Dispatching PDFs to the Right Parser: Controlling Enterprise RAG Decisions
The article presents a rule‑based dispatcher that inspects each PDF, flags its traits, and selects a sequence of parsers—fitz for text, Docling for tables, EasyOCR for scans, vision LLMs for figures—then merges outputs into one searchable corpus. Explicit, logged choices prevent hidden LLM‑driven parsing that could mislead enterprise RAG.