icodebroker - 컴퓨터 프로그래밍 코드 데이터베이스

[PYTHON/COMMON] @classmethod 데코레이터와 @staticmethod 데코레이터의 차이점 비교하기

■ @classmethod 데코레이터와 @staticmethod 데코레이터의 차이점을 비교하는 예제 코드를 보여준다. ▶ 예제 코드 (PY)


class Date:
    def __init__(self, year, month, day):
        self.year  = year
        self.month = month
        self.day   = day

    @classmethod
    def fromString(cls, dateString):
        year, month, day = map(int, dateString.split("-"))
        return cls(year, month, day)

    @staticmethod
    def isValidDate(dateString):
        year, month, day = map(int, dateString.split("-"))
        return year > 0 and 1 <= month <= 12 and 1 <= day <= 31

# 클래스 메소드를 사용한다.
date = Date.fromString("2024-12-19")
print(date.year, date.month, date.day)

# 정적 메소드를 사용한다.
print(Date.isValidDate("2024-12-19"))

class Date:

def __init__(self, year, month, day):

self.year = year

self.month = month

self.day = day

@classmethod

def fromString(cls, dateString):

year, month, day = map(int, dateString.split("-"))

return cls(year, month, day)

@staticmethod

def isValidDate(dateString):

year, month, day = map(int, dateString.split("-"))

return year > 0 and 1 <= month <= 12 and 1 <= day <= 31

# 클래스 메소드를 사용한다.

date = Date.fromString("2024-12-19")

print(date.year, date.month, date.day)

# 정적 메소드를 사용한다.

print(Date.isValidDate("2024-12-19"))

[PYTHON/LANGCHAIN] CYPHER 템플리트와 커스텀 도구를 사용해 NEO4J 데이터베이스 검색하기

■ CYPHER 템플리트와 커스텀 도구를 사용해 NEO4J 데이터베이스를 검색하는 방법을 보여준다. ※ NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD 환경 변수 값은 .env 파일에 정의한다. ※

[PYTHON/LANGCHAIN] NEO4J 데이터베이스 결과에 기반한 답변 생성하기

■ NEO4J 데이터베이스 결과에 기반한 답변을 생성하는 방법을 보여준다. ※ NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD 환경 변수 값은 .env 파일에 정의한다. ※ OPENAI_API_KEY 환경

[PYTHON/LANGCHAIN] Neo4jGraph 클래스 : query 메소드를 사용해 데이터 추가하기

■ Neo4jGraph 클래스의 query 메소드를 사용해 데이터를 추가하는 방법을 보여준다. ▶ main.py


from dotenv          import load_dotenv
from langchain_neo4j import Neo4jGraph

load_dotenv()

neo4jGraph = Neo4jGraph()

insertDataQuery = """
LOAD CSV WITH HEADERS FROM 'https://raw.githubusercontent.com/tomasonjo/blog-datasets/main/movies/movies_small.csv' AS row
MERGE (m:Movie {id:row.movieId})
SET
    m.released   = date(row.released),
    m.title      = row.title,
    m.imdbRating = toFloat(row.imdbRating)
FOREACH (director in split(row.director, '|') |
    MERGE (p:Person {name:trim(director)})
    MERGE (p)-[:DIRECTED]->(m))
FOREACH (actor in split(row.actors, '|') |
    MERGE (p:Person {name:trim(actor)})
    MERGE (p)-[:ACTED_IN]->(m))
FOREACH (genre in split(row.genres, '|') |
    MERGE (g:Genre {name:trim(genre)})
    MERGE (m)-[:IN_GENRE]->(g))
"""

neo4jGraph.query(insertDataQuery)

from dotenv import load_dotenv

from langchain_neo4j import Neo4jGraph

load_dotenv()

neo4jGraph = Neo4jGraph()

insertDataQuery = """

LOAD CSV WITH HEADERS FROM 'https://raw.githubusercontent.com/tomasonjo/blog-datasets/main/movies/movies_small.csv' AS row

MERGE (m:Movie {id:row.movieId})

SET

m.released = date(row.released),

m.title = row.title,

m.imdbRating = toFloat(row.imdbRating)

FOREACH (director in split(row.director, '|') |

MERGE (p:Person {name:trim(director)})

MERGE (p)-[:DIRECTED]->(m))

FOREACH (actor in split(row.actors, '|') |

MERGE (p:Person {name:trim(actor)})

MERGE (p)-[:ACTED_IN]->(m))

FOREACH (genre in split(row.genres, '|') |

MERGE (g:Genre {name:trim(genre)})

MERGE (m)-[:IN_GENRE]->(g))

"""

neo4jGraph.query(insertDataQuery)

▶ requirements.txt


aiohappyeyeballs==2.4.4
aiohttp==3.11.10
aiosignal==1.3.2
annotated-types==0.7.0
anyio==4.7.0
attrs==24.3.0
certifi==2024.12.14
charset-normalizer==3.4.0
frozenlist==1.5.0
greenlet==3.1.1
h11==0.14.0
httpcore==1.0.7
httpx==0.28.1
idna==3.10
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.3.12
langchain-core==0.3.25
langchain-neo4j==0.1.1
langchain-text-splitters==0.3.3
langsmith==0.2.3
multidict==6.1.0
neo4j==5.27.0
numpy==2.2.0
orjson==3.10.12
packaging==24.2
propcache==0.2.1
pydantic==2.10.3
pydantic_core==2.27.1
python-dotenv==1.0.1
pytz==2024.2
PyYAML==6.0.2
requests==2.32.3
requests-toolbelt==1.0.0
sniffio==1.3.1
SQLAlchemy==2.0.36
tenacity==9.0.0
typing_extensions==4.12.2
urllib3==2.2.3
yarl==1.18.3

