Learn Python Coding
40.9K subscribers
723 photos
37 videos
24 files
538 links
Learn Python through simple, practical examples and real coding ideas. Clear explanations, useful snippets, and hands-on learning for anyone starting or improving their programming skills.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
Convert PDF to docx using Python

📂 Tags: #DataScience #Python #ML #AI #LLM #BIGDATA #Courses

http://t.iss.one/codeprogrammer ⭐️
Please open Telegram to view this post
VIEW IN TELEGRAM
👍5
📕 Python Basics Made Simple!

📷 Course: AI Python for Beginners

👨‍💻 Instructor: Andrew Ng

In the #AIPythonforBeginners course series you'll learn how to identify strings, integers, and floats with the type() function, and build a solid Python foundation for your AI journey.

Enroll Free: https://learn.deeplearning.ai/courses/ai-python-for-beginners

📂 Tags: #DataScience #Python #ML #AI #LLM #BIGDATA #Courses #Transformer

http://t.iss.one/codeprogrammer ⭐️
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3
Part 4: Cutting-Edge Web Scraping – AI, Blockchain, Quantum Resistance, and the Future of Data Extraction

Duration: ~60 minutes

Link A: https://hackmd.io/@husseinsheikho/WS-4A

Link B: https://hackmd.io/@husseinsheikho/WS-4B

#AIWebScraping #BlockchainData #QuantumScraping #EthicalAI #FutureProof #SelfHealingScrapers #DataSovereignty #LLM #Web3 #Innovation
❤3
🔥 10 GitHub Repositories to Scrape Almost Any Website

1. Firecrawl
Turns entire websites into clean, AI-ready Markdown or structured data with just a few API calls. Perfect for feeding LLMs. 🤖

2. Crawl4AI
An open source python crawler built specifically for AI. Extracts clean, structured content optimized for LLMs. 🐍

3. Browser Use
AI Agent that control browsers like a human. It allows an AI agent to dynamically visually navigate, click elements, bypass popups, and extract data. 🖱️

4. Crawlee
A powerful scraping framework for building fast, reliable crawlers with support for Playwright, Puppeteer, and Cheerio. ⚡

5. Scrapy
One of the most popular Python frameworks for large-scale web scraping and crawling projects. 🕷️

6. MarkItDown
Converts PDFs, Office documents, HTML, and many other file types into clean Markdown for AI workflows. 📄

7. Scrapling
A modern Python scraping library that combines speed, browser automation, and smart parsing with a simple API. 🚀

8. Skyvern
An AI-powered scraping tool that dynamically solve CAPTCHAs, log into complex portals, and extract data without requiring any pre-defined HTML selectors or XPaths. 🔓

9. AutoScraper
Automatically learns how to extract similar data from web pages by showing it just a few examples. 🧠

10. curl-impersonate
Makes cURL mimic real browsers like Chrome and Safari to bypass bot detection and access protected websites more reliably. 🕵️

💡 Save this list for your next web scraping or AI automation project.

#WebScraping #AI #GitHub #Python #Automation #LLM

✨ Join Best TG Channels https://t.iss.one/addlist/0f6vfFbEMdAwODBk

⭐️ Join Our WhatsApp Channel https://whatsapp.com/channel/0029VaC7Weq29753hpcggW2A
❤6
🌟 Detecting Hallucinations in LLM Responses through Perplexity Calculation 🤖

Hallucinations in language models lead to the generation of false, yet convincingly sounding, facts. 📝
Calculating the perplexity of the generated text allows us to assess the model's confidence in its responses. 📊
We will write a Python script to calculate perplexity and filter out questionable generations. 🐍

Let's install the
transformers

and
torch

libraries to work with language models and calculate perplexity.
pip install transformers torch

The libraries for calculating perplexity have been successfully installed. ✅

Let's create a Python script called
perplexity_check.py

that calculates the perplexity level for a given text.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "gpt2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

inputs = tokenizer("Example text for perplexity check.", return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs, labels=inputs["input_ids"])
print("Loss value:", outputs.loss.item())

The perplexity calculation script has been successfully created and is ready to run. 🚀
# Verify the script's functionality
python3 -c "import torch; print('PyTorch Ready')"

Expected output:
PyTorch Ready

# cleanup (remove the test script)
rm -f perplexity_check.py

An abnormally high perplexity often indicates that the model has started "hallucinating" and generating illogical text. 🚫

Integrate this threshold into safety filters (Guardrails) to automatically block incorrect responses. 🛡️

https://t.iss.one/pythonRe

#Python #AI #LLM #MachineLearning #Coding #Tech

🌟 Join Best TG Channels
https://t.iss.one/addlist/0f6vfFbEMdAwODBk

⭐️ Join Our WhatsApp Channel
https://whatsapp.com/channel/0029VaC7Weq29753hpcggW2A
Please open Telegram to view this post
VIEW IN TELEGRAM
❤4