Технозаметки Малышева | United States America (US)

Create: 2025-06-30 Update: 2025-06-30 16:51:45

🚀 Docling 2.0: Новый cтандарт предобработки документов для RAG

32,830 звёзд на GitHub за год — Docling от IBM Research завоевывает все большую популярность и становится основным инструментом для подготовки документов к AI обработке.

Что изменилось в версии 2.0:
30x ускорение по сравнению с традиционным OCR:

- 3.1 сек/страница на CPU x86
- 0.49 сек/страница на Nvidia L4 GPU
- 0.35 сек/страница с новой SmolDocling (256M параметров, <500MB VRAM)

Ключевой подход: компьютерное зрение вместо OCR там, где возможно — PDF обрабатываются напрямую через специализированные AI-модели.

Технические преимущества
TableFormer достигает 93.6% точности против 67.9% у Tabula и 73.0% у Camelot — обрабатывает сложные таблицы с частичными границами и иерархическими заголовками.

SmolDocling + формат DocTags — сквозное преобразование документов в один проход.

Новый markup-формат под VLMки.

ASR-поддержка для WAV/MP3 — теперь можно обрабатывать записи встреч и лекций.

Корпоративные внедрения
- Red Hat Enterprise Linux AI использует Docling как ядро InstructLab для кастомизации моделей.
- IBM: уже обработали 2.1M PDF из Common Crawl, планы до 1.8B PDF для обучения Granite.
- Linux Foundation AI & Data — официальное управление с мая 2025, статус enterprise-ready.

Интеграции "из коробки"
- LangChain: DoclingLoader с режимами DOC_CHUNKS и MARKDOWN
- LlamaIndex: DoclingReader + DoclingNodeParser
- Haystack/CrewAI: прямая поддержка агентных workflow
- Унифицированный формат: экспорт в Markdown, HTML, DocTags, JSON

Практическое применение
Когда использовать: сложные документы, где структурная точность критична (финансовые отчёты, юридические контракты, научные статьи).
Когда НЕ использовать: простое извлечение текста — PyMuPDF будет в 50x быстрее.

MIT-лицензия - свободно используем для коммерции.

В планах разработки:
- Извлечение метаданных (авторы, ссылки, язык)
- Понимание диаграмм (уже частично в SmolDocling)
- Химические структуры (молекулы в патентах/исследованиях)

Полезная штука. Добавляем в пул микросервисов.

GitHub

#Docling #Documents #RAG #IBM
———
@tsingular

Технозаметки Малышева

hottg.com/tsingular/4344

874 viewsedited Jun 30 at 05:56

>>Click here to continue<<

Технозаметки Малышева

Share with your best friend

Telegram Desktop App Not Working on Windows?

Preliminary Fixes.

Rule out internet issues: Make sure your device is connected to a stable internet connection by running other apps on the same computer. When other apps work fine, connectivity issues get ruled out. Check Telegram status: When the internet is connected correctly, the next step should be to check that Telegram isn't experiencing downtime. To do that, visit the downdetector website and type in "Telegram" to see what's happening. When Telegram's status is active and there are no reported issues on downdetector, Telegram's backend is unlikely to present any issues.Give Telegram a fresh start: After ruling out internet and backend issues, give Telegram a fresh start to remove the possibility of temporary glitches that prevent you from contacting your friends. Shut down the Telegram app completely, preferably from Task Manager, and then relaunch it.

🚀 Docling 2.0: Новый cтандарт предобработки документов для RAG

Технозаметки Малышева TG
Webview: 4344
Telegram TG Webview: hottg.com/tsingular/webview
Telegram TG Channel: Технозаметки Малышева
Telegram Updated: 2025-06-30 16:51:45

United States America Popular Telegram Group (US)

Telegram Q&A

Q: How does hottg.com work?

Once you've set up a username, you can give people a hottg.com/username link. Opening that link on their phone will automatically fire up their Telegram app and open a chat with you. You can share username links with friends, write them on business cards or put them up on your website.This way people can contact you on Telegram without knowing your phone number.

With Telegram, you can send messages, photos, videos and files of any type (doc, zip, mp3, etc), as well as create groups for up to 200,000 people or channels for broadcasting to unlimited audiences. You can write to your phone contacts and find people by their usernames. As a result, Telegram is like SMS and email combined — and can take care of all your personal or business messaging needs. In addition to this, we support end-to-end encrypted voice calls.

Q: What is Telegram? What do I do here?

Telegram is a messaging app with a focus on speed and security, it’s super-fast, simple and free. You can use Telegram on all your devices at the same time — your messages sync seamlessly across any number of your phones, tablets or computers.

Q: Who is Telegram for?

Telegram is for everyone who wants fast and reliable messaging and calls. Business users and small teams may like the large groups, usernames, desktop apps and powerful file sharing options. You can appoint admins with advanced tools to help these communities prosper in peace. Public groups can be joined by anyone and are powerful platforms for discussions and collecting feedback.In case you're more into pictures, Telegram has animated gif search, a state of the art photo editor, and an open sticker platform (find some cool stickers here or here). What's more, there is no need to worry about disk space on your device. With Telegram's cloud support and cache management options, Telegram can take up nearly zero space on your phone.

Q: How is Telegram different from WhatsApp?

Unlike WhatsApp, Telegram is a cloud-based messenger with seamless sync. As a result, you can access your messages from several devices at once, including tablets and computers, and share an unlimited number of photos, videos and files (doc, zip, mp3, etc.) of up to 2 GB each. And if you don't want to store all that data on your device, you can always keep it in the cloud.Thanks to our multi-data center infrastructure and encryption, Telegram is faster and way more secure. On top of that, Telegram is free and will stay free — no ads, no subscription fees, forever.

Q: Can I make calls via Telegram?

Yes! Voice calls are currently available to users around the world.

Many modern travelers appear to struggle with managing various aspects of their finances simultaneously while abroad, such as banking, budgeting, investing, trading, and saving. It is important to have apps installed on the device that will help you carry out these necessary tasks.

Hot Topic in US