6월 2024 - 32 중 4 번째 페이지

[PYTHON/LANGCHAIN] BaseLoader 클래스 : 커스텀 문서 로더 만들기

■ BaseLoader 클래스를 사용해 커스텀 문서 로더를 만드는 방법을 보여준다. ▶ main.py


from typing import AsyncIterator
from typing import Iterator

from langchain_core.document_loaders import BaseLoader
from langchain_core.documents        import Document

class CustomDocumentLoader(BaseLoader):
    """파일을 한 줄씩 읽는 예제 문서 로더이다."""

    def __init__(self, filePath : str) -> None:
        """파일 경로로 로더를 초기화한다.

        인자:
            filePath : 로드할 파일의 경로이다.
        """
        self.filePath = filePath

    def lazy_load(self) -> Iterator[Document]:  # <-- 인자를 사용하지 않는다.
        """파일을 한 줄씩 읽는 지연 로더이다.

        지연 로드 메소드를 구현할 때 생성기를 사용하여 문서를 하나씩 생성해야 한다.
        """
        with open(self.filePath, encoding = "utf-8") as textIOWrapper:
            lineNumber = 0

            for line in textIOWrapper:
                yield Document(page_content = line, metadata = {"line_number" : lineNumber, "source" : self.filePath})

                lineNumber += 1

    # alazy_load는 선택사항이다.
    # 구현을 생략하면 lazy_load에 위임하는 기본 구현이 사용된다!
    async def alazy_load(self,) -> AsyncIterator[Document]:  # <-- 인자를 사용하지 않는다.
        """파일을 한 줄씩 읽는 비동기 지연 로더이다."""

        # aiofile이 필요하다.
        # `pip install aiofiles`로 설치한다.
        # https://github.com/Tinche/aiofiles
        import aiofiles

        async with aiofiles.open(self.filePath, encoding = "utf-8") as asyncTextIOWrapper:
            lineNumber = 0

            async for line in asyncTextIOWrapper:
                yield Document(page_content = line, metadata = {"line_number" : lineNumber, "source" : self.filePath})

                lineNumber += 1

with open("./meow.txt", "w", encoding="utf-8") as textIOWrapper:
    fileContent = "meow meow\nmeow meow\nmeow"
    textIOWrapper.write(fileContent)

customDocumentLoader = CustomDocumentLoader("./meow.txt")

documentList = customDocumentLoader.lazy_load()

for document in documentList:
    print(document.page_content)

"""
meow meow

meow meow

meow
"""

from typing import AsyncIterator

from typing import Iterator

from langchain_core.document_loaders import BaseLoader

from langchain_core.documents import Document

class CustomDocumentLoader(BaseLoader):

"""파일을 한 줄씩 읽는 예제 문서 로더이다."""

def __init__(self, filePath : str) -> None:

"""파일 경로로 로더를 초기화한다.

인자:

filePath : 로드할 파일의 경로이다.

"""

self.filePath = filePath

def lazy_load(self) -> Iterator[Document]: # <-- 인자를 사용하지 않는다.

"""파일을 한 줄씩 읽는 지연 로더이다.

지연 로드 메소드를 구현할 때 생성기를 사용하여 문서를 하나씩 생성해야 한다.

"""

with open(self.filePath, encoding = "utf-8") as textIOWrapper:

lineNumber = 0

for line in textIOWrapper:

yield Document(page_content = line, metadata = {"line_number" : lineNumber, "source" : self.filePath})

lineNumber += 1

# alazy_load는 선택사항이다.

# 구현을 생략하면 lazy_load에 위임하는 기본 구현이 사용된다!

async def alazy_load(self,) -> AsyncIterator[Document]: # <-- 인자를 사용하지 않는다.

"""파일을 한 줄씩 읽는 비동기 지연 로더이다."""

# aiofile이 필요하다.

# `pip install aiofiles`로 설치한다.

# https://github.com/Tinche/aiofiles

import aiofiles

async with aiofiles.open(self.filePath, encoding = "utf-8") as asyncTextIOWrapper:

lineNumber = 0

async for line in asyncTextIOWrapper:

yield Document(page_content = line, metadata = {"line_number" : lineNumber, "source" : self.filePath})

lineNumber += 1

with open("./meow.txt", "w", encoding="utf-8") as textIOWrapper:

fileContent = "meow meow\nmeow meow\nmeow"

textIOWrapper.write(fileContent)

customDocumentLoader = CustomDocumentLoader("./meow.txt")

documentList = customDocumentLoader.lazy_load()

for document in documentList:

print(document.page_content)

"""

meow meow

meow

"""

▶ requirements.txt


aiofiles==24.1.0
aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
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
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiofiles==24.1.0

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

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

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community aiofiles 명령을

[PYTHON/LANGCHAIN] PDFPlumberLoader 클래스 : load 메소드를 사용해 PDF 파일 문서 로드하기

■ PDFPlumberLoader 클래스의 load 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import PDFPlumberLoader

pdfPlumberLoader = PDFPlumberLoader("nke-10k-2023.pdf")

documentList = pdfPlumberLoader.load()

for document in documentList[:3]:
    print(document.page_content)
    print()

"""
FFOORRMM 1100--KK

UNITED STATES
SECURITIES AND EXCHANGE COMMISSION
Washington, D.C. 20549
FORM 10-K
(Mark One)
☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE FISCAL YEAR ENDED MAY 31, 2023
OR
☐TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE TRANSITION PERIOD FROM TO .
Commission File No. 1-10635
NIKE, Inc.
(Exact name of Registrant as specified in its charter)
Oregon 93-0584541
(State or other jurisdiction of incorporation) (IRS Employer Identification No.)
One Bowerman Drive, Beaverton, Oregon 97005-6453
(Address of principal executive offices and zip code)
(503) 671-6453
(Registrant's telephone number, including area code)
SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:
Class B Common Stock NKE New York Stock Exchange
(Title of each class) (Trading symbol) (Name of each exchange on which registered)
SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:
NONE
Indicate by check mark: YES NO
• if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨
• if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ
• whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities þ ¨
Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required
to file such reports), and (2) has been subject to such filing requirements for the past 90 days.
• whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to þ ¨
Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period
that the registrant was required to submit such files).
• whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth
company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of
the Exchange Act.
Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐
• if an emerging growth company, if the registrant has elected not to use the extended transition period for ¨
complying with any new or revised financial accounting standards provided pursuant to Section 13(a) of the
Exchange Act.
• whether the registrant has filed a report on and attestation to its management's assessment of the effectiveness of þ
its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by
the registered public accounting firm that prepared or issued its audit report.
• if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant ¨
included in the filing reflect the correction of an error to previously issued financial statements.
• whether any of those error corrections are restatements that required a recovery analysis of incentive-based ¨
compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to
§ 240.10D-1(b).
• whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ
As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:
Class A $ 7,831,564,572
Class B 136,467,702,472
$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:
Class A 304,897,252
Class B 1,225,074,356
1,529,971,608
DOCUMENTS INCORPORATED BY REFERENCE:
Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III
of this report.
"""

from langchain_community.document_loaders import PDFPlumberLoader

pdfPlumberLoader = PDFPlumberLoader("nke-10k-2023.pdf")

documentList = pdfPlumberLoader.load()

for document in documentList[:3]:

print(document.page_content)

print()

"""

FFOORRMM 1100--KK

UNITED STATES

SECURITIES AND EXCHANGE COMMISSION

Washington, D.C. 20549

FORM 10-K

(Mark One)

☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE FISCAL YEAR ENDED MAY 31, 2023

☐TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE TRANSITION PERIOD FROM TO .

Commission File No. 1-10635

NIKE, Inc.

