Urgent.News

What's breaking now, across thousands of outlets.

Saturday, 29 August 2026 Reading Room

Tech

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

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 takes a better approach: classify first, extract native text when possible, and route only the pages that actually need OCR. The routing pattern The core decision is…

dev.to ·

OCR is frequently the most costly and time-consuming stage in document ingestion. Many PDFs already contain readable text, yet naive pipelines still perform OCR on every document. pdf_inspector offers a superior method: classify first, extract native text when possible, and only OCR pages that require it. The routing process begins with the PDF arriving, then classifying the document and its pages.

If native text is already present, it is extracted locally and converted to Markdown. If text is missing or broken, those pages are routed to OCR. This simple decision can significantly reduce unnecessary OCR work in RAG ingestion, invoice processing, research paper parsing, and document search. pdf_inspector classifies PDFs as TextBased, Scanned ImageBased, or Mixed, providing a confidence score and identifying specific pages needing OCR.

Using Python, install the package via pip install pdf_inspector, then process a PDF with result = pdf_inspector.process_pdf(document.pdf). The result includes the PDF type, pages needing OCR, and Markdown output. For selective OCR, use the process_pdf_with_ocr function to get the pages routed to OCR. Node.js and browser support are also available through the @firecrawl/pdf-inspector and @firecrawl/pdf-inspector-wasm packages.

Classification preserves structure such as headings, bold and italic text, numbered and bulleted lists, code blocks, tables, links, page breaks, captions, and common font encodings. The output is Markdown, ideal for search indexing and LLM/RAG pipelines. Classification works by inspecting PDF content streams for text operators (Tj and TJ) and image operators (Do).

It can scan all pages, sample large documents, or inspect a caller-provided page set. While the library provides a routing signal, it does not guarantee perfect parsing for every PDF. The library reports encoding issues to allow fallback to specialized parsers if needed. Benchmark numbers are available for a 200-document corpus, showing strong performance but not a universal latency guarantee.

The key takeaway is that OCR should be a per-page fallback, not a default for every file. A conservative router might check the PDF type and confidence score, storing Markdown for text-based PDFs with high confidence or routing pages needing OCR accordingly. This approach balances extraction costs and false positive risks, making it suitable for various use cases like casual knowledge bases or legal and financial workflows.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

A static analysis rule written from a spec is a hypothesis

Last week I shipped a tool that predicts which ComfyUI custom nodes will break on your next git pull . It answered one question: does every name a pack imports still exist upstream?

  • ComfyUI tool predicts node pack breakage after latest changes
  • Static analysis rule identifies ImportError errors in packs
  • Tool adds commit/PR/release info to issues, not just bug detection

·dev.to

When 'Kim Jong-un', 'Republic of Korea' and 'boyfriend' were typed on a North Korean smartphone, an autocorrect function showed the results were 'Great Leader', 'South: hostile nation' and 'comrade'. Typing 'Kim Jong-un' on the device autocorrected to 'Great Leader'. When 'Republic of Korea' was typed, autocorrect suggested 'South: hostile nation'. Typing 'boyfriend' autocorrected to 'comrade'. The experiments were conducted by a source who possesses a smartphone used in North Korea. The source said that when searching for terms on a North Korean smartphone, users are often redirected to a propaganda site operated by the North Korean government. The smartphone in question was provided by the 'Kwangmyong' network, which is run by the North Korean government. Kwangmyong provides internet services to residents of North Korea. The findings suggest that North Korean authorities are making efforts to control the flow of information through smartphones. The smartphone user said that when searching for information on the device, they often could not find what they were looking for. The user said that although smartphones have become popular in North Korea, they do not provide the same level of internet freedom as in other countries. The North Korean government is known to operate a 'national intranet', which provides limited internet services to residents. The findings highlight the strict controls on information flow in North Korea. The experiment also showed that typing 'United States' on the smartphone autocorrected to 'imperialist aggressor'. Typing 'Japan' autocorrected to 'Japanese imperialist aggressor'. The source said that North Korean authorities are using technology to control what information residents can access. The findings suggest that North Korean authorities are using autocorrect functions and search results to shape public opinion. The experiment was conducted to understand the level of internet freedom in North Korea. The findings provide insight into the strict controls on information flow in the country. The North Korean government's control of information flow has significant implications for residents' access to information. The experiment highlights the challenges of accessing information in North Korea. The findings have significant implications for understanding the level of internet freedom in North Korea. The North Korean government's efforts to control information flow through smartphones are part of a broader strategy to control the flow of information. The experiment provides insight into the ways in which North Korean authorities are using technology to control information flow. The findings have significant implications for understanding the role of technology in shaping public opinion in North Korea. The North Korean government's control of information flow has significant implications for residents' access to information and their understanding of the world. The experiment highlights the importance of understanding the level of internet freedom in North Korea. The findings provide insight into the challenges of accessing information in the country. The North Korean government's efforts to control information flow through smartphones are significant. The experiment provides insight into the ways in which North Korean authorities are using technology to shape public opinion. The findings have significant implications for understanding the level of internet freedom in North Korea and the challenges of accessing information in the country.

·hani.co.kr

More from Saturday 29 August →