aiohappyeyeballs==2.4.4

aiohttp==3.11.10

aiosignal==1.3.2

annotated-types==0.7.0

anyio==4.7.0

attrs==24.3.0

certifi==2024.12.14

charset-normalizer==3.4.0

frozenlist==1.5.0

greenlet==3.1.1

h11==0.14.0

httpcore==1.0.7

httpx==0.28.1

idna==3.10

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.3.12

langchain-core==0.3.25

langchain-neo4j==0.1.1

langchain-text-splitters==0.3.3

langsmith==0.2.3

multidict==6.1.0

neo4j==5.27.0

numpy==2.2.0

orjson==3.10.12

packaging==24.2

propcache==0.2.1

pydantic==2.10.3

pydantic_core==2.27.1

python-dotenv==1.0.1

pytz==2024.2

PyYAML==6.0.2

requests==2.32.3

requests-toolbelt==1.0.0

sniffio==1.3.1

SQLAlchemy==2.0.36

tenacity==9.0.0

typing_extensions==4.12.2

urllib3==2.2.3

yarl==1.18.3

※ pip install python-dotenv langchain-neo4j 명령을

[DATABASE/NEO4J] ALTER USER ~ SET PASSWORD 명령 : 사용자 계정 패스워드 변경하기

■ ALTER USER ~ SET PASSWORD 명령을 사용해 사용자 계정의 패스워드를 변경하는 방법을 보여준다. ▶ 예제 코드 (CYPHER)


ALTER USER neo4j SET PASSWORD 'test1234'

ALTER USER neo4j SET PASSWORD 'test1234'

※ neo4j :

[DATABASE/NEO4J] SHOW USERS 명령 : 사용자 목록 조회하기

■ SHOW USERS 명령을 사용해 사용자 목록을 조회하는 방법을 보여준다. ▶ 예제 코드 (CYPHER)


SHOW USERS

SHOW USERS

[PYTHON/LANGCHAIN] trim_messages 함수 : RunnableWithMessageHistory 객체와 함께 사용하기

■ trim_messages 함수를 RunnableWithMessageHistory 객체와 함께 사용하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv                           import load_dotenv
from langchain_core.messages          import SystemMessage
from langchain_core.messages          import HumanMessage
from langchain_core.messages          import AIMessage
from langchain_openai                 import ChatOpenAI
from langchain_core.messages          import trim_messages
from langchain_core.chat_history      import InMemoryChatMessageHistory
from langchain_core.runnables.history import RunnableWithMessageHistory

load_dotenv()

messageList = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!")
]

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

runnableLambda = trim_messages(
    max_tokens     = 45,
    strategy       = "last",
    token_counter  = chatOpenAI,
    include_system = True
)

runnableSequence = runnableLambda | chatOpenAI

inMemoryChatMessageHistory = InMemoryChatMessageHistory(messages = messageList)

def getSessionHistory(session_id):
    if session_id != "1":
        return InMemoryChatMessageHistory()
    return inMemoryChatMessageHistory

runnableWithMessageHistory = RunnableWithMessageHistory(runnableSequence, getSessionHistory)

responseAIMessage = runnableWithMessageHistory.invoke(
    [HumanMessage("what do you call a speechless parrot")],
    config = {"configurable" : {"session_id" : "1"}}
)

print(responseAIMessage)

"""
content           ='A bird of few words!'
additional_kwargs = {'refusal' : None}
response_metadata = {
    'token_usage' : {
        'completion_tokens'         : 6,
        'prompt_tokens'             : 32,
        'total_tokens'              : 38,
        'completion_tokens_details' : {
            'accepted_prediction_tokens' : 0,
            'audio_tokens'               : 0,
            'reasoning_tokens'           : 0,
            'rejected_prediction_tokens' : 0
        },
        'prompt_tokens_details'     : {'audio_tokens' : 0, 'cached_tokens' : 0}
    },
    'model_name'         : 'gpt-4o-2024-08-06',
    'system_fingerprint' : 'fp_f785eb5f47',
    'finish_reason'      : 'stop',
    'logprobs'           : None
}
id             = 'run-d5feab66-cda1-462c-ad1a-a6a8b4de9c8f-0'
usage_metadata = {
    'input_tokens'         : 32,
    'output_tokens'        : 6,
    'total_tokens'         : 38,
    'input_token_details'  : {
        'audio'     : 0,
        'cache_read': 0
    },
    'output_token_details' : {'audio' : 0, 'reasoning' : 0}
}
"""

from dotenv import load_dotenv

from langchain_core.messages import SystemMessage

from langchain_core.messages import HumanMessage

from langchain_core.messages import AIMessage

from langchain_openai import ChatOpenAI

from langchain_core.messages import trim_messages

from langchain_core.chat_history import InMemoryChatMessageHistory

from langchain_core.runnables.history import RunnableWithMessageHistory

load_dotenv()

messageList = [

SystemMessage("you're a good assistant, you always respond with a joke."),

HumanMessage("i wonder why it's called langchain"),

AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),

HumanMessage("and who is harrison chasing anyways"),

AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!")