(Exact name of Registrant as specified in its charter)

Oregon 93-0584541

(State or other jurisdiction of incorporation) (IRS Employer Identification No.)

One Bowerman Drive, Beaverton, Oregon 97005-6453

(Address of principal executive offices and zip code)

(503) 671-6453

(Registrant's telephone number, including area code)

SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:

Class B Common Stock NKE New York Stock Exchange

(Title of each class) (Trading symbol) (Name of each exchange on which registered)

SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:

NONE

Indicate by check mark: YES NO

• if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨

• if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ

• whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities þ ¨

Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required

to file such reports), and (2) has been subject to such filing requirements for the past 90 days.

• whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to þ ¨

Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period

that the registrant was required to submit such files).

• whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth

company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of

the Exchange Act.

Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐

• if an emerging growth company, if the registrant has elected not to use the extended transition period for ¨

complying with any new or revised financial accounting standards provided pursuant to Section 13(a) of the

Exchange Act.

• whether the registrant has filed a report on and attestation to its management's assessment of the effectiveness of þ

its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by

the registered public accounting firm that prepared or issued its audit report.

• if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant ¨

included in the filing reflect the correction of an error to previously issued financial statements.

• whether any of those error corrections are restatements that required a recovery analysis of incentive-based ¨

compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to

§ 240.10D-1(b).

• whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ

As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:

Class A $ 7,831,564,572

Class B 136,467,702,472

$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:

Class A 304,897,252

Class B 1,225,074,356

1,529,971,608

DOCUMENTS INCORPORATED BY REFERENCE:

Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III

of this report.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
cffi==1.16.0
charset-normalizer==3.3.2
cryptography==42.0.8
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pdfminer.six==20231228
pdfplumber==0.11.1
pillow==10.3.0
pycparser==2.22
pydantic==2.7.4
pydantic_core==2.18.4
pypdfium2==4.30.0
PyYAML==6.0.1
requests==2.32.3
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

cffi==1.16.0

charset-normalizer==3.3.2

cryptography==42.0.8

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pdfminer.six==20231228

pdfplumber==0.11.1

pillow==10.3.0

pycparser==2.22

pydantic==2.7.4

pydantic_core==2.18.4

pypdfium2==4.30.0

PyYAML==6.0.1

requests==2.32.3

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community

[PYTHON/COMMON] pdfplumber 패키지 설치하기

■ pdfplumber 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install pdfplumber

pip install pdfplumber

[PYTHON/LANGCHAIN] PyPDFDirectoryLoader 클래스 : load 메소드를 사용해 PDF 파일 문서 로드하기

■ PyPDFDirectoryLoader 클래스의 load 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import PyPDFDirectoryLoader

pyPDFDirectoryLoader = PyPDFDirectoryLoader("./")

documentList = pyPDFDirectoryLoader.load()

for document in documentList[:3]:
    print(document.page_content)
    print()

"""
FORM 10-K FORM 10-K

UNITED STATES
SECURITIES AND EXCHANGE COMMISSION
Washington, D.C. 20549
FORM 10-K
(Mark One)
☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE FISCAL YEAR ENDED MAY 31, 2023
OR
☐TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE TRANSITION PERIOD FROM TO .
Commission File No. 1-10635
NIKE, Inc.
(Exact name of Registrant as specified in its charter)
Oregon 93-0584541
(State or other jurisdiction of incorporation) (IRS Employer Identification No.)
One Bowerman Drive, Beaverton, Oregon 97005-6453
(Address of principal executive offices and zip code)
(503) 671-6453
(Registrant's telephone number, including area code)
SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:
Class B Common Stock NKE New York Stock Exchange
(Title of each class) (Trading symbol) (Name of each exchange on which registered)
SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:
NONE
Indicate by check mark: YES NO
•if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨
•if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ
•whether the registrant (1) has filed all reports required to be filed by S ection 13 or 15(d) of the Securities
Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required
to file such reports), and (2) has been subject to such filing requirements for the past 90 days.þ ¨
•whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to
Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period
that the registrant was required to submit such files).þ ¨
•whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth
company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of
the Exchange Act.
Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐
•if an emerging growth company, if the registrant has elected not to use the extended transition period for
complying with any new or revised financial accounting standards provided pursuant to S ection 13(a) of the
Exchange Act.¨
•whether the registrant has filed a report on and attestation to its management's assessment of the ef fectiveness of
its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by
the registered public accounting firm that prepared or issued its audit report.þ
•if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant
included in the filing reflect the correction of an error to previously issued financial statements. ¨
•whether any of those error corrections are restatements that required a recovery analysis of incentive-based
compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to
§ 240.10D-1(b). ¨
•whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ
As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:
Class A $ 7,831,564,572
Class B 136,467,702,472
$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:
Class A  304,897,252
Class B  1,225,074,356
 1,529,971,608
DOCUMENTS INCORPORATED BY REFERENCE:
Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III
of this report.
"""

from langchain_community.document_loaders import PyPDFDirectoryLoader

pyPDFDirectoryLoader = PyPDFDirectoryLoader("./")

documentList = pyPDFDirectoryLoader.load()

for document in documentList[:3]:

print(document.page_content)

print()

"""

FORM 10-K FORM 10-K

UNITED STATES

SECURITIES AND EXCHANGE COMMISSION

Washington, D.C. 20549

FORM 10-K

(Mark One)

☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE FISCAL YEAR ENDED MAY 31, 2023

☐TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE TRANSITION PERIOD FROM TO .

Commission File No. 1-10635

NIKE, Inc.

(Exact name of Registrant as specified in its charter)

Oregon 93-0584541

(State or other jurisdiction of incorporation) (IRS Employer Identification No.)

One Bowerman Drive, Beaverton, Oregon 97005-6453

(Address of principal executive offices and zip code)

(503) 671-6453

(Registrant's telephone number, including area code)

SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:

Class B Common Stock NKE New York Stock Exchange

(Title of each class) (Trading symbol) (Name of each exchange on which registered)

SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:

NONE

Indicate by check mark: YES NO

•if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨

•if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ

•whether the registrant (1) has filed all reports required to be filed by S ection 13 or 15(d) of the Securities

Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required

to file such reports), and (2) has been subject to such filing requirements for the past 90 days.þ ¨

•whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to

Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period

that the registrant was required to submit such files).þ ¨

•whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth

company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of

the Exchange Act.

Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐

•if an emerging growth company, if the registrant has elected not to use the extended transition period for

complying with any new or revised financial accounting standards provided pursuant to S ection 13(a) of the

Exchange Act.¨

•whether the registrant has filed a report on and attestation to its management's assessment of the ef fectiveness of

its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by

the registered public accounting firm that prepared or issued its audit report.þ

•if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant

included in the filing reflect the correction of an error to previously issued financial statements. ¨

•whether any of those error corrections are restatements that required a recovery analysis of incentive-based

compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to

§ 240.10D-1(b). ¨

•whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ

As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:

Class A $ 7,831,564,572

Class B 136,467,702,472

$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:

Class A 304,897,252

Class B 1,225,074,356

1,529,971,608

DOCUMENTS INCORPORATED BY REFERENCE:

Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III

of this report.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pydantic==2.7.4
pydantic_core==2.18.4
pypdf==4.2.0
PyYAML==6.0.1
requests==2.32.3
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pydantic==2.7.4

pydantic_core==2.18.4

pypdf==4.2.0

PyYAML==6.0.1

requests==2.32.3

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community

[PYTHON/LANGCHAIN] PDFMinerPDFasHTMLLoader 클래스 : load 메소드를 사용해 PDF 파일 문서 로드하기

■ PDFMinerPDFasHTMLLoader 클래스의 load 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


import re

from bs4 import BeautifulSoup

from langchain_community.document_loaders import PDFMinerPDFasHTMLLoader
from langchain_core.documents             import Document

pdfMinerPDFasHTMLLoader = PDFMinerPDFasHTMLLoader("nke-10k-2023.pdf")

documentList = pdfMinerPDFasHTMLLoader.load()

document = documentList[0]

beautifulSoup = BeautifulSoup(document.page_content, "html.parser")

resultSet = beautifulSoup.find_all("div")

currentFontSize = None
currentText     = ""

snippetList = [] # (text, fontSize) 튜플 리스트

for result in resultSet:
    span = result.find("span")

    if not span:
        continue

    style = span.get("style")

    if not style:
        continue

    fontSizeString = re.findall("font-size:(\d+)px", style)

    if not fontSizeString:
        continue

    fontSize = int(fontSizeString[0])

    if not currentFontSize:
        currentFontSize = fontSize

    if fontSize == currentFontSize:
        currentText += result.text
    else:
        snippetList.append((currentText, currentFontSize))

        currentFontSize = fontSize
        currentText     = result.text

snippetList.append((currentText, currentFontSize))

# for snippet in snippetList[:3]:
#     print(snippet)

"""
('FORM 10-K\nFORM 10-K\n', 29)
('UNITED STATES\nSECURITIES AND EXCHANGE COMMISSION\nWashington, D.C. 20549\n', 7)
('FORM 10-K \n', 10)
"""

currentIndex                = -1
semanticSnippetDocumentList = []

# 가정 : 제목은 해당 내용보다 글꼴 크기가 더 크다.
for snippet in snippetList:
    # 현재 조각의 글꼴 크기 > 이전 섹션의 제목 => 새 제목인 경우
    if (not semanticSnippetDocumentList or snippet[1] > semanticSnippetDocumentList[currentIndex].metadata["heading_font"]):
        metadataDictionary = {"heading" : snippet[0], "content_font" : 0, "heading_font" : snippet[1]}

        metadataDictionary.update(document.metadata)

        semanticSnippetDocumentList.append(Document(page_content = "", metadata = metadataDictionary))

        currentIndex += 1

        continue

    # 현재 조각의 글꼴 크기 <= 이전 섹션의 콘텐츠 => 콘텐츠가 동일한 섹션에 속하는 경우
    # (필요한 경우 하위 섹션에 대해 트리와 같은 구조를 만들 수도 있지만 이는 더 많은 생각이 필요할 수 있으며 데이터에 따라 다를 수 있다)
    if (not semanticSnippetDocumentList[currentIndex].metadata["content_font"] or snippet[1] <= semanticSnippetDocumentList[currentIndex].metadata["content_font"]):
        semanticSnippetDocumentList[currentIndex].page_content += snippet[0]

        semanticSnippetDocumentList[currentIndex].metadata["content_font"] = max(snippet[1], semanticSnippetDocumentList[currentIndex].metadata["content_font"])

        continue

    # 현재 조각의 글꼴 크기가 이전 섹션의 내용보다 크지만 이전 섹션의 제목보다 작은 경우 새 섹션을 만드는 것
    # (예 : PDF 제목의 글꼴 크기가 가장 높지만 모든 섹션을 포함하는 것을 원하지 않는다)
    metadataDictionary = {"heading" : snippet[0], "content_font" : 0, "heading_font" : snippet[1]}

    metadataDictionary.update(document.metadata)

    semanticSnippetDocumentList.append(Document(page_content = "", metadata = metadataDictionary))

    currentIndex += 1

for semanticSnippetDocument in semanticSnippetDocumentList[:3]:
    print(semanticSnippetDocument.page_content)
    print()

"""
UNITED STATES
SECURITIES AND EXCHANGE COMMISSION
Washington, D.C. 20549

(Mark One)
☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE FISCAL YEAR ENDED MAY 31, 2023
OR
☐ TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE TRANSITION PERIOD FROM
TO
.
Commission File No. 1-10635

(Exact name of Registrant as specified in its charter)
Oregon
(State or other jurisdiction of incorporation)
93-0584541
(IRS Employer Identification No.)
One Bowerman Drive, Beaverton, Oregon 97005-6453
(Address of principal executive offices and zip code)
(503) 671-6453
(Registrant's telephone number, including area code)
SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:
Class B Common Stock
(Title of each class)
NKE
New York Stock Exchange
(Trading symbol)
(Name of each exchange on which registered)
SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:
NONE
Indicate by check mark:
• if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act.
• if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act.
• whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities
Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required
to file such reports), and (2) has been subject to such filing requirements for the past 90 days.
"""

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

import re

from bs4 import BeautifulSoup

from langchain_community.document_loaders import PDFMinerPDFasHTMLLoader

from langchain_core.documents import Document

pdfMinerPDFasHTMLLoader = PDFMinerPDFasHTMLLoader("nke-10k-2023.pdf")

documentList = pdfMinerPDFasHTMLLoader.load()

document = documentList[0]

beautifulSoup = BeautifulSoup(document.page_content, "html.parser")

resultSet = beautifulSoup.find_all("div")

currentFontSize = None

currentText = ""

snippetList = [] # (text, fontSize) 튜플 리스트

for result in resultSet:

span = result.find("span")

if not span:

continue

style = span.get("style")

if not style:

continue

fontSizeString = re.findall("font-size:(\d+)px", style)

if not fontSizeString:

continue

fontSize = int(fontSizeString[0])

if not currentFontSize:

currentFontSize = fontSize

if fontSize == currentFontSize:

currentText += result.text

else:

snippetList.append((currentText, currentFontSize))

currentFontSize = fontSize

currentText = result.text

snippetList.append((currentText, currentFontSize))

# for snippet in snippetList[:3]:

# print(snippet)

"""

('FORM 10-K\nFORM 10-K\n', 29)

('UNITED STATES\nSECURITIES AND EXCHANGE COMMISSION\nWashington, D.C. 20549\n', 7)

('FORM 10-K \n', 10)

"""

currentIndex = -1

semanticSnippetDocumentList = []

# 가정 : 제목은 해당 내용보다 글꼴 크기가 더 크다.

for snippet in snippetList:

# 현재 조각의 글꼴 크기 > 이전 섹션의 제목 => 새 제목인 경우

if (not semanticSnippetDocumentList or snippet[1] > semanticSnippetDocumentList[currentIndex].metadata["heading_font"]):

metadataDictionary = {"heading" : snippet[0], "content_font" : 0, "heading_font" : snippet[1]}

metadataDictionary.update(document.metadata)

semanticSnippetDocumentList.append(Document(page_content = "", metadata = metadataDictionary))

currentIndex += 1

continue

# 현재 조각의 글꼴 크기 <= 이전 섹션의 콘텐츠 => 콘텐츠가 동일한 섹션에 속하는 경우

# (필요한 경우 하위 섹션에 대해 트리와 같은 구조를 만들 수도 있지만 이는 더 많은 생각이 필요할 수 있으며 데이터에 따라 다를 수 있다)

if (not semanticSnippetDocumentList[currentIndex].metadata["content_font"] or snippet[1] <= semanticSnippetDocumentList[currentIndex].metadata["content_font"]):

semanticSnippetDocumentList[currentIndex].page_content += snippet[0]

semanticSnippetDocumentList[currentIndex].metadata["content_font"] = max(snippet[1], semanticSnippetDocumentList[currentIndex].metadata["content_font"])

continue

# 현재 조각의 글꼴 크기가 이전 섹션의 내용보다 크지만 이전 섹션의 제목보다 작은 경우 새 섹션을 만드는 것

# (예 : PDF 제목의 글꼴 크기가 가장 높지만 모든 섹션을 포함하는 것을 원하지 않는다)

metadataDictionary = {"heading" : snippet[0], "content_font" : 0, "heading_font" : snippet[1]}

metadataDictionary.update(document.metadata)

semanticSnippetDocumentList.append(Document(page_content = "", metadata = metadataDictionary))

currentIndex += 1

for semanticSnippetDocument in semanticSnippetDocumentList[:3]:

print(semanticSnippetDocument.page_content)

print()

"""

UNITED STATES

SECURITIES AND EXCHANGE COMMISSION

Washington, D.C. 20549

(Mark One)

☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE FISCAL YEAR ENDED MAY 31, 2023

☐ TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE TRANSITION PERIOD FROM

Commission File No. 1-10635

(Exact name of Registrant as specified in its charter)

Oregon

(State or other jurisdiction of incorporation)

93-0584541

(IRS Employer Identification No.)

