Stop OCRing Every PDF: Route It First with pdf-inspector

Firecrawl has released pdf-inspector, an open-source library that classifies PDFs as text-based, scanned, image-based, or mixed, and routes only the pages that need OCR to the OCR engine. The tool, available in Python, Node.js, and WebAssembly, aims to reduce unnecessary OCR work in document-ingestion pipelines for RAG, invoice processing, and research-paper parsing. It also provides a confidence score and identifies specific pages requiring OCR, with a benchmark against a 200-document corpus.

OCR is often the most expensive and slowest step in a document-ingestion pipeline. The frustrating part is that many PDFs already contain usable text, yet a naive pipeline sends every document through OCR anyway. pdf-inspector https://github.com/firecrawl/pdf-inspector takes a better approach: classify first, extract native text when possible, and route only the pages that actually need OCR. The core decision is simple: PDF arrives ↓ Classify the document and its pages ├─ native text available → extract locally → Markdown └─ text missing/broken → route those pages to OCR That small decision can remove a large amount of unnecessary OCR work from RAG ingestion, invoice processing, research-paper parsing, and document search. The library classifies PDFs as: TextBased Scanned ImageBased Mixed It also returns a confidence score and the specific pages that need OCR. A 40-page report with one scanned appendix does not have to become a 40-page OCR job. Install the package: pip install pdf-inspector Then process a PDF: python import pdf inspector result = pdf inspector.process pdf "document.pdf" print result.pdf type print result.pages needing ocr print result.markdown For selective OCR, the native package also exposes an OCR-aware pipeline: ocr result = pdf inspector.process pdf with ocr "document.pdf" print ocr result.pages routed to ocr The OCR runtime remains separate and is only touched when a page is routed to it. That keeps the default extraction path lightweight. The same idea is available for Node.js: npm install @firecrawl/pdf-inspector js import { readFileSync } from "fs"; import { processPdf } from "@firecrawl/pdf-inspector"; const pdf = readFileSync "document.pdf" ; const result = processPdf pdf ; console.log result.pdfType ; console.log result.markdown ; There is also a WebAssembly package for running the Rust parser locally in a browser or Web Worker: npm install @firecrawl/pdf-inspector-wasm This is useful when documents should not be uploaded to a parsing service just to determine whether they contain native text. Classification is only half the project. For text-based PDFs, the extractor attempts to preserve structure such as: The output is Markdown, which makes the library convenient for search indexing and LLM/RAG pipelines. At a high level, the detector inspects PDF content streams for text operators such as Tj and TJ , and image operators such as Do . It can scan all pages, stop early, sample a large document, or inspect a caller-provided page set. This is a routing signal, not a promise that every PDF will be perfectly parsed. PDFs with broken encodings, text converted to vector paths, or extremely complex layouts may still need OCR or a specialized parser. The library explicitly reports encoding problems so callers can fall back instead of silently accepting bad text. The project publishes a reproducible benchmark against a 200-document corpus. Its July 2026 results report strong reading-order and table scores as well as fast local processing. Those are project-published measurements on specified hardware—not a universal latency guarantee—so benchmark your own document mix before committing to production thresholds. The more durable takeaway is architectural: OCR should be a fallback chosen per page, not the default chosen per file. A conservative router might look like this: result = pdf inspector.process pdf "document.pdf" if result.pdf type == "text based" and result.confidence = 0.95: store markdown result.markdown else: send pages to ocr result.pages needing ocr Your threshold should depend on the cost of a false positive. A casual knowledge base can tolerate more extraction noise than a legal or financial workflow. If your pipeline currently OCRs every incoming PDF, classification-first routing is a small change with a clear operational payoff. The longer version and implementation notes are available on ToolGenix https://toolgenix.nxtniche.com/posts/article-2026-08-03-qr/?utm source=devto&utm medium=referral&utm campaign=traffic pilot 202608&utm content=pdf inspector .