03. Hangeul (HWP)

HWP (Korean)

Hangeul (HWP) is a word processor developed by Hangeul and the computer, a representative document writing program in Korea.

It uses .hwp as a file extension, and is widely used by businesses, schools, and government agencies. That's why Korean developers .hwp You may have had an experience with handling documents. (Or I will try)

Unfortunately, LangChain is not yet an integration, so I implemented it myself HWPLoader Should be used.

Copy

# installation
# !pip install -qU langchain-teddynote

Copy

from langchain_teddynote.document_loaders import HWPLoader

# HWP Loader object creation
loader = HWPLoader("./data/Digital Government Innovation Promotion Plan.hwp")

# load document
docs = loader.load()

Copy

# Output the results
print(docs[0].page_content[:1000])

Copy

Digital Government Innovation Promotion Plan 2019. 10. 29.      Ministry of Relations Joint Order Ⅰ. Overview ⁇  1II. Digital government innovation promotion plan  ⁇  2 1. Priority Promotion  ⁇  2 ① Preemptive and Integrated Large National Service Innovation ② Activating Public Sector Mydata ③ Platform for Citizen Participation ④ Implementing a Smart Work Environment to Support Field Center Collaboration ⑤ Enabling Cloud and Digital Service Use ⑥ Building an open data and service ecosystem 2. Established a mid- to long-term pan-government digital conversion roadmap  ⁇  4III. Propellant System and Schedule 4 [Paste] Digital Government Innovation Priority Promotion Agent (Detailed) ⁇  8I. Dogs □ Propulsion Background ○ Our country builds the world's highest level of e-government by contributing to the national high-speed information network investment and active public information business promotion ‧Operation * 2010 at the UN e-government assessment ‧12 ‧14 years 1st, 16‧18 years 3rd year, UN Public Administration Award ○ A system for the use of new technologies ‧ Shortage-There is no control tower for digital transformation, and no specific strategy ○ Accordingly, ‘From 19.3, embarked on a review of the current situation and problems of utilizing public sector ICT to establish a momentum for digital transformation in the public sector * Ministry of Relations 21st meeting (action, over-the-counter, materials, welfare, benefits  Private Expert Opinion Hearing 10th □ Problem Diagnosis and Assessment ○ (Service) Insufficient service innovation from the perspective of the people and end users-It is difficult to grasp the public services that they may receive even if they are eligible, a blind spot occurs, and online applications available Services are also limited ○ (Data) Accumulation by institutionLack of linkage and utilization of data held-Data is properly utilized to improve national interests, including the practice of receiving documents from the agency and submitting them to the B agency (issuing 9.5 billion annual ‘18 years).

metadata contains file name information.

Copy

# Output the results
print(docs[0].metadata)

Copy

 {'source':'./data/digital government innovation promotion plan.hwp'}