One Bowerman Drive, Beaverton, Oregon 97005-6453

(Address of principal executive offices and zip code)

(503) 671-6453

(Registrant's telephone number, including area code)

SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:

Class B Common Stock

(Title of each class)

NKE

New York Stock Exchange

(Trading symbol)

(Name of each exchange on which registered)

SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:

NONE

Indicate by check mark:

• if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act.

• if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act.

• whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities

Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required

to file such reports), and (2) has been subject to such filing requirements for the past 90 days.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
beautifulsoup4==4.12.3
bs4==0.0.2
certifi==2024.6.2
cffi==1.16.0
charset-normalizer==3.3.2
cryptography==42.0.8
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pdfminer.six==20231228
pycparser==2.22
pydantic==2.7.4
pydantic_core==2.18.4
PyYAML==6.0.1
requests==2.32.3
soupsieve==2.5
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

beautifulsoup4==4.12.3

bs4==0.0.2

certifi==2024.6.2

cffi==1.16.0

charset-normalizer==3.3.2

cryptography==42.0.8

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pdfminer.six==20231228

pycparser==2.22

pydantic==2.7.4

pydantic_core==2.18.4

PyYAML==6.0.1

requests==2.32.3

soupsieve==2.5

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community

[PYTHON/LANGCHAIN] PDFMinerPDFasHTMLLoader 클래스 : PDF 파일 로드 후 HTML 텍스트 만들기

■ PDFMinerPDFasHTMLLoader 클래스를 사용해 PDF 파일 로드 후 HTML 텍스트를 만드는 방법을 보여준다. ▶ main.py


from bs4 import BeautifulSoup

from langchain_community.document_loaders import PDFMinerPDFasHTMLLoader

pdfMinerPDFasHTMLLoader = PDFMinerPDFasHTMLLoader("nke-10k-2023.pdf")

documentList = pdfMinerPDFasHTMLLoader.load()

document = documentList[0]

soup = BeautifulSoup(document.page_content, "html.parser")

resultSet = soup.find_all("div")

for result in resultSet[:2]:
    print(result)
    print()

"""
<div style="position:absolute; top:50px;"><a name="1">Page 1</a></div>

<div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:422px; top:192px; width:138px; height:29px;"><span style="font-family: FuturaStd-CondensedExtraBd; font-size:29px">FORM 10-K
<br/>FORM 10-K
<br/></span></div>
"""

from bs4 import BeautifulSoup

from langchain_community.document_loaders import PDFMinerPDFasHTMLLoader

pdfMinerPDFasHTMLLoader = PDFMinerPDFasHTMLLoader("nke-10k-2023.pdf")

documentList = pdfMinerPDFasHTMLLoader.load()

document = documentList[0]

soup = BeautifulSoup(document.page_content, "html.parser")

resultSet = soup.find_all("div")

for result in resultSet[:2]:

print(result)

print()

"""

<div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:422px; top:192px; width:138px; height:29px;"><span style="font-family: FuturaStd-CondensedExtraBd; font-size:29px">FORM 10-K

<br/>FORM 10-K

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
beautifulsoup4==4.12.3
bs4==0.0.2
certifi==2024.6.2
cffi==1.16.0
charset-normalizer==3.3.2
cryptography==42.0.8
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pdfminer.six==20231228
pycparser==2.22
pydantic==2.7.4
pydantic_core==2.18.4
PyYAML==6.0.1
requests==2.32.3
soupsieve==2.5
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

beautifulsoup4==4.12.3

bs4==0.0.2

certifi==2024.6.2

cffi==1.16.0

charset-normalizer==3.3.2

cryptography==42.0.8

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pdfminer.six==20231228

pycparser==2.22

pydantic==2.7.4

pydantic_core==2.18.4

PyYAML==6.0.1

requests==2.32.3

soupsieve==2.5

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install

[PYTHON/COMMON] PDFMinerLoader 클래스 : load 메소드를 사용해 PDF 파일 문서 로드하기

■ PDFMinerLoader 클래스의 load 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ※ PDFMinerLoader 클래스는 PDF 파일을 하나의 Document 객체로 로드한다. ▶

[PYTHON/COMMON] pdfminer.six 패키지 설치하기

■ pdfminer.six 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install pdfminer.six

pip install pdfminer.six

[PYTHON/LANGCHAIN] PyPDFium2Loader 클래스 : load 메소드를 사용해 PDF 파일 문서 로드하기

■ PyPDFium2Loader 클래스의 load 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import PyPDFium2Loader

pyPDFium2Loader = PyPDFium2Loader("nke-10k-2023.pdf")

documentList = pyPDFium2Loader.load()

for document in documentList[:3]:
    print(document.page_content)
    print()

"""
  warnings.warn("get_text_range() call with default params will be implicitly redirected to get_text_bounded()")
FORM 10-K

UNITED STATES
SECURITIES AND EXCHANGE COMMISSION
Washington, D.C. 20549
FORM 10-K
(Mark One)
☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE FISCAL YEAR ENDED MAY 31, 2023
OR
☐ TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE TRANSITION PERIOD FROM TO .
Commission File No. 1-10635
NIKE, Inc.
(Exact name of Registrant as specified in its charter)
Oregon 93-0584541
(State or other jurisdiction of incorporation) (IRS Employer Identification No.)
One Bowerman Drive, Beaverton, Oregon 97005-6453
(Address of principal executive offices and zip code)
(503) 671-6453
(Registrant's telephone number, including area code)
SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:
Class B Common Stock NKE New York Stock Exchange
(Title of each class) (Trading symbol) (Name of each exchange on which registered)
SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:
NONE
Indicate by check mark: YES NO
• if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨
• if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ
• whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities
Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required
to file such reports), and (2) has been subject to such filing requirements for the past 90 days.
þ ¨
• whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to
Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period
that the registrant was required to submit such files).
þ ¨
• whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth
company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of
the Exchange Act.
Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐
• if an emerging growth company, if the registrant has elected not to use the extended transition period for
complying with any new or revised financial accounting standards provided pursuant to Section 13(a) of the
Exchange Act.
¨
• whether the registrant has filed a report on and attestation to its management's assessment of the effectiveness of
its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by
the registered public accounting firm that prepared or issued its audit report.
þ
• if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant
included in the filing reflect the correction of an error to previously issued financial statements.
¨
• whether any of those error corrections are restatements that required a recovery analysis of incentive-based
compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to
§ 240.10D-1(b).
¨
• whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ
As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:
Class A $ 7,831,564,572
Class B 136,467,702,472
$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:
Class A 304,897,252
Class B 1,225,074,356
 1,529,971,608
DOCUMENTS INCORPORATED BY REFERENCE:
Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III
of this report.
"""

from langchain_community.document_loaders import PyPDFium2Loader

pyPDFium2Loader = PyPDFium2Loader("nke-10k-2023.pdf")

documentList = pyPDFium2Loader.load()

for document in documentList[:3]:

print(document.page_content)

print()

"""

warnings.warn("get_text_range() call with default params will be implicitly redirected to get_text_bounded()")

FORM 10-K

UNITED STATES

SECURITIES AND EXCHANGE COMMISSION

Washington, D.C. 20549

FORM 10-K

(Mark One)

☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE FISCAL YEAR ENDED MAY 31, 2023

☐ TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE TRANSITION PERIOD FROM TO .

