PDF Archives - icodebroker

[PYTHON/PYPDF] PDF 파일 분할하기

■ PDF 파일을 분할하는 방법을 보여준다. ▶ main.py


import os

from PyPDF2 import PdfReader
from PyPDF2 import PdfWriter

def splitPDFFile(sourceFilePath, targetDirectoryPath, pageCountPerFile):
    pdfReader      = PdfReader(sourceFilePath)
    totalPageCount = len(pdfReader.pages)
    if not os.path.exists(targetDirectoryPath):
        os.makedirs(targetDirectoryPath)
    fileNameWithoutExtension = os.path.splitext(os.path.basename(sourceFilePath))[0]
    for i in range(0, totalPageCount, pageCountPerFile):
        pdfWriter = PdfWriter()
        for page in range(i, min(i + pageCountPerFile, totalPageCount)):
            pdfWriter.add_page(pdfReader.pages[page])
        targetFileName = f"{fileNameWithoutExtension}_part_{i//pageCountPerFile + 1}.pdf"
        targetFilePath = os.path.join(targetDirectoryPath, targetFileName)
        with open(targetFilePath, "wb") as bufferedWriter:
            pdfWriter.write(bufferedWriter)
        print(f"Created : {targetFileName}")
    print("PDF splitting completed.")

sourceFilePath      = "d:\\Practical C# Charts and Graphics.pdf"
targetDirectoryPath = "d:\\Practical C# Charts and Graphics"
pageCountPerFile    = 100

splitPDFFile(sourceFilePath, targetDirectoryPath, pageCountPerFile)

import os

from PyPDF2 import PdfReader

from PyPDF2 import PdfWriter

def splitPDFFile(sourceFilePath, targetDirectoryPath, pageCountPerFile):

pdfReader = PdfReader(sourceFilePath)

totalPageCount = len(pdfReader.pages)

if not os.path.exists(targetDirectoryPath):

os.makedirs(targetDirectoryPath)

fileNameWithoutExtension = os.path.splitext(os.path.basename(sourceFilePath))[0]

for i in range(0, totalPageCount, pageCountPerFile):

pdfWriter = PdfWriter()

for page in range(i, min(i + pageCountPerFile, totalPageCount)):

pdfWriter.add_page(pdfReader.pages[page])

targetFileName = f"{fileNameWithoutExtension}_part_{i//pageCountPerFile + 1}.pdf"

targetFilePath = os.path.join(targetDirectoryPath, targetFileName)

with open(targetFilePath, "wb") as bufferedWriter:

pdfWriter.write(bufferedWriter)

print(f"Created : {targetFileName}")

print("PDF splitting completed.")

sourceFilePath = "d:\\Practical C# Charts and Graphics.pdf"

targetDirectoryPath = "d:\\Practical C# Charts and Graphics"

pageCountPerFile = 100

splitPDFFile(sourceFilePath, targetDirectoryPath, pageCountPerFile)

▶ requirements.txt


PyPDF2==3.0.1

PyPDF2==3.0.1

※ pip install pypdf2 명령을 실행했다.

[PYTHON/PYPDF] pypdf2 패키지 설치하기

■ pypdf2 패키지를 설치하는 방법을 보여준다. 1. 명령 프롬프트를 실행한다. 2. 명령 프롬프트에서 아래 명령을 실행한다. ▶ 실행 명령


pip install pypdf2

pip install pypdf2

[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/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/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/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] OPENAI 모델을 사용해 PDF 문서 로드 및 질문/응답 애플리케이션 만들기

■ OPENAI 모델을 사용해 PDF 문서 로드 및 질의 응답 애플리케이션을 만드는 방법을 보여준다. ▶ main.py


import os

from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters             import RecursiveCharacterTextSplitter
from langchain_openai                     import OpenAIEmbeddings
from langchain_chroma                     import Chroma
from langchain_openai                     import ChatOpenAI
from langchain_core.prompts               import ChatPromptTemplate
from langchain.chains.combine_documents   import create_stuff_documents_chain
from langchain.chains                     import create_retrieval_chain

