[PYTHON/LANGCHAIN] ChatMistralAI 클래스 : with_structured_output 메소드를 사용해 비정형 텍스트에서 객체 구하기

■ ChatMistralAI 클래스의 with_structured_output 메소드를 사용해 비정형 텍스트에서 객체를 구하는 방법을 보여준다.

▶ main.py


import os

from typing import Optional

from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_core.prompts     import ChatPromptTemplate
from langchain_mistralai        import ChatMistralAI

os.environ["MISTRAL_API_KEY"] = "<MISTRAL_API_KEY>"

# 구조화된 모델 클래스를 정의한다.
class Person(BaseModel):
    """Information about a person."""

    # ^ Doc-string for the entity Person.
    # This doc-string is sent to the LLM as the description of the schema Person,
    # and it can help to improve extraction results.

    # Note that:
    # 1. Each field is an `optional` -- this allows the model to decline to extract it!
    # 2. Each field has a `description` -- this description is used by the LLM.
    # Having a good description can help improve extraction results.
    name             : Optional[str] = Field(default = None, description = "The name of the person"                 )
    hair_color       : Optional[str] = Field(default = None, description = "The color of the person's hair if known")
    height_in_meters : Optional[str] = Field(default = None, description = "Height measured in meters"              )

# 채팅 프롬프트 템플리트를 설정한다.
chatPromptTemplate = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are an expert extraction algorithm. "
            "Only extract relevant information from the text. "
            "If you do not know the value of an attribute asked to extract, "
            "return null for the attribute's value.",
        ),
        ("human", "{text}"),
    ]
)

# LLM 모델을 설정한다.
chatMistralAI = ChatMistralAI(model = "mistral-large-latest", temperature = 0)

# 추출 체인을 설정한다.
extractionRunnableSequence = chatMistralAI.with_structured_output(schema = Person)

# 실행 체인을 설정한다.
executeRunnableSequence = chatPromptTemplate | extractionRunnableSequence

# 질의 응답을 실행한다.
person = executeRunnableSequence.invoke({"text" : "Alan Smith is 6 feet tall and has blond hair."})

print(person)

"""
name='Alan Smith' hair_color='blond' height_in_meters='1.8288'
"""

import os

from typing import Optional

from langchain_core.pydantic_v1 import BaseModel, Field

from langchain_core.prompts import ChatPromptTemplate

from langchain_mistralai import ChatMistralAI

os.environ["MISTRAL_API_KEY"] = "<MISTRAL_API_KEY>"

# 구조화된 모델 클래스를 정의한다.

class Person(BaseModel):

"""Information about a person."""

# ^ Doc-string for the entity Person.

# This doc-string is sent to the LLM as the description of the schema Person,

# and it can help to improve extraction results.

# Note that:

# 1. Each field is an `optional` -- this allows the model to decline to extract it!

# 2. Each field has a `description` -- this description is used by the LLM.

# Having a good description can help improve extraction results.

name : Optional[str] = Field(default = None, description = "The name of the person" )

hair_color : Optional[str] = Field(default = None, description = "The color of the person's hair if known")

height_in_meters : Optional[str] = Field(default = None, description = "Height measured in meters" )

# 채팅 프롬프트 템플리트를 설정한다.

chatPromptTemplate = ChatPromptTemplate.from_messages(

[

(

"system",

"You are an expert extraction algorithm. "

"Only extract relevant information from the text. "

"If you do not know the value of an attribute asked to extract, "

"return null for the attribute's value.",

("human", "{text}"),

]

)

# LLM 모델을 설정한다.

chatMistralAI = ChatMistralAI(model = "mistral-large-latest", temperature = 0)

# 추출 체인을 설정한다.

extractionRunnableSequence = chatMistralAI.with_structured_output(schema = Person)

# 실행 체인을 설정한다.

executeRunnableSequence = chatPromptTemplate | extractionRunnableSequence

# 질의 응답을 실행한다.

person = executeRunnableSequence.invoke({"text" : "Alan Smith is 6 feet tall and has blond hair."})

print(person)

"""

name='Alan Smith' hair_color='blond' height_in_meters='1.8288'

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
exceptiongroup==1.2.1
filelock==3.15.1
frozenlist==1.4.1
fsspec==2024.6.0
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
httpx-sse==0.4.0
huggingface-hub==0.23.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.4
langchain-core==0.2.6
langchain-mistralai==0.1.8
langchain-text-splitters==0.2.1
langsmith==0.1.77
multidict==6.0.5
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pydantic==2.7.4
pydantic_core==2.18.4
PyYAML==6.0.1
requests==2.32.3
sniffio==1.3.1
SQLAlchemy==2.0.30
tenacity==8.3.0
tokenizers==0.19.1
tqdm==4.66.4
typing_extensions==4.12.2
urllib3==2.2.1
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

exceptiongroup==1.2.1

filelock==3.15.1

frozenlist==1.4.1

fsspec==2024.6.0

greenlet==3.0.3

h11==0.14.0

httpcore==1.0.5

httpx==0.27.0

httpx-sse==0.4.0

huggingface-hub==0.23.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.4

langchain-core==0.2.6

langchain-mistralai==0.1.8

langchain-text-splitters==0.2.1

langsmith==0.1.77

multidict==6.0.5

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pydantic==2.7.4

pydantic_core==2.18.4

PyYAML==6.0.1

requests==2.32.3

sniffio==1.3.1

SQLAlchemy==2.0.30

tenacity==8.3.0

tokenizers==0.19.1

tqdm==4.66.4

typing_extensions==4.12.2

urllib3==2.2.1

yarl==1.9.4

※ pip install langchain langchain_mistralai 명령을 실행했다.