Commission File No. 1-10635

NIKE, Inc.

(Exact name of Registrant as specified in its charter)

Oregon 93-0584541

(State or other jurisdiction of incorporation) (IRS Employer Identification No.)

One Bowerman Drive, Beaverton, Oregon 97005-6453

(Address of principal executive offices and zip code)

(503) 671-6453

(Registrant's telephone number, including area code)

SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:

Class B Common Stock NKE New York Stock Exchange

(Title of each class) (Trading symbol) (Name of each exchange on which registered)

SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:

NONE

Indicate by check mark: YES NO

• if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨

• if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ

• whether the registrant (1) has filed all reports required to be filed by Section 13 or 15(d) of the Securities

Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required

to file such reports), and (2) has been subject to such filing requirements for the past 90 days.

þ ¨

• whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to

Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period

that the registrant was required to submit such files).

þ ¨

• whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth

company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of

the Exchange Act.

Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐

• if an emerging growth company, if the registrant has elected not to use the extended transition period for

complying with any new or revised financial accounting standards provided pursuant to Section 13(a) of the

Exchange Act.

• whether the registrant has filed a report on and attestation to its management's assessment of the effectiveness of

its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by

the registered public accounting firm that prepared or issued its audit report.

• if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant

included in the filing reflect the correction of an error to previously issued financial statements.

• whether any of those error corrections are restatements that required a recovery analysis of incentive-based

compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to

§ 240.10D-1(b).

• whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ

As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:

Class A $ 7,831,564,572

Class B 136,467,702,472

$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:

Class A 304,897,252

Class B 1,225,074,356

1,529,971,608

DOCUMENTS INCORPORATED BY REFERENCE:

Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III

of this report.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pydantic==2.7.4
pydantic_core==2.18.4
pypdfium2==4.30.0
PyYAML==6.0.1
requests==2.32.3
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pydantic==2.7.4

pydantic_core==2.18.4

pypdfium2==4.30.0

PyYAML==6.0.1

requests==2.32.3

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community

[PYTHON/COMMON] pypdfium2 패키지 설치하기

■ pypdfium2 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install pypdfium2

pip install pypdfium2

[PYTHON/COMMON] pdfminer 패키지 설치하기

■ pdfminer 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install pdfminer

pip install pdfminer

[PYTHON/LANGCHAIN] PyPDFLoader 클래스 : load_and_split 메소드를 사용해 PDF 파일 문서 로드하기

■ PyPDFLoader 클래스의 load_and_split 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import PyPDFLoader

pyPDFLoader = PyPDFLoader("./nke-10k-2023.pdf")

documentList = pyPDFLoader.load_and_split()

for document in documentList[:3]:
    print(document.page_content)
    print()

"""
FORM 10-K FORM 10-K

UNITED STATES
SECURITIES AND EXCHANGE COMMISSION
Washington, D.C. 20549
FORM 10-K
(Mark One)
☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE FISCAL YEAR ENDED MAY 31, 2023
OR
☐TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934
FOR THE TRANSITION PERIOD FROM TO .
Commission File No. 1-10635
NIKE, Inc.
(Exact name of Registrant as specified in its charter)
Oregon 93-0584541
(State or other jurisdiction of incorporation) (IRS Employer Identification No.)
One Bowerman Drive, Beaverton, Oregon 97005-6453
(Address of principal executive offices and zip code)
(503) 671-6453
(Registrant's telephone number, including area code)
SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:
Class B Common Stock NKE New York Stock Exchange
(Title of each class) (Trading symbol) (Name of each exchange on which registered)
SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:
NONE
Indicate by check mark: YES NO
•if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨
•if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ
•whether the registrant (1) has filed all reports required to be filed by S ection 13 or 15(d) of the Securities
Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required
to file such reports), and (2) has been subject to such filing requirements for the past 90 days.þ ¨
•whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to
Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period
that the registrant was required to submit such files).þ ¨
•whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth
company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of
the Exchange Act.
Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐
•if an emerging growth company, if the registrant has elected not to use the extended transition period for
complying with any new or revised financial accounting standards provided pursuant to S ection 13(a) of the
Exchange Act.¨
•whether the registrant has filed a report on and attestation to its management's assessment of the ef fectiveness of
its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by
the registered public accounting firm that prepared or issued its audit report.þ
•if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant
included in the filing reflect the correction of an error to previously issued financial statements. ¨
•whether any of those error corrections are restatements that required a recovery analysis of incentive-based
compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to
§ 240.10D-1(b). ¨
•whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ
As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:
Class A $ 7,831,564,572
Class B 136,467,702,472
$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:
Class A  304,897,252
Class B  1,225,074,356
 1,529,971,608
DOCUMENTS INCORPORATED BY REFERENCE:
Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III
of this report.
"""

from langchain_community.document_loaders import PyPDFLoader

pyPDFLoader = PyPDFLoader("./nke-10k-2023.pdf")

documentList = pyPDFLoader.load_and_split()

for document in documentList[:3]:

print(document.page_content)

print()

"""

FORM 10-K FORM 10-K

UNITED STATES

SECURITIES AND EXCHANGE COMMISSION

Washington, D.C. 20549

FORM 10-K

(Mark One)

☑ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE FISCAL YEAR ENDED MAY 31, 2023

☐TRANSITION REPORT PURSUANT TO SECTION 13 OR 15(D) OF THE SECURITIES EXCHANGE ACT OF 1934

FOR THE TRANSITION PERIOD FROM TO .

Commission File No. 1-10635

NIKE, Inc.

(Exact name of Registrant as specified in its charter)

Oregon 93-0584541

(State or other jurisdiction of incorporation) (IRS Employer Identification No.)

One Bowerman Drive, Beaverton, Oregon 97005-6453

(Address of principal executive offices and zip code)

(503) 671-6453

(Registrant's telephone number, including area code)

SECURITIES REGISTERED PURSUANT TO SECTION 12(B) OF THE ACT:

Class B Common Stock NKE New York Stock Exchange

(Title of each class) (Trading symbol) (Name of each exchange on which registered)

SECURITIES REGISTERED PURSUANT TO SECTION 12(G) OF THE ACT:

NONE

Indicate by check mark: YES NO

•if the registrant is a well-known seasoned issuer, as defined in Rule 405 of the Securities Act. þ ¨

•if the registrant is not required to file reports pursuant to Section 13 or Section 15(d) of the Act. ¨ þ

•whether the registrant (1) has filed all reports required to be filed by S ection 13 or 15(d) of the Securities

Exchange Act of 1934 during the preceding 12 months (or for such shorter period that the registrant was required

to file such reports), and (2) has been subject to such filing requirements for the past 90 days.þ ¨

•whether the registrant has submitted electronically every Interactive Data File required to be submitted pursuant to

Rule 405 of Regulation S-T (§232.405 of this chapter) during the preceding 12 months (or for such shorter period

that the registrant was required to submit such files).þ ¨

•whether the registrant is a large accelerated filer, an accelerated filer, a non-accelerated filer, a smaller reporting company or an emerging growth

company. See the definitions of “large accelerated filer,” “accelerated filer,” “smaller reporting company,” and “emerging growth company” in Rule 12b-2 of

the Exchange Act.