]

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

runnableLambda = trim_messages(

max_tokens = 45,

strategy = "last",

token_counter = chatOpenAI,

include_system = True

)

runnableSequence = runnableLambda | chatOpenAI

inMemoryChatMessageHistory = InMemoryChatMessageHistory(messages = messageList)

def getSessionHistory(session_id):

if session_id != "1":

return InMemoryChatMessageHistory()

return inMemoryChatMessageHistory

runnableWithMessageHistory = RunnableWithMessageHistory(runnableSequence, getSessionHistory)

responseAIMessage = runnableWithMessageHistory.invoke(

[HumanMessage("what do you call a speechless parrot")],

config = {"configurable" : {"session_id" : "1"}}

)

print(responseAIMessage)

"""

content ='A bird of few words!'

additional_kwargs = {'refusal' : None}

response_metadata = {

'token_usage' : {

'completion_tokens' : 6,

'prompt_tokens' : 32,

'total_tokens' : 38,

'completion_tokens_details' : {

'accepted_prediction_tokens' : 0,

'audio_tokens' : 0,

'reasoning_tokens' : 0,

'rejected_prediction_tokens' : 0

'prompt_tokens_details' : {'audio_tokens' : 0, 'cached_tokens' : 0}

'model_name' : 'gpt-4o-2024-08-06',

'system_fingerprint' : 'fp_f785eb5f47',

'finish_reason' : 'stop',

'logprobs' : None

}

id = 'run-d5feab66-cda1-462c-ad1a-a6a8b4de9c8f-0'

usage_metadata = {

'input_tokens' : 32,

'output_tokens' : 6,

'total_tokens' : 38,

'input_token_details' : {

'audio' : 0,

'cache_read': 0

'output_token_details' : {'audio' : 0, 'reasoning' : 0}

}

"""

▶ requirements.txt

[PYTHON/LANGCHAIN] trim_messages 함수 : token_counter 인자를 사용해 커스텀 카운터 만들기

■ trim_messages 함수의 token_counter 인자를 사용해 커스텀 카운터를 만드는 방법을 보여준다. ▶ main.py


import tiktoken

from langchain_core.messages import SystemMessage
from langchain_core.messages import HumanMessage
from langchain_core.messages import AIMessage
from typing                  import List
from langchain_core.messages import BaseMessage
from langchain_core.messages import ToolMessage
from langchain_core.messages import trim_messages

messageList = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),
    HumanMessage("what do you call a speechless parrot")
]

def getStringTokenCount(text : str) -> int:
    encoding = tiktoken.get_encoding("o200k_base")
    return len(encoding.encode(text))

def tiktokenCounter(messageList : List[BaseMessage]) -> int:
    tokenCount           = 3  # 모든 답변은 <|start|>assistant<|message|>로 시작된다.
    tokenCountPerMessage = 3
    tokenCountPerName    = 1
    for message in messageList:
        if isinstance(message, HumanMessage):
            role = "user"
        elif isinstance(message, AIMessage):
            role = "assistant"
        elif isinstance(message, ToolMessage):
            role = "tool"
        elif isinstance(message, SystemMessage):
            role = "system"
        else:
            raise ValueError(f"Unsupported messages type {message.__class__}")
        tokenCount += (tokenCountPerMessage + getStringTokenCount(role) + getStringTokenCount(message.content))
        if message.name:
            tokenCount += tokenCountPerName + getStringTokenCount(message.name)
    return tokenCount

trimMessageList = trim_messages(
    messageList,
    max_tokens    = 45,
    strategy      = "last",
    token_counter = tiktokenCounter
)

print(trimMessageList)

"""
[
    AIMessage(
        content           = "Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!",
        additional_kwargs = {},
        response_metadata = {}
    ),
    HumanMessage(
        content           = 'what do you call a speechless parrot',
        additional_kwargs = {},
        response_metadata = {}
    )
]
"""

import tiktoken

from langchain_core.messages import SystemMessage

from langchain_core.messages import HumanMessage

from langchain_core.messages import AIMessage

from typing import List

from langchain_core.messages import BaseMessage

from langchain_core.messages import ToolMessage

from langchain_core.messages import trim_messages

messageList = [

SystemMessage("you're a good assistant, you always respond with a joke."),

HumanMessage("i wonder why it's called langchain"),

AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),

HumanMessage("and who is harrison chasing anyways"),

AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),

HumanMessage("what do you call a speechless parrot")

]

def getStringTokenCount(text : str) -> int:

encoding = tiktoken.get_encoding("o200k_base")

return len(encoding.encode(text))

def tiktokenCounter(messageList : List[BaseMessage]) -> int:

tokenCount = 3 # 모든 답변은 <|start|>assistant<|message|>로 시작된다.

tokenCountPerMessage = 3

tokenCountPerName = 1

for message in messageList:

if isinstance(message, HumanMessage):

role = "user"

elif isinstance(message, AIMessage):

role = "assistant"

elif isinstance(message, ToolMessage):

role = "tool"

elif isinstance(message, SystemMessage):

role = "system"

else:

raise ValueError(f"Unsupported messages type {message.__class__}")

tokenCount += (tokenCountPerMessage + getStringTokenCount(role) + getStringTokenCount(message.content))

if message.name:

tokenCount += tokenCountPerName + getStringTokenCount(message.name)

return tokenCount

trimMessageList = trim_messages(

messageList,

max_tokens = 45,

strategy = "last",

token_counter = tiktokenCounter

)

print(trimMessageList)

"""

[

AIMessage(

content = "Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!",

additional_kwargs = {},

response_metadata = {}

HumanMessage(

content = 'what do you call a speechless parrot',

additional_kwargs = {},

response_metadata = {}

)

]

"""

