3 projects
pdfmux
Self-healing PDF extraction for RAG that flags pages it can't read instead of dropping them — and certifies any extractor's output for silent drops. Per-page confidence scoring, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse alternative.
llama-index-readers-pdfmux
llama-index readers pdfmux integration
langchain-pdfmux
LangChain document loader for pdfmux — self-healing PDF extraction