YOU CAN NOW RUN OCR COMPLETELY OFFLINE ON YOUR OWN MACHINE WITH ZERO API COSTS.
AWS Textract charges $1.50 per 1,000 pages. Google Document AI charges $1.50 per 1,000. Adobe Acrobat Pro locks basic OCR behind a subscription. this repo replaces all of them and its completely free.
Its called Ollama-OCR -- a Python package that runs vision language models locally through Ollama to extract text from images and PDFs. No cloud. No API keys. No usage limits.
Here's what you can actually do with it:
→ Extract text from images and PDF files with a single Python function call
→ Choose from 5 vision models depending on your hardware -- LLaVA, Llama 3.2 Vision, Granite3.2-vision (built for documents, tables, charts), Moondream (edge devices), or MiniCPM-V (handles images up to 1.8M pixels)
→ 6 output formats -- Markdown, plain text, JSON, structured data, key-value pairs, and clean table extraction
→ Batch processing with parallel workers and progress tracking
→ Custom prompts to focus extraction on specific fields like dates, names, invoice numbers
→ Language selection for better OCR accuracy on non-English documents
→ Streamlit web app included for drag-and-drop OCR without writing code
Here's the wildest part:
If your extracting handwritten notes, scanned invoices, tables from PDFs, or receipts in any language, this handles all of it locally on your GPU or even CPU. Your documents never leave your machine, which means sensitive medical records, legal documents, and financial statements stay private.
It also works inside Autogen and LangGraph pipelines out of the box -- so you can plug it directly into agent workflows.
Install with one line: pip install ollama-ocr
2.3K GitHub stars. 258 forks. MIT license.
100% open source.
(link in the comments)
🇺🇸📨 Vcs sabiam que os correios dos USA deu prejuízo nos últimos 20 anos?
Correio é um serviço estatal, essencial, de direito do povo.
https://t.co/2A5Yxk4iZo
É bom acordar! Jamais deveria ter sido aceita a candidatura do Flávio Bolsonaro! Seu pai está preso por tentativa de golpe. O que esperam que o filho do Jair faça? Respeite o estado democrático de direito?
Influenciadora denuncia transfobia após funcionário insinuar que ela era prostitut*:
“Tá mas a gente é cliente, a gente tá comprando. Eu tô achando você muito
folgado. Você tá falando ‘A Praça da República é ali’ como se a gente fosse prostitut*. A gente não faz programa, a gente é travesti.”
Finalmente a verdade sobre o polêmico corrimão da escada do Itamaraty! Ele realmente existiu? Foi instalado para a visita da Rainha Elizabeth II?
Niemeyer era contra ou a favor?
Conteúdo produzido com base no levantamento feito pela Coordenação-Geral de Patrimônio Histórico do @ItamaratyGovBr.
Quem mente mais: a direita ou a esquerda?
Quando um político admite que "é difícil lutar dentro das regras porque a luta é muito desigual", fica a pergunta: se até quem diz defender as regras admite a tentação de abandoná-las, onde termina a estratégia política e começa a manipulação?
No fim, quem paga essa conta é o eleitor, que precisa descobrir todos os dias quem está defendendo uma ideia e quem está apenas defendendo a própria narrativa.
MERECE VIRALIZAR! É um dos vídeos mais importantes que você vai assistir hoje. Mostra de forma didática a ligação entre a família Bolsonaro, o Caso Master, Dark Horse e as tarifas contra o Brasil.
ASSISTAM ATÉ O FINAL! 👏🏾
Brazilian lawmaker Erika Hilton is taking a stand against Sony’s “end of discs” announcement sending the issue to Brazil’s consumer protection agency and calling for Sony to be investigated.
Hilton says people pay extra for PlayStation consoles with disc drives, so moving away from physical games raises consumer rights concerns.
She believes Sony should be investigated if the company releases games only in digital format to push more people toward digital-only consoles.
She also wants game publishers to be clearer about digital ownership, so players know exactly what they own when they buy a digital game.
It took a little longer than expected, but we have created a website for people to view the footage collected from Gaza in one place. You no longer have to download the entire archives to see them.
It includes:
64,537 videos
17,905 photos
Ability to download individual videos
Searchable index
Exhaustive sources list (300+ journalists)
Geolocation data
Livemap with minute to minute updates
Victim list
It can be accessed here: https://t.co/s0Se94PXWF
Please share & quote tweet to help this post break out of the twitter algorithm prison.
We will keep adding the rest of the archives to the site, be patient- it is difficult work. Continue to seed the torrents provided, as that is the best way to ensure the footage remains stored in decentalized way.
God bless all those who sacrificed their lives to get this footage out, and everyone invovled in collecting/archiving it.
Join our telegram:
https://t.co/bvcis3b9GT
Follow our backup accounts:
@ZionismExposedx & @IsraelExposedAr
Instagram launches forced Data Collection to use their app
If you login and get this prompt, you must accept data all this data collection or you will be promoted to log out and not allowed to use the App
Here is a full down of what’s mandatory to give up to use Instagram:
Collection and use of personal data: They collect our activity on Instagram (posts, stories, likes, comments, searches, time spent), device info, IP address, contacts (if synced), messages, location (when enabled), demographics, and inferred interests
Sharing of data with other Meta companies. They take all the personal data they collected and share across Facebook, WhatsApp, Threads, Oculus, etc.
Cross-border transfers of personal data: Your data is sent and stored in the US and other countries where Meta has offices/data centers or partners.
Location information: Precise location (GPS when you use features like Stories or check-ins), approximate location from IP/Wi-Fi, and location-based activity history.
Stop using META products