Бесплатная верстка и перевод книг: как я создал конвейер, работающий на видеокарте
Три месяца отладки, десятки книг и переход от Claude к локальным моделям. Рассказываю, как собрал открытый конвейер перевода и вёрстки книг: MinerU…
Programming
⚑ Report a ProblemLatest Programming news from Tech News
All topics
AI
agents
ai
api
architecture
automation
backend
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
rust
security
showdev
testing
tutorial
typescript
webdev
Auditable Monthly Report Archiving with PDF Text Extraction and OCR Verification
Short answer: extract embedded PDF text first, but make the decision per page rather than per file; send only pages that fail structural and content…
OCR + LLM Pipeline for Contract Review: What Actually Works in Production
If you’ve ever tried to extract data from legal contracts, financial reports, or dense PDFs, you already know the pain. You throw a standard OCR too…
Guarding OCR Costs With Node.js Hash Dedupe for Supplier Images
TL;DR: In a Node.js and Express catalogue importer, dedupe supplier images by using normalized metadata as a quick filter and a SHA-256 hash of the…
Is Tesseract accurate enough for production?
Tesseract is accurate enough for production when your documents look like the ones it was built for, clean printed pages at a sufficient resolution,…
Searchable Edtech Reports in Node.js — OCR and Page-Level Indexing
Short answer: archive the original monthly report, extract its existing text layer first, and send only pages without useful text through OCR. Index…
YOalphabet & YOconlang: A Spatial 4-Bit Bytecode Script for Zero-Inference Machine Vision
Modern Optical Character Recognition (OCR) forces edge devices to run heavy neural networks just to read basic text. YOalphabet introduces AIneograp…
Running the PaddleOCR PDF OCR service as a one-shot job, locally and on Azure Container Apps
paddleocr-pdf-api runs as an HTTP server that accepts PDF uploads and returns markdown. Setting RUN_MODE=job runs the same OCR pipeline on a single…
Human-in-the-Loop Metadata Inspection — Linking Extracted Text to Source Images
A receipt review console is only trustworthy when every extracted value can be traced to the exact pixels a reviewer is judging. Short answer: store…
Экранный переводчик для macOS: читаем статьи и смотрим видео без переключения окон
При чтении технической литературы, англоязычных статей или просмотре видео с субтитрами часто натыкаешься на незнакомые слова. В этой статье я расск…
A document pipeline in 30 lines, running in a browser tab
Written 2026-09-03. Targets @stabrise/[email protected] , pdfjs-dist@6 , [email protected] . Assumes TypeScript and npm; assumes nothing about OCR or…
Где VLM не читали старых газет: разбираем PereStruct, открытый датасет и модульный парсер
Попробуйте открыть скан советской газеты и прочитать одну статью от начала до конца. Человек быстро замечает крупный заголовок, продо…
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 tex…
Как мы написали свой OCR и автоматизировали горы первички
Когда внутренних заказчиков становится слишком много — каждый со своими хотелками и типом документов — поддерживать кучу отдельных сервисов уже нере…
Draft vs High: The OCR Quality Parameter Nobody Reads the Docs For
Five different places document PDF4me's OCR quality setting: the REST API and four no-code platforms. Read all five pages back to back and you'll fi…
Small in Code. Large in Behavior.
Neuroloq's attachment pipeline turns on one boundary that comes before transcription: whether to treat an upload as document-like at all, and only t…
Building a Financial Document OCR with Claude Vision API: Lessons from Production
After processing thousands of bank statements, invoices, and receipts through Claude Vision API, I've learned that financial document OCR is harder…
TrulyFreeOCR – a Java OCR pipeline in a single fat JAR, zero native deps required
Introduction I'm the author of TrulyFreeOCR, an open-source OCR pipeline that turns scanned PDFs into searchable, highly-compressed PDFs. Everything…
The quiet race to turn messy documents into AI-ready text
Mistral introduced a new version of its document-reading model as a hosted OCR service, and the open-source project MinerU has been climbing fast on…
AI Dev Weekly #16: Mistral OCR 4, Claude Tag, Alibaba Caught Stealing, GPT-5.6 Delayed
AI Dev Weekly is a Thursday series where I cover the week's most important AI developer news, with my take as someone who actually uses these tools…
Deploying Paperless-ngx Open-Source Document Management System on Ubuntu 24.04
Paperless-ngx is an open-source document management system that converts scans and PDFs into a fully searchable archive using Tesseract OCR, with ta…
Arabic OCR with an API: Make Scanned Arabic PDFs Searchable (Python)
If you've ever tried to extract text from a scanned Arabic document, you already know the pain. Most OCR tooling is built English-first. Arabic adds…
[Перевод] Почему промпты для VLM работают наоборот: как это исправить
Недавно я пытался выжать максимум из корпоративной OCR-модели, перебирая промпты и гиперпараметры, когда наткнулся на issue в репозитории Qwen-3-VL.…
Как я написал свой overlay-переводчик на python
Бывало у вас такое: находите крутую инди-игру или визуальную новеллу, а официальной русской локализации нет? Сидеть со смартфоном в руках и переводи…
AI Invoice OCR Explained: How Local AI Reads Your PDFs
jaklens.com Step 1 in depth: pdfjs-dist pdfjs-dist is Mozilla's PDF rendering library — the same engine that powers Firefox's built-in PDF viewer. I…
Как построить умный реестр документов с бесплатным OCR и обходом лимитов API AI
Формирование реестров документов для указанных папках с нужными параметрами (такими как название статьи, краткое описание и т.п.) с использова…
One API Call Changed Everything
Sunday morning. I'm about ready to type everything by hand and call it a weekend. But I want to try one more thing. Instead of OCR to extract charac…
The OCR Rabbit Hole
Long weekend. Pile of handwritten documents on the desk. They need to become structured data - searchable fields in an app, not just scanned images.…