▶ requirements.txt


aiohappyeyeballs==2.4.4
aiohttp==3.11.10
aiosignal==1.3.2
annotated-types==0.7.0
anyio==4.7.0
attrs==24.3.0
certifi==2024.12.14
charset-normalizer==3.4.0
frozenlist==1.5.0
greenlet==3.1.1
h11==0.14.0
httpcore==1.0.7
httpx==0.28.1
idna==3.10
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.3.12
langchain-core==0.3.25
langchain-text-splitters==0.3.3
langsmith==0.2.3
multidict==6.1.0
numpy==2.2.0
orjson==3.10.12
packaging==24.2
propcache==0.2.1
pydantic==2.10.3
pydantic_core==2.27.1
PyYAML==6.0.2
regex==2024.11.6
requests==2.32.3
requests-toolbelt==1.0.0
sniffio==1.3.1
SQLAlchemy==2.0.36
tenacity==9.0.0
tiktoken==0.8.0
typing_extensions==4.12.2
urllib3==2.2.3
yarl==1.18.3

aiohappyeyeballs==2.4.4

aiohttp==3.11.10

aiosignal==1.3.2

annotated-types==0.7.0

anyio==4.7.0

attrs==24.3.0

certifi==2024.12.14

charset-normalizer==3.4.0

frozenlist==1.5.0

greenlet==3.1.1

h11==0.14.0

httpcore==1.0.7

httpx==0.28.1

idna==3.10

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.3.12

langchain-core==0.3.25

langchain-text-splitters==0.3.3

langsmith==0.2.3

multidict==6.1.0

numpy==2.2.0

orjson==3.10.12

packaging==24.2

propcache==0.2.1

pydantic==2.10.3

pydantic_core==2.27.1

PyYAML==6.0.2

regex==2024.11.6

requests==2.32.3

requests-toolbelt==1.0.0

sniffio==1.3.1

SQLAlchemy==2.0.36

tenacity==9.0.0

tiktoken==0.8.0

typing_extensions==4.12.2

urllib3==2.2.3

yarl==1.18.3

※ pip install langchain tiktoken

[PYTHON/LANGCHAIN] trimMessageList 함수 : strategy 인자에서 “first” 값 사용하기

■ trimMessageList 함수의 strategy 인자에서 "first" 값을 사용하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv                  import load_dotenv
from langchain_core.messages import SystemMessage
from langchain_core.messages import HumanMessage
from langchain_core.messages import AIMessage
from langchain_openai        import ChatOpenAI
from langchain_core.messages import trim_messages

load_dotenv()

messageList = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),
    HumanMessage("what do you call a speechless parrot")
]

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

trimMessageList = trim_messages(
    messageList,
    max_tokens     = 45,
    strategy       = "first",
    token_counter  = chatOpenAI
)

print(trimMessageList)

"""
[
    SystemMessage(
        content           = "you're a good assistant, you always respond with a joke.",
        additional_kwargs = {},
        response_metadata = {}
    ),
    HumanMessage(
        content           = "i wonder why it's called langchain",
        additional_kwargs = {},
        response_metadata = {}
    )
]
"""

from dotenv import load_dotenv

from langchain_core.messages import SystemMessage

from langchain_core.messages import HumanMessage

from langchain_core.messages import AIMessage

from langchain_openai import ChatOpenAI

from langchain_core.messages import trim_messages

load_dotenv()

messageList = [

SystemMessage("you're a good assistant, you always respond with a joke."),

HumanMessage("i wonder why it's called langchain"),

AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),

HumanMessage("and who is harrison chasing anyways"),

AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),

HumanMessage("what do you call a speechless parrot")

]

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

trimMessageList = trim_messages(

messageList,

max_tokens = 45,

strategy = "first",

token_counter = chatOpenAI

)

print(trimMessageList)

"""

[

SystemMessage(

content = "you're a good assistant, you always respond with a joke.",

additional_kwargs = {},

response_metadata = {}

HumanMessage(

content = "i wonder why it's called langchain",

additional_kwargs = {},

response_metadata = {}

)

]

"""

▶

[PYTHON/LANGCHAIN] trim_messages 함수 : start_on 인자를 사용해 첫번째 유형 메시지 확인하기 (시스템 메시지 제외)

■ trim_messages 함수의 start_on 인자를 사용해 첫번째 유형 메시지를 확인하는 방법을 보여준다. (시스템 메시지 제외) ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에

[PYTHON/LANGCHAIN] trim_messages 함수 : allow_partial 인자를 사용해 메시지 내용 분할하기

■ trim_messages 함수의 allow_partial 인자를 사용해 메시지 내용을 분할하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv                  import load_dotenv
from langchain_core.messages import SystemMessage
from langchain_core.messages import HumanMessage
from langchain_core.messages import AIMessage
from langchain_openai        import ChatOpenAI
from langchain_core.messages import trim_messages

load_dotenv()

messageList = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),
    HumanMessage("what do you call a speechless parrot")
]

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

trimMessageList = trim_messages(
    messageList,
    max_tokens     = 56,
    strategy       = "last",
    token_counter  = chatOpenAI,
    include_system = True,
    allow_partial  = True
)

print(trimMessageList)

"""
[
    SystemMessage(
        content = "you're a good assistant, you always respond with a joke.",
        additional_kwargs = {},
        response_metadata = {}
    ),
    AIMessage(
        content           = "\nWhy, he's probably chasing after the last cup of coffee in the office!",
        additional_kwargs = {},
        response_metadata = {}
    ),
    HumanMessage(
        content           = 'what do you call a speechless parrot',
        additional_kwargs = {},
        response_metadata = {}
    )
]
"""

from dotenv import load_dotenv

from langchain_core.messages import SystemMessage

from langchain_core.messages import HumanMessage

from langchain_core.messages import AIMessage

from langchain_openai import ChatOpenAI

from langchain_core.messages import trim_messages

load_dotenv()

messageList = [

SystemMessage("you're a good assistant, you always respond with a joke."),

HumanMessage("i wonder why it's called langchain"),

AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),

HumanMessage("and who is harrison chasing anyways"),

AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),

HumanMessage("what do you call a speechless parrot")

]

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

trimMessageList = trim_messages(

messageList,

max_tokens = 56,

strategy = "last",

token_counter = chatOpenAI,

include_system = True,

allow_partial = True

)

print(trimMessageList)

"""