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

# PDF 문서를 로드한다.
filePath = "./nke-10k-2023.pdf"

pyPDFLoader = PyPDFLoader(filePath)

documentList = pyPDFLoader.load()

# 문서를 분할한다.
recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

# 벡터 저장소를 설정한다.
chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings())

# 벡터 저장소 검색기를 설정한다.
vectorStoreRetriever = chroma.as_retriever()

# LLM 모델을 설정한다.
chatOpenAI = ChatOpenAI(model = "gpt-4o")

# 채팅 프롬프트 템플리트를 설정한다.
systemMessage = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer "
    "the question. If you don't know the answer, say that you "
    "don't know. Use three sentences maximum and keep the "
    "answer concise."
    "\n\n"
    "{context}"
)

chatPromptTemplate = ChatPromptTemplate.from_messages(
    [
        ("system", systemMessage),
        ("human" , "{input}"),
    ]
)

# 질의 응답 체인을 설정한다.
qnaRunnableSequence = create_stuff_documents_chain(chatOpenAI, chatPromptTemplate)

# RAG 체인을 설정한다.
ragRunnableSequence = create_retrieval_chain(vectorStoreRetriever, qnaRunnableSequence)

# 질의 응답을 실행한다.
resultDictionary = ragRunnableSequence.invoke({"input" : "What was Nike's revenue in 2023?"})

print(resultDictionary["context"][0].page_content)

"""
FISCAL 2023 NIKE BRAND REVENUE HIGHLIGHTS
The following tables present NIKE Brand revenues disaggregated by reportable operating segment, distribution channel and
major product line:
FISCAL 2023 COMPARED TO FISCAL 2022
•NIKE, Inc. Revenues were $51.2 billion in fiscal 2023, which increased 10% and 16% compared to fiscal 2022 on a reported
and currency-neutral basis, respectively. The increase was due to higher revenues in North America, Europe, Middle East &
Africa ("EMEA"), APLA and Greater China, which contributed approximately 7, 6, 2 and 1 percentage points to NIKE, Inc.
Revenues, respectively.
•NIKE Brand revenues, which represented over 90% of NIKE, Inc. Revenues,  increased  10% and 16% on a reported and
currency-neutral basis, respectively. This increase was primarily due to higher revenues in Men's, the Jordan Brand,
Women's and Kids' which grew 17%, 35%,11% and 10%, respectively, on a wholesale equivalent basis.
"""

import os

from langchain_community.document_loaders import PyPDFLoader

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_openai import OpenAIEmbeddings

from langchain_chroma import Chroma

from langchain_openai import ChatOpenAI

from langchain_core.prompts import ChatPromptTemplate

from langchain.chains.combine_documents import create_stuff_documents_chain

from langchain.chains import create_retrieval_chain

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

# PDF 문서를 로드한다.

filePath = "./nke-10k-2023.pdf"

pyPDFLoader = PyPDFLoader(filePath)

documentList = pyPDFLoader.load()

# 문서를 분할한다.

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

# 벡터 저장소를 설정한다.

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings())

# 벡터 저장소 검색기를 설정한다.

vectorStoreRetriever = chroma.as_retriever()

# LLM 모델을 설정한다.

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

# 채팅 프롬프트 템플리트를 설정한다.

systemMessage = (

"You are an assistant for question-answering tasks. "

"Use the following pieces of retrieved context to answer "

"the question. If you don't know the answer, say that you "

"don't know. Use three sentences maximum and keep the "

"answer concise."