Large accelerated filer þ Accelerated filer ☐ Non-accelerated filer ☐ Smaller reporting company ☐ Emerging growth company ☐

•if an emerging growth company, if the registrant has elected not to use the extended transition period for

complying with any new or revised financial accounting standards provided pursuant to S ection 13(a) of the

Exchange Act.¨

•whether the registrant has filed a report on and attestation to its management's assessment of the ef fectiveness of

its internal control over financial reporting under Section 404(b) of the Sarbanes-Oxley Act (15 U.S.C. 7262(b)) by

the registered public accounting firm that prepared or issued its audit report.þ

•if securities are registered pursuant to Section 12(b) of the Act, whether the financial statements of the registrant

included in the filing reflect the correction of an error to previously issued financial statements. ¨

•whether any of those error corrections are restatements that required a recovery analysis of incentive-based

compensation received by any of the registrant's executive officers during the relevant recovery period pursuant to

§ 240.10D-1(b). ¨

•whether the registrant is a shell company (as defined in Rule 12b-2 of the Act). ☐ þ

As of November 30, 2022, the aggregate market values of the Registrant's Common Stock held by non-affiliates were:

Class A $ 7,831,564,572

Class B 136,467,702,472

$ 144,299,267,044

As of July 12, 2023, the number of shares of the Registrant's Common Stock outstanding were:

Class A 304,897,252

Class B 1,225,074,356

1,529,971,608

DOCUMENTS INCORPORATED BY REFERENCE:

Parts of Registrant's Proxy Statement for the Annual Meeting of Shareholders to be held on September 12, 2023, are incorporated by reference into Part III

of this report.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
install==1.3.5
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
orjson==3.10.5
packaging==24.1
pydantic==2.7.4
pydantic_core==2.18.4
pypdf==4.2.0
PyYAML==6.0.1
requests==2.32.3
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

install==1.3.5

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

orjson==3.10.5

packaging==24.1

pydantic==2.7.4

pydantic_core==2.18.4

pypdf==4.2.0

PyYAML==6.0.1

requests==2.32.3

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install install

[PYTHON/LANGCHAIN] PyMuPDFLoader 클래스 : load 메소드를 사용해 PDF 파일 문서 로드하기

■ PyMuPDFLoader 클래스의 load 메소드를 사용해 PDF 파일 문서를 로드하는 방법을 보여준다. ※ PyPDFLoader 클래스와의 차이는 PyMuPDFLoader 클래스가 PDF 파일의 페이지 단위로

[PYTHON/COMMON] pymupdf 패키지 설치하기

■ pymupdf 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install pymupdf

pip install pymupdf

[PYTHON/LANGCHAIN] PyPDFLoader 클래스 : 생성자에서 extract_images 인자를 사용해 PDF 파일 문서 로드시 이미지 텍스트 추출하기

■ PyPDFLoader 클래스의 생성자에서 extract_images 인자를 사용해 PDF 파일 문서 로드시 이미지 텍스트를 추출하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import PyPDFLoader

pyPDFLoader = PyPDFLoader("./nke-10k-2023.pdf", extract_images = True)

documentList = pyPDFLoader.load_and_split()

for document in documentList[:3]:
    print(document.page_content)
    print()

from langchain_community.document_loaders import PyPDFLoader

pyPDFLoader = PyPDFLoader("./nke-10k-2023.pdf", extract_images = True)

documentList = pyPDFLoader.load_and_split()

for document in documentList[:3]:

print(document.page_content)

print()

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
coloredlogs==15.0.1
dataclasses-json==0.6.7
flatbuffers==24.3.25
frozenlist==1.4.1
greenlet==3.0.3
humanfriendly==10.0
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
onnxruntime==1.18.0
opencv-python==4.10.0.84
orjson==3.10.5
packaging==24.1
pillow==10.3.0
protobuf==5.27.2
pyclipper==1.3.0.post5
pydantic==2.7.4
pydantic_core==2.18.4
pypdf==4.2.0
PyYAML==6.0.1
rapidocr-onnxruntime==1.3.22
requests==2.32.3
shapely==2.0.4
six==1.16.0
SQLAlchemy==2.0.31
sympy==1.12.1
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

coloredlogs==15.0.1

dataclasses-json==0.6.7

flatbuffers==24.3.25

frozenlist==1.4.1

greenlet==3.0.3

humanfriendly==10.0

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

mpmath==1.3.0

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

onnxruntime==1.18.0

opencv-python==4.10.0.84

orjson==3.10.5

packaging==24.1

pillow==10.3.0

protobuf==5.27.2

pyclipper==1.3.0.post5

pydantic==2.7.4

pydantic_core==2.18.4

pypdf==4.2.0

PyYAML==6.0.1

rapidocr-onnxruntime==1.3.22

requests==2.32.3

shapely==2.0.4

six==1.16.0

SQLAlchemy==2.0.31

sympy==1.12.1

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

[PYTHON/COMMON] rapidocr-onnxruntime 패키지 설치하기

■ rapidocr-onnxruntime 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install rapidocr-onnxruntime

pip install rapidocr-onnxruntime

[PYTHON/LANGCHAIN] FAISS 클래스 : similarity_search 메소드를 사용해 문자열 쿼리 유사성 기반으로 문서 리스트 구하기

■ FAISS 클래스의 similarity_search 메소드를 사용해 문자열 쿼리 유사성 기반으로 문서 리스트를 구하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에

[PYTHON/LANGCHAIN] from_documents 함수 : 메모리 내 벡터 저장소를 위한 FAISS 객체 만들기

■ from_documents 함수를 사용해 메모리 내 벡터 저장소를 위한 FAISS 객체를 만드는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다.

[PYTHON/LANGCHAIN] UnstructuredMarkdownLoader 클래스 : 생성자에서 mode 인자를 사용해 특정 단위로 분리해 문서 로드하기

■ UnstructuredMarkdownLoader 클래스의 생성자에서 mode 인자를 사용해 특정 단위로 분리해 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import UnstructuredMarkdownLoader

unstructuredMarkdownLoader = UnstructuredMarkdownLoader("list.md", mode = "elements")

documentList = unstructuredMarkdownLoader.load()

for document in documentList:
    print(document)

"""
page_content='첫번째' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}
page_content='두번째' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}
page_content='세번째' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}
page_content='항목1\n\n항목 2\n항목 3\n항목 4' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}
"""

from langchain_community.document_loaders import UnstructuredMarkdownLoader

unstructuredMarkdownLoader = UnstructuredMarkdownLoader("list.md", mode = "elements")

documentList = unstructuredMarkdownLoader.load()

for document in documentList:

print(document)

"""

page_content='첫번째' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}

page_content='두번째' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}

page_content='세번째' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}

page_content='항목1\n\n항목 2\n항목 3\n항목 4' metadata={'source': 'list.md', 'category_depth': 1, 'last_modified': '2024-06-27T19:30:15', 'languages': ['kor'], 'filetype': 'text/markdown', 'filename': 'list.md', 'category': 'ListItem'}

"""

