Classify PDFs. Extract Markdown. No OCR.

use pdf_inspector::process_pdf;

let result = process_pdf("document.pdf")?;
println!("Type: {:?}", result.pdf_type);
if let Some(markdown) = &result.markdown {
    println!("{}", markdown);
}
// full reference → docs/rust-api.md

import pdf_inspector

result = pdf_inspector.process_pdf("document.pdf")
print(result.pdf_type)   # "text_based" | "scanned" | "image_based" | "mixed"
print(result.markdown)   # Markdown string or None
# full reference → docs/python.md

import { readFileSync } from 'fs';
import { processPdf } from '@firecrawl/pdf-inspector';

const result = processPdf(readFileSync('document.pdf'));
console.log(result.pdfType);   // "TextBased" | "Scanned" | ...
console.log(result.markdown);  // Markdown string or null
// full reference → napi/README.md

# install the CLI tools
cargo install pdf-inspector

# convert a PDF to Markdown
pdf2md document.pdf

# classify only — is it scanned?
detect-pdf document.pdf --analyze --json

# structured output for pipelines
pdf2md document.pdf --json