[PYTHON/LANGCHAIN] PydanticOutputParser 클래스 : 정형화된 데이터 추출하기 (프롬프트만 사용)

■ PydanticOutputParser 클래스를 사용해 정형화된 데이터를 추출하는 방법을 보여준다. (프롬프트만 사용)

※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다.

▶ main.py


from dotenv                        import load_dotenv
from pydantic                      import BaseModel
from pydantic                      import Field
from typing                        import List
from langchain_core.output_parsers import PydanticOutputParser
from langchain_core.prompts        import ChatPromptTemplate
from langchain_openai              import ChatOpenAI

load_dotenv()

class Person(BaseModel):
    """Information about a person."""

    name             : str   = Field(..., description = "The name of the person"                       )
    height_in_meters : float = Field(..., description = "The height of the person expressed in meters.")

class People(BaseModel):
    """Identifying information about all people in a text."""

    people : List[Person]

pydanticOutputParser = PydanticOutputParser(pydantic_object = People)

chatPromptTemplate1 = ChatPromptTemplate.from_messages(
    [
        ("system", "Answer the user query. Wrap the output in `json` tags\n{format_instructions}"),
        ("human" , "{query}")
    ]
)

chatPromptTemplate2 = chatPromptTemplate1.partial(format_instructions = pydanticOutputParser.get_format_instructions())

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini")

runnableSequence = chatPromptTemplate2 | chatOpenAI | pydanticOutputParser

responsePeople = runnableSequence.invoke({"query" : "Anna is 23 years old and she is 6 feet tall"})

print(responsePeople)

"""
people=[Person(name='Anna', height_in_meters=1.8288)]
"""

from dotenv import load_dotenv

from pydantic import BaseModel

from pydantic import Field

from typing import List

from langchain_core.output_parsers import PydanticOutputParser

from langchain_core.prompts import ChatPromptTemplate

from langchain_openai import ChatOpenAI

load_dotenv()

class Person(BaseModel):

"""Information about a person."""

name : str = Field(..., description = "The name of the person" )

height_in_meters : float = Field(..., description = "The height of the person expressed in meters.")

class People(BaseModel):

"""Identifying information about all people in a text."""

people : List[Person]

pydanticOutputParser = PydanticOutputParser(pydantic_object = People)

chatPromptTemplate1 = ChatPromptTemplate.from_messages(

[

("system", "Answer the user query. Wrap the output in `json` tags\n{format_instructions}"),

("human" , "{query}")

]

)

chatPromptTemplate2 = chatPromptTemplate1.partial(format_instructions = pydanticOutputParser.get_format_instructions())

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini")

runnableSequence = chatPromptTemplate2 | chatOpenAI | pydanticOutputParser

responsePeople = runnableSequence.invoke({"query" : "Anna is 23 years old and she is 6 feet tall"})

print(responsePeople)

"""

people=[Person(name='Anna', height_in_meters=1.8288)]

"""

▶ requirements.txt


annotated-types==0.7.0
anyio==4.7.0
certifi==2024.8.30
charset-normalizer==3.4.0
colorama==0.4.6
distro==1.9.0
h11==0.14.0
httpcore==1.0.7
httpx==0.28.1
idna==3.10
jiter==0.8.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain-core==0.3.22
langchain-openai==0.2.11
langsmith==0.1.147
openai==1.57.0
orjson==3.10.12
packaging==24.2
pydantic==2.10.3
pydantic_core==2.27.1
python-dotenv==1.0.1
PyYAML==6.0.2
regex==2024.11.6
requests==2.32.3
requests-toolbelt==1.0.0
sniffio==1.3.1
tenacity==9.0.0
tiktoken==0.8.0
tqdm==4.67.1
typing_extensions==4.12.2
urllib3==2.2.3

annotated-types==0.7.0

anyio==4.7.0

certifi==2024.8.30

charset-normalizer==3.4.0

colorama==0.4.6

distro==1.9.0

h11==0.14.0

httpcore==1.0.7

httpx==0.28.1

idna==3.10

jiter==0.8.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain-core==0.3.22

langchain-openai==0.2.11

langsmith==0.1.147

openai==1.57.0

orjson==3.10.12

packaging==24.2

pydantic==2.10.3

pydantic_core==2.27.1

python-dotenv==1.0.1

PyYAML==6.0.2

regex==2024.11.6

requests==2.32.3

requests-toolbelt==1.0.0

sniffio==1.3.1

tenacity==9.0.0

tiktoken==0.8.0

tqdm==4.67.1

typing_extensions==4.12.2

urllib3==2.2.3

※ pip install python-dotenv langchain-openai 명령을 실행했다.