▶ 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
backoff==2.2.1
beautifulsoup4==4.12.3
certifi==2024.6.2
chardet==5.2.0
charset-normalizer==3.3.2
click==8.1.7
dataclasses-json==0.6.7
deepdiff==7.0.1
emoji==2.12.1
exceptiongroup==1.2.1
filetype==1.2.0
frozenlist==1.4.1
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
joblib==1.4.2
jsonpatch==1.33
jsonpath-python==1.0.6
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langdetect==1.0.9
langsmith==0.1.82
lxml==5.2.2
Markdown==3.6
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
nest-asyncio==1.6.0
nltk==3.8.1
numpy==1.26.4
ordered-set==4.1.0
orjson==3.10.5
packaging==24.1
pydantic==2.7.4
pydantic_core==2.18.4
pypdf==4.2.0
python-dateutil==2.9.0.post0
python-iso639==2024.4.27
python-magic==0.4.27
PyYAML==6.0.1
rapidfuzz==3.9.3
regex==2024.5.15
requests==2.32.3
requests-toolbelt==1.0.0
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.31
tabulate==0.9.0
tenacity==8.4.2
tqdm==4.66.4
typing-inspect==0.9.0
typing_extensions==4.12.2
unstructured==0.14.8
unstructured-client==0.23.7
urllib3==2.2.2
wrapt==1.16.0
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

backoff==2.2.1

beautifulsoup4==4.12.3

certifi==2024.6.2

chardet==5.2.0

charset-normalizer==3.3.2

click==8.1.7

dataclasses-json==0.6.7

deepdiff==7.0.1

emoji==2.12.1

exceptiongroup==1.2.1

filetype==1.2.0

frozenlist==1.4.1

greenlet==3.0.3

h11==0.14.0

httpcore==1.0.5

httpx==0.27.0

idna==3.7

joblib==1.4.2

jsonpatch==1.33

jsonpath-python==1.0.6

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langdetect==1.0.9

langsmith==0.1.82

lxml==5.2.2

Markdown==3.6

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

nest-asyncio==1.6.0

nltk==3.8.1

numpy==1.26.4

ordered-set==4.1.0

orjson==3.10.5

packaging==24.1

pydantic==2.7.4

pydantic_core==2.18.4

pypdf==4.2.0

python-dateutil==2.9.0.post0

python-iso639==2024.4.27

python-magic==0.4.27

PyYAML==6.0.1

rapidfuzz==3.9.3

regex==2024.5.15

requests==2.32.3

requests-toolbelt==1.0.0

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.31

tabulate==0.9.0

tenacity==8.4.2

tqdm==4.66.4

typing-inspect==0.9.0

typing_extensions==4.12.2

unstructured==0.14.8

unstructured-client==0.23.7

urllib3==2.2.2

wrapt==1.16.0

yarl==1.9.4

※ pip

[PYTHON/LANGCHAIN] UnstructuredMarkdownLoader 클래스 : load 메소드를 사용해 MD 파일 문서 로드하기

■ UnstructuredMarkdownLoader 클래스의 load 메소드를 사용해 MD 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import UnstructuredMarkdownLoader

unstructuredMarkdownLoader = UnstructuredMarkdownLoader("list.md")

documentList = unstructuredMarkdownLoader.load()

for document in documentList:
    print(document)

"""
page_content='첫번째\n\n두번째\n\n세번째\n\n항목1\n\n항목 2\n항목 3\n항목 4' metadata={'source': 'list.md'}
"""

from langchain_community.document_loaders import UnstructuredMarkdownLoader

unstructuredMarkdownLoader = UnstructuredMarkdownLoader("list.md")

documentList = unstructuredMarkdownLoader.load()

for document in documentList:

print(document)

"""

page_content='첫번째\n\n두번째\n\n세번째\n\n항목1\n\n항목 2\n항목 3\n항목 4' metadata={'source': 'list.md'}

"""

▶ 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
backoff==2.2.1
beautifulsoup4==4.12.3
certifi==2024.6.2
chardet==5.2.0
charset-normalizer==3.3.2
click==8.1.7
dataclasses-json==0.6.7
deepdiff==7.0.1
emoji==2.12.1
exceptiongroup==1.2.1
filetype==1.2.0
frozenlist==1.4.1
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
joblib==1.4.2
jsonpatch==1.33
jsonpath-python==1.0.6
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langdetect==1.0.9
langsmith==0.1.82
lxml==5.2.2
Markdown==3.6
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
nest-asyncio==1.6.0
nltk==3.8.1
numpy==1.26.4
ordered-set==4.1.0
orjson==3.10.5
packaging==24.1
pydantic==2.7.4
pydantic_core==2.18.4
pypdf==4.2.0
python-dateutil==2.9.0.post0
python-iso639==2024.4.27
python-magic==0.4.27
PyYAML==6.0.1
rapidfuzz==3.9.3
regex==2024.5.15
requests==2.32.3
requests-toolbelt==1.0.0
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.31
tabulate==0.9.0
tenacity==8.4.2
tqdm==4.66.4
typing-inspect==0.9.0
typing_extensions==4.12.2
unstructured==0.14.8
unstructured-client==0.23.7
urllib3==2.2.2
wrapt==1.16.0
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

backoff==2.2.1

beautifulsoup4==4.12.3

certifi==2024.6.2

chardet==5.2.0

charset-normalizer==3.3.2

click==8.1.7

dataclasses-json==0.6.7

deepdiff==7.0.1

emoji==2.12.1

exceptiongroup==1.2.1

filetype==1.2.0

frozenlist==1.4.1

greenlet==3.0.3

h11==0.14.0

httpcore==1.0.5

httpx==0.27.0

idna==3.7

joblib==1.4.2

jsonpatch==1.33

jsonpath-python==1.0.6

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langdetect==1.0.9

langsmith==0.1.82

lxml==5.2.2

Markdown==3.6

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

nest-asyncio==1.6.0

nltk==3.8.1

numpy==1.26.4

ordered-set==4.1.0

orjson==3.10.5

packaging==24.1

pydantic==2.7.4

pydantic_core==2.18.4

pypdf==4.2.0

python-dateutil==2.9.0.post0

python-iso639==2024.4.27

python-magic==0.4.27

PyYAML==6.0.1

rapidfuzz==3.9.3

regex==2024.5.15

requests==2.32.3

requests-toolbelt==1.0.0

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.31

tabulate==0.9.0

tenacity==8.4.2

tqdm==4.66.4

typing-inspect==0.9.0

typing_extensions==4.12.2

unstructured==0.14.8

unstructured-client==0.23.7

urllib3==2.2.2

wrapt==1.16.0

yarl==1.9.4

※ pip langchain-community unstructured[md]

[PYTHON/LANGCHAIN] JSONLoader 클래스 : 생성자에서 metadata_func 인자를 사용해 메타 데이터 항목 추가하기

■ JSONLoader 클래스의 생성자에서 metadata_func 인자를 사용해 메타 데이터 항목을 추가하는 방법을 보여준다. ▶ main.py


from datetime import datetime
from pprint   import pprint

from langchain_community.document_loaders import JSONLoader

def manipulateMetadata(recordDictionary : dict, metadataDictionary : dict) -> dict:
    metadataDictionary["left"] = recordDictionary["MainFormLeft"]
    metadataDictionary["time"] = datetime.now().isoformat()

    return metadataDictionary

jsonLoader = JSONLoader(
    file_path     = "./settings.json",
    jq_schema     = ".",
    text_content  = False,
    metadata_func = manipulateMetadata
)

documentList = jsonLoader.load()

for document in documentList[:5]:
    pprint(document.metadata)
    print()

"""
{'left': 0,
 'seq_num': 1,
 'source': '/home/king/testproject/settings.json',
 'time': '2024-06-27T22:35:30.360160'}
"""

from datetime import datetime

from pprint import pprint

from langchain_community.document_loaders import JSONLoader

def manipulateMetadata(recordDictionary : dict, metadataDictionary : dict) -> dict:

metadataDictionary["left"] = recordDictionary["MainFormLeft"]

metadataDictionary["time"] = datetime.now().isoformat()

return metadataDictionary

jsonLoader = JSONLoader(

file_path = "./settings.json",

jq_schema = ".",

text_content = False,

metadata_func = manipulateMetadata

)

documentList = jsonLoader.load()

for document in documentList[:5]:

pprint(document.metadata)

print()

"""

{'left': 0,

'seq_num': 1,

'source': '/home/king/testproject/settings.json',

'time': '2024-06-27T22:35:30.360160'}

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jq==1.7.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
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
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jq==1.7.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