"\n\n"

"{context}"

)

chatPromptTemplate = ChatPromptTemplate.from_messages(

[

("system", systemMessage),

("human" , "{input}"),

]

)

# 질의 응답 체인을 설정한다.

qnaRunnableSequence = create_stuff_documents_chain(chatOpenAI, chatPromptTemplate)

# RAG 체인을 설정한다.

ragRunnableSequence = create_retrieval_chain(vectorStoreRetriever, qnaRunnableSequence)

# 질의 응답을 실행한다.

resultDictionary = ragRunnableSequence.invoke({"input" : "What was Nike's revenue in 2023?"})

print(resultDictionary["context"][0].page_content)

"""

FISCAL 2023 NIKE BRAND REVENUE HIGHLIGHTS

The following tables present NIKE Brand revenues disaggregated by reportable operating segment, distribution channel and

major product line:

FISCAL 2023 COMPARED TO FISCAL 2022

•NIKE, Inc. Revenues were $51.2 billion in fiscal 2023, which increased 10% and 16% compared to fiscal 2022 on a reported

and currency-neutral basis, respectively. The increase was due to higher revenues in North America, Europe, Middle East &

Africa ("EMEA"), APLA and Greater China, which contributed approximately 7, 6, 2 and 1 percentage points to NIKE, Inc.

Revenues, respectively.

•NIKE Brand revenues, which represented over 90% of NIKE, Inc. Revenues, increased 10% and 16% on a reported and

currency-neutral basis, respectively. This increase was primarily due to higher revenues in Men's, the Jordan Brand,

Women's and Kids' which grew 17%, 35%,11% and 10%, respectively, on a wholesale equivalent basis.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
asgiref==3.8.1
async-timeout==4.0.3
attrs==23.2.0
backoff==2.2.1
bcrypt==4.1.3
build==1.2.1
cachetools==5.3.3
certifi==2024.6.2
charset-normalizer==3.3.2
chroma-hnswlib==0.7.3
chromadb==0.5.0
click==8.1.7
coloredlogs==15.0.1
dataclasses-json==0.6.7
Deprecated==1.2.14
distro==1.9.0
dnspython==2.6.1
email_validator==2.1.1
exceptiongroup==1.2.1
fastapi==0.111.0
fastapi-cli==0.0.4
filelock==3.15.1
flatbuffers==24.3.25
frozenlist==1.4.1
fsspec==2024.6.0
google-auth==2.30.0
googleapis-common-protos==1.63.1
greenlet==3.0.3
grpcio==1.64.1
h11==0.14.0
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.0
huggingface-hub==0.23.3
humanfriendly==10.0
idna==3.7
importlib_metadata==7.1.0
importlib_resources==6.4.0
Jinja2==3.1.4
jsonpatch==1.33
jsonpointer==3.0.0
kubernetes==30.1.0
langchain==0.2.4
langchain-chroma==0.1.1
langchain-community==0.2.4
langchain-core==0.2.6
langchain-openai==0.1.8
langchain-text-splitters==0.2.1
langsmith==0.1.77
markdown-it-py==3.0.0
MarkupSafe==2.1.5
marshmallow==3.21.3
mdurl==0.1.2
mmh3==4.1.0
monotonic==1.6
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
oauthlib==3.2.2
onnxruntime==1.18.0
openai==1.34.0
opentelemetry-api==1.25.0
opentelemetry-exporter-otlp-proto-common==1.25.0
opentelemetry-exporter-otlp-proto-grpc==1.25.0
opentelemetry-instrumentation==0.46b0
opentelemetry-instrumentation-asgi==0.46b0
opentelemetry-instrumentation-fastapi==0.46b0
opentelemetry-proto==1.25.0
opentelemetry-sdk==1.25.0
opentelemetry-semantic-conventions==0.46b0
opentelemetry-util-http==0.46b0
orjson==3.10.5
overrides==7.7.0
packaging==24.1
posthog==3.5.0
protobuf==4.25.3
pyasn1==0.6.0
pyasn1_modules==0.4.0
pydantic==2.7.4
pydantic_core==2.18.4
Pygments==2.18.0
pypdf==4.2.0
PyPika==0.48.9
pyproject_hooks==1.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-multipart==0.0.9
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
requests-oauthlib==2.0.0
rich==13.7.1
rsa==4.9
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
SQLAlchemy==2.0.30
starlette==0.37.2
sympy==1.12.1
tenacity==8.3.0
tiktoken==0.7.0
tokenizers==0.19.1
tomli==2.0.1
tqdm==4.66.4
typer==0.12.3
typing-inspect==0.9.0
typing_extensions==4.12.2
ujson==5.10.0
urllib3==2.2.1
uvicorn==0.30.1
uvloop==0.19.0
watchfiles==0.22.0
websocket-client==1.8.0
websockets==12.0
wrapt==1.16.0
yarl==1.9.4
zipp==3.19.2