[

SystemMessage(

content = "you're a good assistant, you always respond with a joke.",

additional_kwargs = {},

response_metadata = {}

AIMessage(

content = "\nWhy, he's probably chasing after the last cup of coffee in the office!",

additional_kwargs = {},

response_metadata = {}

HumanMessage(

content = 'what do you call a speechless parrot',

additional_kwargs = {},

response_metadata = {}

)

]

"""

[PYTHON/LANGCHAIN] trim_messages 함수 : include_system 인자를 사용해 초기 시스템 메시지 유지하기

■ trim_messages 함수의 include_system 인자를 사용해 초기 시스템 메시지를 유지하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py

[PYTHON/LANGCHAIN] trim_messages 함수 : max_tokens/strategy/token_counter 인자를 사용해 메시지 리스트 줄이기

■ trim_messages 함수의 max_tokens/strategy/token_counter 인자를 사용해 메시지 리스트를 줄이는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv                  import load_dotenv
from langchain_core.messages import SystemMessage
from langchain_core.messages import HumanMessage
from langchain_core.messages import AIMessage
from langchain_openai        import ChatOpenAI
from langchain_core.messages import trim_messages

load_dotenv()

messageList = [
    SystemMessage("you're a good assistant, you always respond with a joke."),
    HumanMessage("i wonder why it's called langchain"),
    AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),
    HumanMessage("what do you call a speechless parrot")
]

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

trimMessageList = trim_messages(
    messageList,
    max_tokens    = 45,
    strategy      = "last",
    token_counter = chatOpenAI
)

print(trimMessageList)

"""
[
    AIMessage(
        content           = "Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!",
        additional_kwargs = {},
        response_metadata = {}
    ),
    HumanMessage(
        content           = 'what do you call a speechless parrot',
        additional_kwargs = {},
        response_metadata = {}
    )
]
"""

from dotenv import load_dotenv

from langchain_core.messages import SystemMessage

from langchain_core.messages import HumanMessage

from langchain_core.messages import AIMessage

from langchain_openai import ChatOpenAI

from langchain_core.messages import trim_messages

load_dotenv()

messageList = [

SystemMessage("you're a good assistant, you always respond with a joke."),

HumanMessage("i wonder why it's called langchain"),

AIMessage('Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'),

HumanMessage("and who is harrison chasing anyways"),

AIMessage("Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!"),

HumanMessage("what do you call a speechless parrot")

]

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

trimMessageList = trim_messages(

messageList,

max_tokens = 45,

strategy = "last",

token_counter = chatOpenAI

)

print(trimMessageList)

"""

[

AIMessage(

content = "Hmmm let me think.\n\nWhy, he's probably chasing after the last cup of coffee in the office!",

additional_kwargs = {},

response_metadata = {}

HumanMessage(

content = 'what do you call a speechless parrot',

additional_kwargs = {},

response_metadata = {}

)

]

"""

[PYTHON/LANGCHAIN] RunnableWithMessageHistory 클래스 : invoke 메소드를 사용해 채팅하기

■ RunnableWithMessageHistory 클래스의 invoke 메소드를 사용해 채팅하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv                                     import load_dotenv
from langchain_community.tools.tavily_search    import TavilySearchResults
from langchain_openai                           import ChatOpenAI
from langchain_core.prompts                     import ChatPromptTemplate
from langchain.agents                           import AgentExecutor
from langchain.agents                           import create_tool_calling_agent
from langchain_community.chat_message_histories import ChatMessageHistory
from langchain_core.runnables.history           import RunnableWithMessageHistory
from langchain_core.messages                    import HumanMessage

load_dotenv()

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini", temperature = 0)

toolList = [TavilySearchResults(max_results = 1)]

chatPromptTemplate = ChatPromptTemplate.from_messages(
    [
        ("system"     , "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!"),
        ("placeholder", "{messages}"        ),
        ("placeholder", "{agent_scratchpad}")
    ]
)

runnableSequence = create_tool_calling_agent(chatOpenAI, toolList, chatPromptTemplate)

agentExecutor = AgentExecutor(agent = runnableSequence, tools = toolList, verbose = False)

chatMessageHistory = ChatMessageHistory()

runnableWithMessageHistory = RunnableWithMessageHistory(
    agentExecutor,
    lambda session_id : chatMessageHistory,
    input_messages_key  = "messages",
    output_messages_key = "output"
)

responseDictionary1 = runnableWithMessageHistory.invoke({"messages" : [HumanMessage("I'm Nemo!")]}, {"configurable" : {"session_id" : "unused"}})

print(responseDictionary1)

"""
{
    'messages' : [HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {})],
    'output'   : 'Hi Nemo! How can I assist you today?'
}
"""

responseDictionary2 = runnableWithMessageHistory.invoke({"messages" : [HumanMessage("What is my name?")]}, {"configurable" : {"session_id": "unused"}})

print(responseDictionary2)

"""
{
    'messages' : [
        HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {}),
        AIMessage(content = 'Hi Nemo! How can I assist you today?', additional_kwargs = {}, response_metadata = {}),
        HumanMessage(content = 'What is my name?', additional_kwargs = {}, response_metadata = {})
    ],
    'output'   : 'Your name is Nemo!'
}
"""

from dotenv import load_dotenv

from langchain_community.tools.tavily_search import TavilySearchResults

from langchain_openai import ChatOpenAI

from langchain_core.prompts import ChatPromptTemplate

from langchain.agents import AgentExecutor

from langchain.agents import create_tool_calling_agent

from langchain_community.chat_message_histories import ChatMessageHistory

from langchain_core.runnables.history import RunnableWithMessageHistory

from langchain_core.messages import HumanMessage

load_dotenv()

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini", temperature = 0)

toolList = [TavilySearchResults(max_results = 1)]

chatPromptTemplate = ChatPromptTemplate.from_messages(

[

("system" , "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!"),

("placeholder", "{messages}" ),

("placeholder", "{agent_scratchpad}")

]

)

runnableSequence = create_tool_calling_agent(chatOpenAI, toolList, chatPromptTemplate)

agentExecutor = AgentExecutor(agent = runnableSequence, tools = toolList, verbose = False)

chatMessageHistory = ChatMessageHistory()

runnableWithMessageHistory = RunnableWithMessageHistory(

agentExecutor,

lambda session_id : chatMessageHistory,

input_messages_key = "messages",

output_messages_key = "output"

)

responseDictionary1 = runnableWithMessageHistory.invoke({"messages" : [HumanMessage("I'm Nemo!")]}, {"configurable" : {"session_id" : "unused"}})

print(responseDictionary1)

"""

{

'messages' : [HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {})],

'output' : 'Hi Nemo! How can I assist you today?'

