Extract text from Korean HWP document files
HWP Loader reads HWP files (South Korean official document format) into LlamaIndex, handling both compressed and uncompressed files for document processing.
Why it matters
Load and extract text content from HWP (Hangul Word Processor) files, the standard format for official documents in South Korea, to make them accessible for indexing, search, and AI processing workflows.
Outcomes
What it gets done
Read compressed and uncompressed HWP file formats
Extract text content from Korean government and business documents
Convert HWP files into document objects for LlamaIndex pipelines
Enable RAG indexing of South Korean official document archives
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/li-reader-readers-hwp | bash Overview
HWP Loader
HWP Loader is a LlamaIndex reader that extracts content from HWP files, the standard format for official documents in South Korea. It handles both compressed and uncompressed HWP files, converting them into LlamaIndex Document objects for indexing and querying. Use HWP Loader when you need to read and extract content from HWP files within a LlamaIndex workflow. It handles both compressed and uncompressed HWP files.
What it does
HWP Loader is a LlamaIndex reader that extracts content from HWP files, the standard format for official documents in South Korea. It processes both compressed and uncompressed HWP files, converting them into document objects that can be indexed and queried within the LlamaIndex framework.
When to use - and when NOT to
Use HWP Loader when you need to read and extract content from HWP files within a LlamaIndex workflow. It handles both compressed and uncompressed HWP files.
Do NOT use this loader if your documents are in standard formats like PDF, DOCX, or plain text - use format-specific readers instead.
Inputs and outputs
You provide a file path (as a Path object or string) pointing to an HWP file on your filesystem. The file can be either compressed or uncompressed.
You receive a list of documents from the loader that can be used in your LlamaIndex pipeline.
Installation and usage
Install the reader via pip:
pip install llama-index-readers-file
Load HWP documents with this code:
from llama_index.readers.file import HWPReader
from pathlib import Path
hwp_path = Path("/path/to/hwp")
reader = HWPReader()
documents = reader.load_data(file=hwp_path)
Who it's for
HWP Loader serves developers working with HWP files in LlamaIndex applications.
Source README
HWP Loader
pip install llama-index-readers-file
This loader reads the HWP file, which is the format of many official documents in South Korea.
Usage
To use this loader, you need to pass in a file name. It's fine whether the file is compressed or not.
from llama_index.readers.file import HWPReader
from pathlib import Path
hwp_path = Path("/path/to/hwp")
reader = HWPReader()
documents = reader.load_data(file=hwp_path)
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.