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

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

asgiref==3.8.1

async-timeout==4.0.3

attrs==23.2.0

backoff==2.2.1

bcrypt==4.1.3

build==1.2.1

cachetools==5.3.3

certifi==2024.6.2

charset-normalizer==3.3.2

chroma-hnswlib==0.7.3

chromadb==0.5.0

click==8.1.7

coloredlogs==15.0.1

dataclasses-json==0.6.7

Deprecated==1.2.14

distro==1.9.0

dnspython==2.6.1

email_validator==2.1.1

exceptiongroup==1.2.1

fastapi==0.111.0

fastapi-cli==0.0.4

filelock==3.15.1

flatbuffers==24.3.25

frozenlist==1.4.1

fsspec==2024.6.0

google-auth==2.30.0

googleapis-common-protos==1.63.1

greenlet==3.0.3

grpcio==1.64.1

h11==0.14.0

httpcore==1.0.5

httptools==0.6.1

httpx==0.27.0

huggingface-hub==0.23.3

humanfriendly==10.0

idna==3.7

importlib_metadata==7.1.0

importlib_resources==6.4.0

Jinja2==3.1.4

jsonpatch==1.33

jsonpointer==3.0.0

kubernetes==30.1.0

langchain==0.2.4

langchain-chroma==0.1.1

langchain-community==0.2.4

langchain-core==0.2.6

langchain-openai==0.1.8

langchain-text-splitters==0.2.1

langsmith==0.1.77

markdown-it-py==3.0.0

MarkupSafe==2.1.5

marshmallow==3.21.3

mdurl==0.1.2

mmh3==4.1.0

monotonic==1.6

mpmath==1.3.0

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

oauthlib==3.2.2

onnxruntime==1.18.0

openai==1.34.0

opentelemetry-api==1.25.0

opentelemetry-exporter-otlp-proto-common==1.25.0

opentelemetry-exporter-otlp-proto-grpc==1.25.0

opentelemetry-instrumentation==0.46b0

opentelemetry-instrumentation-asgi==0.46b0

opentelemetry-instrumentation-fastapi==0.46b0

opentelemetry-proto==1.25.0

opentelemetry-sdk==1.25.0

opentelemetry-semantic-conventions==0.46b0

opentelemetry-util-http==0.46b0

orjson==3.10.5

overrides==7.7.0

packaging==24.1

posthog==3.5.0

protobuf==4.25.3

pyasn1==0.6.0

pyasn1_modules==0.4.0

pydantic==2.7.4

pydantic_core==2.18.4

Pygments==2.18.0

pypdf==4.2.0

PyPika==0.48.9

pyproject_hooks==1.1.0

python-dateutil==2.9.0.post0

python-dotenv==1.0.1

python-multipart==0.0.9

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

requests-oauthlib==2.0.0

rich==13.7.1

rsa==4.9

shellingham==1.5.4

six==1.16.0

sniffio==1.3.1

SQLAlchemy==2.0.30

starlette==0.37.2

sympy==1.12.1

tenacity==8.3.0

tiktoken==0.7.0

tokenizers==0.19.1

tomli==2.0.1

tqdm==4.66.4

typer==0.12.3

typing-inspect==0.9.0

typing_extensions==4.12.2

ujson==5.10.0

urllib3==2.2.1

uvicorn==0.30.1

uvloop==0.19.0

watchfiles==0.22.0

websocket-client==1.8.0

websockets==12.0

wrapt==1.16.0

yarl==1.9.4

zipp==3.19.2

※ pip

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

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


from langchain_community.document_loaders import PyPDFLoader

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

documentList = pyPDFLoader.load()

print("문서 길이   :", len(documentList))

document = documentList[0]

print("첫번째 문서 :")
print("    페이지 컨텐츠 :", document.page_content)
print("    메타 데이터   :", document.metadata)