}

"""

responseDictionary2 = runnableWithMessageHistory.invoke({"messages" : [HumanMessage("What is my name?")]}, {"configurable" : {"session_id": "unused"}})

print(responseDictionary2)

"""

{

'messages' : [

HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {}),

AIMessage(content = 'Hi Nemo! How can I assist you today?', additional_kwargs = {}, response_metadata = {}),

HumanMessage(content = 'What is my name?', additional_kwargs = {}, response_metadata = {})

'output' : 'Your name is Nemo!'

}

"""

▶ requirements.txt

[PYTHON/LANGCHAIN] RunnableWithMessageHistory 클래스 : 생성자에서 input_messages_key/history_messages_key 인자를 사용해 RunnableWithMessageHistory 객체 만들기 3

■ RunnableWithMessageHistory 클래스의 생성자에서 input_messages_key/history_messages_key 인자를 사용해 RunnableWithMessageHistory 객체를 만드는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py

[PYTHON/LANGCHAIN] AgentExecutor 클래스 : invoke 메소드를 사용해 에이전트 호출하기 2

■ AgentExecutor 클래스의 invoke 메소드를 사용해 에이전트를 호출하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


#pip install python-dotenv langchain-community langchain-openai tavily-python

from dotenv                                  import load_dotenv
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_openai                        import ChatOpenAI
from langchain_core.prompts                  import ChatPromptTemplate
from langchain.agents                        import AgentExecutor
from langchain.agents                        import create_tool_calling_agent
from langchain_core.messages                 import HumanMessage
from langchain_core.messages                 import AIMessage

load_dotenv()

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini", temperature = 0)

toolList = [TavilySearchResults(max_results = 1)]

chatPromptTemplate = ChatPromptTemplate.from_messages(
    [
        ("system"     , "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!"),
        ("placeholder", "{messages}"        ),
        ("placeholder", "{agent_scratchpad}")
    ]
)

runnableSequence = create_tool_calling_agent(chatOpenAI, toolList, chatPromptTemplate)

agentExecutor = AgentExecutor(agent = runnableSequence, tools = toolList, verbose = False)

responseDictionary = agentExecutor.invoke(
    {
        "messages": [
            HumanMessage(content="I'm Nemo!"),
            AIMessage(content="Hello Nemo! How can I assist you today?"),
            HumanMessage(content="What is my name?"),
        ],
    }
)

print(responseDictionary)

"""
{
    'messages' : [
        HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {}),
        AIMessage(content = 'Hello Nemo! How can I assist you today?', additional_kwargs = {}, response_metadata = {}),
        HumanMessage(content = 'What is my name?', additional_kwargs = {}, response_metadata = {})
    ],
    'output'   : 'Your name is Nemo!'
}
"""

#pip install python-dotenv langchain-community langchain-openai tavily-python

from dotenv import load_dotenv

from langchain_community.tools.tavily_search import TavilySearchResults

from langchain_openai import ChatOpenAI

from langchain_core.prompts import ChatPromptTemplate

from langchain.agents import AgentExecutor

from langchain.agents import create_tool_calling_agent

from langchain_core.messages import HumanMessage

from langchain_core.messages import AIMessage

load_dotenv()

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini", temperature = 0)

toolList = [TavilySearchResults(max_results = 1)]

chatPromptTemplate = ChatPromptTemplate.from_messages(

[

("system" , "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!"),

("placeholder", "{messages}" ),

("placeholder", "{agent_scratchpad}")

]

)

runnableSequence = create_tool_calling_agent(chatOpenAI, toolList, chatPromptTemplate)

agentExecutor = AgentExecutor(agent = runnableSequence, tools = toolList, verbose = False)

responseDictionary = agentExecutor.invoke(

{

"messages": [

HumanMessage(content="I'm Nemo!"),

AIMessage(content="Hello Nemo! How can I assist you today?"),

HumanMessage(content="What is my name?"),

}

)

print(responseDictionary)

"""

{

'messages' : [

HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {}),

AIMessage(content = 'Hello Nemo! How can I assist you today?', additional_kwargs = {}, response_metadata = {}),

HumanMessage(content = 'What is my name?', additional_kwargs = {}, response_metadata = {})

'output' : 'Your name is Nemo!'

