← Back to Vibers
Builder
opendataloader-project
2 Tools
OpenDataLoader is an open-source PDF extraction SDK developed by Hancom Inc., the South Korean software company behind the Hangul word processor — Korea's dominant office suite for over three decades. The project uses a hybrid engine that pairs AI models with rule-based heuristics to convert complex PDFs into structured, LLM-ready output that runs entirely on-premise. The v2.0 release in March 2026 reached #1 on GitHub's global trending chart across all programming languages.
Tools
LangChain OpenDataLoader PDF(https://github.com/opendataloader-project/langchain-opendataloader-pdf)
Python integration that feeds OpenDataLoader's structured PDF parsing into LangChain RAG pipelines.
OpenDataLoader PDF for LlamaIndex(https://github.com/opendataloader-project/opendataloader-pdf-llamaindex)
LlamaIndex reader that runs OpenDataLoader locally for accurate PDF extraction in RAG pipelines.