"""
문서 길이   : 106
첫번째 문서 :
    페이지 컨텐츠 : FORM 10-K FORM 10-K
    메타 데이터   : {'source': 'nke-10k-2023.pdf', 'page': 0}
"""

from langchain_community.document_loaders import PyPDFLoader

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

documentList = pyPDFLoader.load()

print("문서 길이 :", len(documentList))

document = documentList[0]

print("첫번째 문서 :")

print(" 페이지 컨텐츠 :", document.page_content)

print(" 메타 데이터 :", document.metadata)

"""

문서 길이 : 106

첫번째 문서 :

페이지 컨텐츠 : FORM 10-K FORM 10-K

메타 데이터 : {'source': 'nke-10k-2023.pdf', 'page': 0}

"""

▶ 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==0.2.4
langchain-community==0.2.4
langchain-core==0.2.6
langchain-text-splitters==0.2.1
langsmith==0.1.77
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==2.0.30
tenacity==8.3.0
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.1
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

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==0.2.4

langchain-community==0.2.4

langchain-core==0.2.6

langchain-text-splitters==0.2.1

langsmith==0.1.77

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==2.0.30

tenacity==8.3.0

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.1

yarl==1.9.4

※ pip install pypdf langchain_community

[PYTHON/PYPDF] pypdf 패키지 설치하기

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


pip install pypdf

pip install pypdf

[C#/COMMON] PdfSharp 누겟 설치하기

■ PdfSharp 누겟을 설치하는 방법을 보여준다. 1. Visual Studio를 실행한다. 2. [도구] / [NuGet 패키지 관리자] / [패키지 관리자 콘솔] 메뉴를 실행한다.

[POWERSHELL] Out-Printer 명령 : -Name 스위치를 사용해 PDF 파일 생성하기

■ Out-Printer 명령에서 -Name 스위치를 사용해 PDF 파일을 생성하는 방법을 보여준다. ▶ 실행 명령


"Hello PowerShell" | Out-Printer -Name "\\kingdom\Microsoft Print to PDF"

"Hello PowerShell" | Out-Printer -Name "\\kingdom\Microsoft Print to PDF"

[C#/WINFORM/DEVEXPRESS] GridView 클래스 : ExportToPdf 메소드를 사용해 PDF 파일 내보내기

■ GridView 클래스의 ExportToPdf 메소드를 사용해 PDF 파일을 내보내는 방법을 보여준다. ▶ MainForm.cs


using System;
using System.Collections.Generic;
using System.Data.OleDb;
using System.Diagnostics;

using DevExpress.Utils;
using DevExpress.XtraEditors;
using DevExpress.XtraGrid.Views.Grid;

namespace TestProject
{
    /// <summary>
    /// 메인 폼
    /// </summary>
    public partial class MainForm : XtraForm
    {
        //////////////////////////////////////////////////////////////////////////////////////////////////// Field
        ////////////////////////////////////////////////////////////////////////////////////////// Private

        #region Field

        /// <summary>
        /// 연결
        /// </summary>
        private OleDbConnection connection;

        /// <summary>
        /// 소스 리스트
        /// </summary>
        private List<OrderDetail> sourceList;

        #endregion

        //////////////////////////////////////////////////////////////////////////////////////////////////// Constructor
        ////////////////////////////////////////////////////////////////////////////////////////// Public

        #region 생성자 - MainForm()

        /// <summary>
        /// 생성자
        /// </summary>
        public MainForm()
        {
            InitializeComponent();

            this.connection = new OleDbConnection("Provider=Microsoft.Jet.OLEDB.4.0;Data Source=nwind.mdb");

            this.gridView.InitializeView
            (
                true,                           // Multi Select
                GridMultiSelectMode.CellSelect, // Grid Multi Select Mode
                DrawFocusRectStyle.CellFocus,   // Draw Focus Rect Style
                true,                           // Show Indicator
                true,                           // Show Column Headers
                true,                           // Allow Column Moving
                true,                           // Allow Column Resizing
                true,                           // Allow Filter
                true,                           // Allow Sort
                false,                          // Allow Cell Merge
                EditorShowMode.Default,         // Editor Show Mode
                false                           // Editable
            );

            this.gridView.OptionsBehavior.AutoPopulateColumns = true;

            this.sourceList = OrderDetail.GetOrderDetailList(this.connection);

            this.gridControl.DataSource = this.sourceList;

            this.gridView.BestFitColumns();

            this.exportButton.Click += exportButton_Click;
        }

        #endregion

        //////////////////////////////////////////////////////////////////////////////////////////////////// Method
        ////////////////////////////////////////////////////////////////////////////////////////// Private