}

"""

▶

[PYTHON/LANGCHAIN] AgentExecutor 클래스 : invoke 메소드를 사용해 에이전트 호출하기 1

■ AgentExecutor 클래스의 invoke 메소드를 사용해 에이전트를 호출하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv                                  import load_dotenv
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_openai                        import ChatOpenAI
from langchain_core.prompts                  import ChatPromptTemplate
from langchain.agents                        import AgentExecutor
from langchain.agents                        import create_tool_calling_agent
from langchain_core.messages                 import HumanMessage

load_dotenv()

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini", temperature = 0)

toolList = [TavilySearchResults(max_results = 1)]

chatPromptTemplate = ChatPromptTemplate.from_messages(
    [
        ("system"     , "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!"),
        ("placeholder", "{messages}"        ),
        ("placeholder", "{agent_scratchpad}")
    ]
)

runnableSequence = create_tool_calling_agent(chatOpenAI, toolList, chatPromptTemplate)

agentExecutor = AgentExecutor(agent = runnableSequence, tools = toolList, verbose = False)

responseDictionary1 = agentExecutor.invoke({"messages" : [HumanMessage(content = "I'm Nemo!")]})

print(responseDictionary1)

"""
{
    'messages' : [HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {})],
    'output'   : 'Hi Nemo! How can I assist you today?'
}
"""

responseDictionary2 = agentExecutor.invoke({"messages" : [HumanMessage(content = "What is the current conservation status of the Great Barrier Reef?")]})

print(responseDictionary2)

"""
{
    'messages' : [HumanMessage(content = 'What is the current conservation status of the Great Barrier Reef?', additional_kwargs = {}, response_metadata = {})],
    'output'   : 'As of 2023, the Great Barrier Reef is experiencing dynamic responses to cycles of disturbance and recovery. While there have been small declines in coral cover, the overall regional hard coral cover remains similar to the levels reported in 2022. For more detailed information, you can check the full report [here](https://www.ncesc.com/geographic-faq/what-is-the-status-of-the-great-barrier-reef-in-2023/).'
}
"""

from dotenv import load_dotenv

from langchain_community.tools.tavily_search import TavilySearchResults

from langchain_openai import ChatOpenAI

from langchain_core.prompts import ChatPromptTemplate

from langchain.agents import AgentExecutor

from langchain.agents import create_tool_calling_agent

from langchain_core.messages import HumanMessage

load_dotenv()

chatOpenAI = ChatOpenAI(model = "gpt-4o-mini", temperature = 0)

toolList = [TavilySearchResults(max_results = 1)]

chatPromptTemplate = ChatPromptTemplate.from_messages(

[

("system" , "You are a helpful assistant. You may not need to use tools for every query - the user may just want to chat!"),

("placeholder", "{messages}" ),

("placeholder", "{agent_scratchpad}")

]

)

runnableSequence = create_tool_calling_agent(chatOpenAI, toolList, chatPromptTemplate)

agentExecutor = AgentExecutor(agent = runnableSequence, tools = toolList, verbose = False)

responseDictionary1 = agentExecutor.invoke({"messages" : [HumanMessage(content = "I'm Nemo!")]})

print(responseDictionary1)

"""

{

'messages' : [HumanMessage(content = "I'm Nemo!", additional_kwargs = {}, response_metadata = {})],

'output' : 'Hi Nemo! How can I assist you today?'

}

"""

responseDictionary2 = agentExecutor.invoke({"messages" : [HumanMessage(content = "What is the current conservation status of the Great Barrier Reef?")]})

print(responseDictionary2)

"""

{

'messages' : [HumanMessage(content = 'What is the current conservation status of the Great Barrier Reef?', additional_kwargs = {}, response_metadata = {})],

'output' : 'As of 2023, the Great Barrier Reef is experiencing dynamic responses to cycles of disturbance and recovery. While there have been small declines in coral cover, the overall regional hard coral cover remains similar to the levels reported in 2022. For more detailed information, you can check the full report [here](https://www.ncesc.com/geographic-faq/what-is-the-status-of-the-great-barrier-reef-in-2023/).'

}

"""

▶

[PYTHON/OPENPYXL] 엑셀 컬럼 위치 변환하기

■ 엑셀 컬럼 위치를 변환하는 방법을 보여준다. ▶ main.py


from string import ascii_uppercase

def getIndex(coordinate):
    columnString = "".join(filter(str.isalpha, coordinate.upper()))
    rowString    = "".join(filter(str.isdigit, coordinate))

    row    = int(rowString)
    column = 0

    for i, character in enumerate(reversed(columnString)):
        column += (ascii_uppercase.index(character) + 1) * (26 ** i)

    return (row, column)

def getCoordinate(y, x):
    columnString = ""
    while x > 0:
        x -= 1
        columnString = ascii_uppercase[x % 26] + columnString
        x //= 26
    return f"{columnString}{y}"

print(getIndex("A1"   )) # (1, 1)
print(getIndex("B2"   )) # (2, 2)
print(getIndex("AA1"  )) # (1, 27)
print(getIndex("ZZ100")) # (100, 702)

print(getCoordinate(  1,   1)) # "A1"
print(getCoordinate(  2,   2)) # "B2"
print(getCoordinate(  1,  27)) # "AA1"
print(getCoordinate(100, 702)) # "ZZ100"

from string import ascii_uppercase

def getIndex(coordinate):

columnString = "".join(filter(str.isalpha, coordinate.upper()))

rowString = "".join(filter(str.isdigit, coordinate))

row = int(rowString)

column = 0

for i, character in enumerate(reversed(columnString)):

column += (ascii_uppercase.index(character) + 1) * (26 ** i)

return (row, column)

def getCoordinate(y, x):

columnString = ""

while x > 0:

x -= 1

columnString = ascii_uppercase[x % 26] + columnString

x //= 26

return f"{columnString}{y}"

print(getIndex("A1" )) # (1, 1)

print(getIndex("B2" )) # (2, 2)

print(getIndex("AA1" )) # (1, 27)

print(getIndex("ZZ100")) # (100, 702)

print(getCoordinate( 1, 1)) # "A1"

print(getCoordinate( 2, 2)) # "B2"

print(getCoordinate( 1, 27)) # "AA1"

print(getCoordinate(100, 702)) # "ZZ100"

[PYTHON/OPENPYXL] Workbook 클래스 : save 메소드를 사용해 엑셀 파일 저장하기

■ Workbook 클래스의 save 메소드를 사용해 엑셀 파일을 저장하는 방법을 보여준다. ▶ main.py


from openpyxl import Workbook

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

workbook.save("example.xlsx")

from openpyxl import Workbook

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

workbook.save("example.xlsx")

