Chaker Rhim’s Post

Built a simple AI Agent using LangChain 🤖 that can call external tools through APIs. The agent uses DuckDuckGo search and a weather API to perform multi-step tasks like finding the capital of a state and fetching its current weather. Tech used: langchain-openai, langchain-core, langchain-community, requests, duckduckgo-search. Exploring more in AI Agents and LLM tool calling. #AI #LangChain #LLM #Python #AIAgents https://lnkd.in/gMtfUb2V

Day 5: From prompts to production-style AI workflow Today I built a book intelligence tool in Python that: - pulls live metadata from the Google Books API (title, authors, publishedDate, description) - uses a strict system prompt + output contract for consistent formatting - supports dual model backends:  - gpt-4o-mini (via OpenRouter/OpenAI SDK pattern)  - llama3.2 locally via Ollama - includes a reusable summarization pipeline (lookup -> prompt build -> model call -> structured response) - supports streaming responses in Jupyter with live token updates Technical focus areas I implemented: - prompt constraints to reduce hallucination risk (use only provided description) - deterministic generation (temperature=0) for stable output quality - backend abstraction so the same function can switch between cloud and local LLMs - graceful fallback when source metadata is incomplete This is the direction I’m doubling down on:   LLM architecture, interoperability, reliability, and real user-facing utility. Explore the full Day 5 build here (code + outputs): https://lnkd.in/deueEekK  Feedback and ideas for the next iteration are very welcome. Ed Donner #AIEngineering #LLM #GenerativeAI #OpenAI #Ollama #Python #MLOps #BlueOceanStrategy #BuildInPublic #Tech

#Day 16 [03-03-2026] #30DaysOfTech TS Academy End-to-end Python Project on Brand Strategy Analysis This is a learn through Python project on Youtube by @Loresowhat, i learn about how to clean dataset using text.splict() function ,using the Python libraries like the pandas, matplotlib and seaborn #LearningWithTSAcademy #30DaysOfTech TS Academy https://lnkd.in/d835Xu8b

🚀 Excited to share my latest Data Analysis & Machine Learning project using Python and Google Colab! In this project, I worked on analyzing food delivery order data to extract meaningful insights and build predictive models. ✅ Data Cleaning & Duplicate Handling Uploaded Excel dataset into Google Colab Detected and removed duplicate records Structured and prepared data for analysis 📊 Data Analysis & Visualization Restaurant-wise delivery success rate analysis Food item performance evaluation Monthly delivery success trend analysis Payment method vs delivery outcome insights Identified worst-performing food items and restaurants automatically 🤖 Machine Learning Implementation Converted delivery status into numerical labels Feature encoding using pandas Built a Random Forest classification model to predict delivery success/failure Evaluated model performance using train-test split 📈 Tools & Technologies Used: Python | Pandas | Matplotlib | Scikit-learn | Google Colab This project helped me strengthen my skills in data preprocessing, exploratory data analysis (EDA), visualization, and basic machine learning workflows. Project Notebook: https://lnkd.in/dUqeDVeg I’m continuously learning and exploring AI/ML and Data Analytics. Feedback and suggestions are always welcome! #DataAnalytics #Python #MachineLearning #DataScience #GoogleColab #LearningJourney #AI #BeginnerProject

topic :-- Merging, Joining & Concatenating in Pandas – Key Concepts Every Data Analyst Should Know When working with multiple datasets in Python, combining data is a common task. Pandas provides three powerful methods: Merge, Join, and Concat. 🔹 1️⃣ Merge (pd.merge) Used to combine DataFrames based on a common column or key Similar to SQL JOIN operations Supports inner, left, right, and outer joins Very useful when datasets share a common identifier (e.g., customer_id, student_id) Example: pd.merge(df1, df2, on="id", how="inner") 🔹 2️⃣ Join (df.join) Used to combine DataFrames based on the index Simpler syntax compared to merge Best when data is already indexed properly Example: df1.join(df2, how="left") 🔹 3️⃣ Concatenate (pd.concat) Used to stack DataFrames vertically or horizontally No need for a common key Useful for combining datasets with the same structure Example: pd.concat([df1, df2], axis=0) 🚀 Key Differences Merge → column based joining Join → index based joining Concat → stacking datasets 💡 Mastering these operations is essential for data cleaning, data preparation, and real-world data analysis projects. #Python #Pandas #DataScience #DataAnalysis #MachineLearning #DataAnalytics #LinkedInLearning github link :-- https://lnkd.in/dtD9AZWU colob link :-- https://lnkd.in/dpcyPAVM