        #region PDF 파일 내보내기 버튼 클릭시 처리하기 - previewButton_Click(sender, e)

        /// <summary>
        /// PDF 파일 내보내기 버튼 클릭시 처리하기
        /// </summary>
        /// <param name="sender">이벤트 발생자</param>
        /// <param name="e">이벤트 인자</param>
        private void exportButton_Click(object sender, EventArgs e)
        {
            this.gridView.OptionsPrint.ExpandAllDetails = true;

            this.gridView.ExportToPdf("d:\\sample.pdf");

            Process.Start("d:\\sample.pdf");
        }

        #endregion
    }
}

100

using System;

using System.Collections.Generic;

using System.Data.OleDb;

using System.Diagnostics;

using DevExpress.Utils;

using DevExpress.XtraEditors;

using DevExpress.XtraGrid.Views.Grid;

namespace TestProject

{

/// <summary>

/// 메인 폼

/// </summary>

public partial class MainForm : XtraForm

{

//////////////////////////////////////////////////////////////////////////////////////////////////// Field

////////////////////////////////////////////////////////////////////////////////////////// Private

#region Field

/// <summary>

/// 연결

/// </summary>

private OleDbConnection connection;

/// <summary>

/// 소스 리스트

/// </summary>

private List<OrderDetail> sourceList;

#endregion

//////////////////////////////////////////////////////////////////////////////////////////////////// Constructor

////////////////////////////////////////////////////////////////////////////////////////// Public

#region 생성자 - MainForm()

/// <summary>

/// 생성자

/// </summary>

public MainForm()

{

InitializeComponent();

this.connection = new OleDbConnection("Provider=Microsoft.Jet.OLEDB.4.0;Data Source=nwind.mdb");

this.gridView.InitializeView

(

true, // Multi Select

GridMultiSelectMode.CellSelect, // Grid Multi Select Mode

DrawFocusRectStyle.CellFocus, // Draw Focus Rect Style

true, // Show Indicator

true, // Show Column Headers

true, // Allow Column Moving

true, // Allow Column Resizing

true, // Allow Filter

true, // Allow Sort

false, // Allow Cell Merge

EditorShowMode.Default, // Editor Show Mode

false // Editable

);

this.gridView.OptionsBehavior.AutoPopulateColumns = true;

this.sourceList = OrderDetail.GetOrderDetailList(this.connection);

this.gridControl.DataSource = this.sourceList;

this.gridView.BestFitColumns();

this.exportButton.Click += exportButton_Click;

}

#endregion

//////////////////////////////////////////////////////////////////////////////////////////////////// Method

////////////////////////////////////////////////////////////////////////////////////////// Private

#region PDF 파일 내보내기 버튼 클릭시 처리하기 - previewButton_Click(sender, e)

/// <summary>

/// PDF 파일 내보내기 버튼 클릭시 처리하기

/// </summary>

/// <param name="sender">이벤트 발생자</param>

/// <param name="e">이벤트 인자</param>

private void exportButton_Click(object sender, EventArgs e)

{

this.gridView.OptionsPrint.ExpandAllDetails = true;

this.gridView.ExportToPdf("d:\\sample.pdf");

Process.Start("d:\\sample.pdf");

}

#endregion

}

TestProject.zip

[C#/WINFORM] 이미지를 PDF 파일로 저장하기

■ 이미지를 PDF 파일로 저장하는 방법을 보여준다. ▶ 예제 코드 (C#)


using System;
using System.Drawing;
using System.Windows.Forms;

using PdfSharp.Drawing;
using PdfSharp.Pdf;

