Tag
Recommends 5 open-source RAG tools (RAGFlow, AnythingLLM, Onyx, Khoj, kotaemon) that turn documents into a Q&A knowledge base with zero code, each with unique features.
A user seeks recommendations for PDF preprocessing tools to improve input quality for local LLM-based document QA, comparing pymupdf, pdfplumber, docling, and llamaparse for handling messy layouts like tables and multi-column text.
A benchmark comparing vision-capable LLMs (native PDF reading) against OCR-based pipelines on 30 long, image-heavy PDFs finds that OCR with layout extraction still outperforms vision models on chart/table-heavy pages and has a 0% failure rate vs. 7% for native PDF, though the sample size is small and many gaps are within noise.