Over the past period, I’ve been deepening my understanding of Python fundamentals and Object-Oriented Programming concepts through hands-on practice and real problem solving. Some of the key topics I’ve worked on include: Understanding the difference between shallow copy and deep copy when dealing with objects inside lists Using lambda functions for custom sorting based on object attributes Implementing flexible class designs using **kwargs to handle dynamic data Dynamically adding attributes to objects using setattr() Accessing and displaying object attributes using self.dict.items() Applying Encapsulation by creating private attributes (e.g., __balance) inside classes Building practical class-based systems like a BankAccount with deposit, withdraw, and get_balance methods while handling edge cases such as negative withdrawals Writing controlled loops using continue and break for condition-based execution These concepts helped me better understand how to design scalable and flexible class structures that can work with dynamic inputs such as JSON data or API responses — which is essential for real-world applications in automation, data processing, and backend systems. Project Link: https://lnkd.in/dkFY4uuU Special thanks to my Instructor Waled Saied, and my Mentor Iyad Mahdy , for their continuous support and guidance throughout this learning journey. Looking forward to applying these concepts in more advanced projects. #Python #OOP #SoftwareDevelopment #ProblemSolving #Programming #ComputerScience

I'm excited to share a project I've been working on to bring more transparency to the #PropFirm industry. Using Python, Pandas, and Matplotlib, I've built a live monitoring dashboard to track real-time discount levels and payout rules for over 15+ firms. Why? The industry moves fast. Traders deserve clear, data-backed information on where they can get the best risk-adjusted funding. Key Insights (March 2026): - MyFundedFutures and TakeProfitTrader are leading with consistent 40-50% discounts (Code: WIN). - Bulenox remains the value king with 90% OFF (Code: PFK). Access the Interactive Notebook (Google Colab): https://lnkd.in/ew-fv2ge Full Database & Live Coupons: https://propfirmkey.com #Trading #DataScience #Python #FinTech #PropTrading #OpenSource #LataiKamal

This week in our Python class, students will build something fun — a simple Tic-Tac-Toe (XOX) game using Python. Through this small project, they will learn how programming concepts such as lists, loops, conditions, and user input come together to create a real working game. It’s always exciting to see the moment when code turns into something interactive that students can actually play. I will also share a link so anyone can try the game themselves. Sometimes the best way to learn programming is simple: build something, test it, break it, and improve it. Looking forward to seeing what my students create next. #Python #CodingEducation #STEMEducation #ComputerScience #LearningByDoing https://lnkd.in/g9P5iqW9

Just wrapped up an exciting data science project focused on predicting Premier League football match outcomes! ⚽️ This journey took me from in-depth Exploratory Data Analysis (EDA) to building and optimizing Machine Learning models like Logistic Regression, Decision Trees, and SVMs. Key takeaways: EDA revealed fascinating insights: From home bias trends to the distribution of goals, understanding the data was crucial. Model Performance: Optimized Logistic Regression and SVM showed promising accuracy in predicting results, even with the inherent unpredictability of football. Feature Importance: Uncovered which half-time stats truly drive full-time results. The Power of Domain Expertise: Realized how much more potential lies in incorporating deep football knowledge (e.g., team form, injuries, tactics) into feature engineering. This project was a fantastic dive into applying ML to sports data, highlighting both the power and limitations of current models. Always learning! DataScience https://lnkd.in/gGwbFeDY #MachineLearning #FootballAnalytics #PremierLeague #Python #PredictiveModeling #SportsTech #EDA #LemonK #minkhant