#region 이미지를 PDF 파일로 저장하기 - SavePDFFile(sourceImage, targetPDFFilePath)

/// <summary>
/// 이미지를 PDF 파일로 저장하기
/// </summary>
/// <param name="sourceImage">소스 이미지</param>
/// <param name="targetPDFFilePath">타겟 PDF 파일 경로</param>
/// <returns>처리 결과</returns>
public void SavePDFFile(Image sourceImage, string targetPDFFilePath)
{
    PdfDocument pdfDocument = null;

    try
    {
        pdfDocument = new PdfDocument();

        double sourceImageWidth  = (sourceImage.Width  / 96d) * 72d;
        double sourceImageHeight = (sourceImage.Height / 96d) * 72d;

        int pageHeight = (int)((842d / 72d) * 96d);
        int pageCount  = (int)Math.Ceiling(sourceImageHeight / 842d);

        for(int i = 0; i < pageCount; i++)
        {
            Bitmap   pageBitmap   = new Bitmap(sourceImage.Width, pageHeight);
            Graphics pageGraphics = Graphics.FromImage(pageBitmap);

            pageGraphics.DrawImage
            (
                sourceImage,
                new Rectangle(0, 0, sourceImage.Width, pageHeight),
                new Rectangle(0, i * pageHeight, sourceImage.Width, pageHeight),
                GraphicsUnit.Pixel
            );

            PdfPage pdfPage = new PdfPage();

            pdfPage.Width = XUnit.FromPoint(sourceImageWidth);

            pdfDocument.AddPage(pdfPage);

            XImage    xImage    = XImage.FromGdiPlusImage(pageBitmap);
            XGraphics xGraphics = XGraphics.FromPdfPage(pdfPage);

            xGraphics.DrawImage(xImage, 0, 0);
        }

        pdfDocument.Save(targetPDFFilePath);
    }
    finally
    {
        if(pdfDocument != null)
        {
            pdfDocument.Clone();
        }
    }
}

#endregion

using System;

using System.Drawing;

using System.Windows.Forms;

using PdfSharp.Drawing;

using PdfSharp.Pdf;

#region 이미지를 PDF 파일로 저장하기 - SavePDFFile(sourceImage, targetPDFFilePath)

/// <summary>

/// 이미지를 PDF 파일로 저장하기

/// </summary>

/// <param name="sourceImage">소스 이미지</param>

/// <param name="targetPDFFilePath">타겟 PDF 파일 경로</param>

/// <returns>처리 결과</returns>

public void SavePDFFile(Image sourceImage, string targetPDFFilePath)

{

PdfDocument pdfDocument = null;

try

{

pdfDocument = new PdfDocument();

double sourceImageWidth = (sourceImage.Width / 96d) * 72d;

double sourceImageHeight = (sourceImage.Height / 96d) * 72d;

int pageHeight = (int)((842d / 72d) * 96d);

int pageCount = (int)Math.Ceiling(sourceImageHeight / 842d);

for(int i = 0; i < pageCount; i++)

{

Bitmap pageBitmap = new Bitmap(sourceImage.Width, pageHeight);

Graphics pageGraphics = Graphics.FromImage(pageBitmap);

pageGraphics.DrawImage

(

sourceImage,

new Rectangle(0, 0, sourceImage.Width, pageHeight),

new Rectangle(0, i * pageHeight, sourceImage.Width, pageHeight),

GraphicsUnit.Pixel

);

PdfPage pdfPage = new PdfPage();

pdfPage.Width = XUnit.FromPoint(sourceImageWidth);

pdfDocument.AddPage(pdfPage);

XImage xImage = XImage.FromGdiPlusImage(pageBitmap);

XGraphics xGraphics = XGraphics.FromPdfPage(pdfPage);

xGraphics.DrawImage(xImage, 0, 0);

}

pdfDocument.Save(targetPDFFilePath);

}

finally

{

if(pdfDocument != null)

{

pdfDocument.Clone();

}

#endregion

PdfSharp.zip