▶ requirements.txt


et_xmlfile==2.0.0
openpyxl==3.1.5

et_xmlfile==2.0.0

openpyxl==3.1.5

※ pip install openpyxl 명령을

[PYTHON/OPENPYXL] Cell 클래스 : border 속성을 사용해 테두리 선 설정하기

■ Cell 클래스의 border 속성을 사용해 테두리 선을 설정하는 방법을 보여준다. ▶ main.py


from openpyxl        import Workbook
from openpyxl.styles import Side
from openpyxl.styles import Border

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

cell = worksheet.cell(row = 2, column = 2)

side1 = Side(border_style = "medium")
side2 = Side(border_style = "thin"  )

borderSideDictionary = {
    "top"    : side1,
    "bottom" : side2,
    "left"   : side2,
    "right"  : side1
}

border = Border(**borderSideDictionary)

cell.border = border

from openpyxl import Workbook

from openpyxl.styles import Side

from openpyxl.styles import Border

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

cell = worksheet.cell(row = 2, column = 2)

side1 = Side(border_style = "medium")

side2 = Side(border_style = "thin" )

borderSideDictionary = {

"top" : side1,

"bottom" : side2,

"left" : side2,

"right" : side1

}

border = Border(**borderSideDictionary)

cell.border = border

▶ requirements.txt


et_xmlfile==2.0.0
openpyxl==3.1.5

et_xmlfile==2.0.0

openpyxl==3.1.5

※ pip install openpyxl 명령을

[PYTHON/OPENPYXL] Border 클래스 : 생성자를 사용해 Border 객체 만들기

■ Border 클래스의 생성자를 사용해 Border 객체를 만드는 방법을 보여준다. ▶ main.py


from openpyxl.styles import Side
from openpyxl.styles import Border

side1 = Side(border_style = "medium")
side2 = Side(border_style = "thin"  )

borderSideDictionary = {
    "top"    : side1,
    "bottom" : side2,
    "left"   : side2,
    "right"  : side1
}

border = Border(**borderSideDictionary)

from openpyxl.styles import Side

from openpyxl.styles import Border

side1 = Side(border_style = "medium")

side2 = Side(border_style = "thin" )

borderSideDictionary = {

"top" : side1,

"bottom" : side2,

"left" : side2,

"right" : side1

}

border = Border(**borderSideDictionary)

▶ requirements.txt


et_xmlfile==2.0.0
openpyxl==3.1.5

et_xmlfile==2.0.0

openpyxl==3.1.5

※ pip install openpyxl 명령을 실행했다.

[PYTHON/OPENPYXL] Side 클래스 : 생성자에서 border_style 인자를 사용해 Side 객체 만들기

■ Side 클래스의 생성자에서 border_style 인자를 사용해 Side 객체를 만드는 방법을 보여준다. ▶ main.py


from openpyxl.styles import Side

side = Side(border_style = "medium")

from openpyxl.styles import Side

side = Side(border_style = "medium")

※ border_style 인자 : "dashed", "mediumDashed", "dashDot",

[PYTHON/OPENPYXL] Cell 클래스 : fill 속성을 사용해 셀 배경색 설정하기

■ Cell 클래스의 fill 속성을 사용해 셀 배경색을 설정하는 방법을 보여준다. ▶ main.py


from openpyxl        import Workbook
from openpyxl.styles import PatternFill

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

cell = worksheet.cell(row = 2, column = 2)

cell.fill = PatternFill(start_color = "ffff00", end_color = "ffff00", fill_type = "solid")

from openpyxl import Workbook

from openpyxl.styles import PatternFill

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

cell = worksheet.cell(row = 2, column = 2)

cell.fill = PatternFill(start_color = "ffff00", end_color = "ffff00", fill_type = "solid")

▶ requirements.txt


et_xmlfile==2.0.0
openpyxl==3.1.5

et_xmlfile==2.0.0

openpyxl==3.1.5

※ pip install openpyxl 명령을

[PYTHON/OPENPYXL] PatternFill 클래스 : 생성자에서 start_color/end_color/fill_type 인자를 사용해 PatternFill 객체 만들기

■ PatternFill 클래스의 생성자에서 start_color/end_color/fill_type 인자를 사용해 PatternFill 객체를 만드는 방법을 보여준다. ▶ main.py


from openpyxl.styles import PatternFill

patternFill = PatternFill(start_color = "ffff00", end_color = "ffff00", fill_type = "solid")

from openpyxl.styles import PatternFill

patternFill = PatternFill(start_color = "ffff00", end_color = "ffff00", fill_type = "solid")

▶ requirements.txt


et_xmlfile==2.0.0
openpyxl==3.1.5

et_xmlfile==2.0.0

openpyxl==3.1.5

※ pip install openpyxl

[PYTHON/OPENPYXL] Worksheet 클래스 : unmerge_cells 메소드를 사용해 셀 병합 취소하기

■ Worksheet 클래스의 unmerge_cells 메소드를 사용해 셀 병합을 취소하는 방법을 보여준다. ▶ main.py


from openpyxl import Workbook

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

worksheet.merge_cells("B2:C2")

worksheet.unmerge_cells("B2:C2")

from openpyxl import Workbook

workbook = Workbook()

worksheet = workbook.active

worksheet.cell(row = 2, column = 2, value = "문자열1")

worksheet.merge_cells("B2:C2")

worksheet.unmerge_cells("B2:C2")

▶ requirements.txt


et_xmlfile==2.0.0
openpyxl==3.1.5

et_xmlfile==2.0.0

openpyxl==3.1.5

※ pip install openpyxl 명령을