel, Field, validator
from langchain_openai import ChatOpenAI
class Joke(BaseModel):
"""Joke to tell user."""

setup: str = Field(description="question to set up a joke")
punchline: str = Field(description="answer to resolve the joke")


openai_functions = [convert_pydantic_to_openai_function(Joke)]
model = ChatOpenAI(temperature=0)
prompt = ChatPromptTemplate.from_messages(
[("system", "You are helpful assistant"), ("user", "{input}")]
)

JsonOutputFunctionsParser

from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser
parser = JsonOutputFunctionsParser()
chain = prompt | model.bind(functions=openai_functions) | parser
chain.invoke({"input": "tell me a joke"})
    {'setup': "Why don't scientists trust atoms?",
'punchline': 'Because they make up everything!'}
for s in chain.stream({"input": "tell me a joke"}):
print(s)
    {}
{'setup': ''}
{'setup': 'Why'}
{'setup': 'Why don'}
{'setup': "Why don't"}
{'setup': "Why don't scientists"}
{'setup': "Why don't scientists trust"}
{'setup': "Why don't scientists trust atoms"}
{'setup': "Why don't scientists trust atoms?", 'punchline': ''}
{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because'}
{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they'}
{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make'}
{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up'}
{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything'}
{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}

JsonKeyOutputFunctionsParser

This merely extracts a single key from the returned response. This is useful for when you want to return a list of things.

from typing import List

from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser
class Jokes(BaseModel):
"""Jokes to tell user."""

joke: List[Joke]
funniness_level: int
parser = JsonKeyOutputFunctionsParser(key_name="joke")
openai_functions = [convert_pydantic_to_openai_function(Jokes)]
chain = prompt | model.bind(functions=openai_functions) | parser
chain.invoke({"input": "tell me two jokes"})
    [{'setup': "Why don't scientists trust atoms?",
'punchline': 'Because they make up everything!'},
{'setup': 'Why did the scarecrow win an award?',
'punchline': 'Because he was outstanding in his field!'}]
for s in chain.stream({"input": "tell me two jokes"}):
print(s)
    []
[{}]
[{'setup': ''}]
[{'setup': 'Why'}]
[{'setup': 'Why don'}]
[{'setup': "Why don't"}]
[{'setup': "Why don't scientists"}]
[{'setup': "Why don't scientists trust"}]
[{'setup': "Why don't scientists trust atoms"}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': ''}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': ''}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scare'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': ''}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he was'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he was outstanding'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he was outstanding in'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he was outstanding in his'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he was outstanding in his field'}]
[{'setup': "Why don't scientists trust atoms?", 'punchline': 'Because they make up everything!'}, {'setup': 'Why did the scarecrow win an award?', 'punchline': 'Because he was outstanding in his field!'}]

PydanticOutputFunctionsParser

This builds on top of JsonOutputFunctionsParser but passes the results to a Pydantic Model. This allows for further validation should you choose.

from langchain.output_parsers.openai_functions import PydanticOutputFunctionsParser
class Joke(BaseModel):
"""Joke to tell user."""

setup: str = Field(description="question to set up a joke")
punchline: str = Field(description="answer to resolve the joke")

# You can add custom validation logic easily with Pydantic.
@validator("setup")
def question_ends_with_question_mark(cls, field):
if field[-1] != "?":
raise ValueError("Badly formed question!")
return field


parser = PydanticOutputFunctionsParser(pydantic_schema=Joke)
openai_functions = [convert_pydantic_to_openai_function(Joke)]
chain = prompt | model.bind(functions=openai_functions) | parser
chain.invoke({"input": "tell me a joke"})
    Joke(setup="Why don't scientists trust atoms?", punchline='Because they make up everything!')
ПАО Сбербанк использует cookie для персонализации сервисов и удобства пользователей.
Вы можете запретить сохранение cookie в настройках своего браузера.