Document OCR in 90+ languages using python (100% free and without internet):
For document OCR, we'll use opensource toolkit Surya.
Python toolkit that does:
• OCR in 90+ languages
• Line-level text detection in any language
• Layout analysis (table, image detection)
• Reading order detection
• Outperforms Tesseract, on par with Google Cloud vision
1. Install the Python library
Run the following command from your terminal. You'll need python 3.9+ and PyTorch.
2. Try out the OCR (text detection) boilerplate code
3. Try out the built-in interactive demo with Streamlit.
Install Streamlit and run the following command in your terminal: 'surya_gui'
🌟 Support the opensource project:
8000+ readers receive my AI newsletter everyday and you are not one of them. Join @_unwind_ai to stay on top of the latest AI developments and tools: github.com/VikParuchuri/s… unwindai.substack.com
• • •
Missing some Tweet in this thread? You can try to
force a refresh
I vibe coded Instagram clone with this AI Agent using Claude 4 in less than 5 minutes.
Ship full-stack apps using Claude 4 without writing a single line of code.
Let that sink in.
Emergent is an agentic coding platform to build web apps, games, SaaS, Chrome extensions, and everything else.
It doesn't just generate code snippets, it builds entire systems with databases, APIs, authentication, and infrastructure, all with just simple prompts.
Here's another one:
I connected it with my GitHub repo Awesome LLM Apps and asked it to create a nice landing page for my Legal AI Agent Team app.
Web Action AI Agent that doesn’t just scrape but finds the data you need.
Firecrawl launched FIRE-1, an AI agent that navigates complex websites, interacts with buttons, fills forms, and gathers data beyond traditional scraping.
No manual steps required.
FIRE-1 AI Agent is available to use on Firecrawl starting today.