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

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install

[PYTHON/LANGCHAIN] JSONLoader 클래스 : 생성자에서 jq_schema/content_key 인자 사용하기

■ JSONLoader 클래스의 생성자에서 jq_schema/content_key 인자를 사용하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import JSONLoader

jsonLoader = JSONLoader(
    file_path    = "./sample.jsonl",
    jq_schema    = ".",
    content_key  = "prompt",
    text_content = False,
    json_lines   = True
)

documentList = jsonLoader.load()

for document in documentList[:5]:
    print(document)
    print()

"""
page_content='배가 고프다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 1}

page_content='피곤하시군요.' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 2}

page_content='잠을 잘 수 없다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 3}

page_content='누르지 마 절대 누르지 마' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 4}

page_content='보여줄 수 없어' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 5}
"""

from langchain_community.document_loaders import JSONLoader

jsonLoader = JSONLoader(

file_path = "./sample.jsonl",

jq_schema = ".",

content_key = "prompt",

text_content = False,

json_lines = True

)

documentList = jsonLoader.load()

for document in documentList[:5]:

print(document)

print()

"""

page_content='배가 고프다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 1}

page_content='피곤하시군요.' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 2}

page_content='잠을 잘 수 없다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 3}

page_content='누르지 마 절대 누르지 마' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 4}

page_content='보여줄 수 없어' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 5}

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jq==1.7.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
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
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jq==1.7.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

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

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community jq 명령을 실행했다.

[PYTHON/LANGCHAIN] JsonLoader 클래스 : load 메소드를 사용해 JSONL 파일 문서 로드하기

■ JsonLoader 클래스의 load 메소드를 사용해 JSONL 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import JSONLoader

jsonLoader = JSONLoader(
    file_path    = "./sample.jsonl",
    jq_schema    = ".prompt",
    text_content = False,
    json_lines   = True
)

documentList = jsonLoader.load()

for document in documentList[:5]:
    print(document)
    print()

"""
page_content='배가 고프다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 1}

page_content='피곤하시군요.' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 2}

page_content='잠을 잘 수 없다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 3}

page_content='누르지 마 절대 누르지 마' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 4}

page_content='보여줄 수 없어' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 5}
"""

from langchain_community.document_loaders import JSONLoader

jsonLoader = JSONLoader(

file_path = "./sample.jsonl",

jq_schema = ".prompt",

text_content = False,

json_lines = True

)

documentList = jsonLoader.load()

for document in documentList[:5]:

print(document)

print()

"""

page_content='배가 고프다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 1}

page_content='피곤하시군요.' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 2}

page_content='잠을 잘 수 없다' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 3}

page_content='누르지 마 절대 누르지 마' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 4}

page_content='보여줄 수 없어' metadata={'source': '/home/king/testproject/sample.jsonl', 'seq_num': 5}

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jq==1.7.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
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
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jq==1.7.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

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

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community

[PYTHON/LANGCHAIN] JsonLoader 클래스 : load 메소드를 사용해 JSON 파일 문서 로드하기

■ JsonLoader 클래스의 load 메소드를 사용해 JSON 파일 문서를 로드하는 방법을 보여준다. ▶ main.py


from langchain_community.document_loaders import JSONLoader

jsonLoader = JSONLoader(
    file_path    = "./settings.json",
    jq_schema    = ".",
    text_content = False
)

documentList = jsonLoader.load()

for document in documentList:
    print(document)
    print()

"""
page_content='{"MainFormLeft": 0, "MainFormTop": 0, "MainFormWidth": 920, "MainFormHeight": 690, "MainFormState": "Maximized", "SkinStyle": "Office 2016 Colorful", "RibbonMinimized": true, "SidebarStyle": "NavigationPane", "SidebarWidth": 100, "SidebarCollapsable": true, "SidebarVisible": true}' metadata={'source': '/home/king/testproject/settings.json', 'seq_num': 1}
"""

from langchain_community.document_loaders import JSONLoader

jsonLoader = JSONLoader(

file_path = "./settings.json",

jq_schema = ".",

text_content = False

)

documentList = jsonLoader.load()

for document in documentList:

print(document)

print()

"""

page_content='{"MainFormLeft": 0, "MainFormTop": 0, "MainFormWidth": 920, "MainFormHeight": 690, "MainFormState": "Maximized", "SkinStyle": "Office 2016 Colorful", "RibbonMinimized": true, "SidebarStyle": "NavigationPane", "SidebarWidth": 100, "SidebarCollapsable": true, "SidebarVisible": true}' metadata={'source': '/home/king/testproject/settings.json', 'seq_num': 1}

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
frozenlist==1.4.1
greenlet==3.0.3
idna==3.7
jq==1.7.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.6
langchain-community==0.2.6
langchain-core==0.2.10
langchain-text-splitters==0.2.2
langsmith==0.1.82
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
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
SQLAlchemy==2.0.31
tenacity==8.4.2
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

frozenlist==1.4.1

greenlet==3.0.3

idna==3.7

jq==1.7.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.6

langchain-community==0.2.6

langchain-core==0.2.10

langchain-text-splitters==0.2.2

langsmith==0.1.82

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

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

SQLAlchemy==2.0.31

tenacity==8.4.2

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

※ pip install langchain-community

[PYTHON/COMMON] 카라츠바(Karatsuba) 알고리즘을 사용해 큰 수 곱하기

■ 카라츠바(Karatsuba) 알고리즘을 사용해 큰 수를 곱하는 방법을 보여준다. ▶ 예제 코드 (PY)


def multiplyWthKaratsubaAlgorithm(x, y):
    xString = str(x)
    yString = str(y)

    maximumLength = max(len(xString), len(yString))

    if maximumLength == 1:
        return x * y

    middleIndex = maximumLength // 2

    if middleIndex == 1:
        return x * y

    firstX = int(xString[:-middleIndex])
    lastX  = int(xString[-middleIndex:])
    firstY = int(yString[:-middleIndex])
    lastY  = int(yString[-middleIndex:])

    firstXY = multiplyWthKaratsubaAlgorithm(firstX, firstY)
    lastXY  = multiplyWthKaratsubaAlgorithm(lastX, lastY)
    xy      = multiplyWthKaratsubaAlgorithm((firstX + lastX), (firstY + lastY)) - firstXY - lastXY

    targetValue = firstXY * 10 ** (2 * middleIndex) + xy * 10 ** middleIndex + lastXY

    return targetValue

x = 123456789012345678901234567890
y = 987654321098765432109876543210

targetValue = multiplyWthKaratsubaAlgorithm(x, y)

print(targetValue)

"""
121932631137021795226185032733622923332237463801111263526900
"""

def multiplyWthKaratsubaAlgorithm(x, y):

xString = str(x)

yString = str(y)

maximumLength = max(len(xString), len(yString))

if maximumLength == 1:

return x * y

middleIndex = maximumLength // 2

if middleIndex == 1:

return x * y

firstX = int(xString[:-middleIndex])

lastX = int(xString[-middleIndex:])

firstY = int(yString[:-middleIndex])

lastY = int(yString[-middleIndex:])

firstXY = multiplyWthKaratsubaAlgorithm(firstX, firstY)

lastXY = multiplyWthKaratsubaAlgorithm(lastX, lastY)

xy = multiplyWthKaratsubaAlgorithm((firstX + lastX), (firstY + lastY)) - firstXY - lastXY

targetValue = firstXY * 10 ** (2 * middleIndex) + xy * 10 ** middleIndex + lastXY

return targetValue

x = 123456789012345678901234567890

y = 987654321098765432109876543210

targetValue = multiplyWthKaratsubaAlgorithm(x, y)

print(targetValue)

"""

121932631137021795226185032733622923332237463801111263526900

"""