Built a CodeRabbit clone with Python, FastAPI, LangChain, and LangGraph

💻 Handwritten Digit Recognizer using KNN 🚀 Excited to share my latest ML project — a Handwritten Digit Recognizer built using the K-Nearest Neighbors (KNN) algorithm! 🧠 Tech Stack: Python 🐍 scikit-learn OpenCV Streamlit (for the web app interface) 🎯 About the Project: This app takes your handwritten digit as input (drawn on canvas) and predicts the correct digit using a KNN classifier trained on the Digits dataset from scikit-learn. 🔗 Try it here: 👉 https://lnkd.in/gXpC8RWM GitHub repo: https://lnkd.in/gMc3z3GN A small step in exploring Machine Learning and Model Deployment! ✨ #MachineLearning #KNN #Streamlit #AI #DataScience #Python #MLProjects

🚀 Just launched my first Python package — coding-agent-python! 🐍 An AI-powered coding assistant that can generate, read, write, and even run Python code — all from a simple natural language command. Just type 👇 > coding-agent "make a file for writing the roots of quadratic equation" — powered by Gemini AI 🤖 (Add your GEMINI_API_KEY in the environment) 💡 It can even generate LeetCode solutions by giving inputs and outputs ! This was my first deep dive into Python packaging, learning the role of core files like __init__.py, pyproject.toml, LICENSE, mkdocs.yml, and README.md while exploring: 🧩 uv by Astral — for building & publishing 📘 mkdocs — for simple documentation 📦 PyPI — for sharing with the world 🌍 Open source is the best way to learn — contributions are welcome! 🔗 GitHub: https://lnkd.in/gju9xqXe 🔗 Docs: https://lnkd.in/gejgdf32 🔗 PyPI: https://lnkd.in/gvdkCSFb #Python #OpenSource #AI #Gemini #DevTools #PyPI #Astral #mkdocs #uv

🔹 Day 2 of 30 – LeetCode Challenge: Postorder Traversal of Binary Tree 🌲Today’s problem was about implementing Postorder Traversal of a binary tree — one of the most fundamental tree traversal techniques in Data Structures and Algorithms. 🧩 Problem: Return the postorder traversal (Left → Right → Root) of a given binary tree. Example: Input: root = [1, null, 2, 3] Output: [3, 2, 1] 💡 Approach: In Postorder Traversal, we: Visit Left Subtree Visit Right Subtree Visit Root Node I implemented both recursive and iterative approaches. The recursive version is simpler, while the iterative version helps understand how to simulate recursion using a stack. ⚙️ Complexity: Time Complexity: O(n) Space Complexity: O(h) 🏆 Result: ✅ All test cases passed 🚀 Runtime Efficiency: 100% 💬 Learning: This problem helped me deepen my understanding of recursion and stack-based traversal logic. Iterative postorder traversal is tricky but a great exercise to strengthen logical thinking in DSA. #LeetCode #Day2 #Python #DataStructures #BinaryTree #PostorderTraversal #Algorithms #Recursion #30DaysOfCode #MTech #CodingChallenge

Why I Use TypedDict Instead of a Regular Dictionary in LangGraph (and Python) When working with LangGraph, we often pass data between nodes — inputs, outputs, and intermediate states. At first glance, a plain dict seems fine: flexible, simple, and quick to write. But that flexibility comes at a cost — lack of structure. Here’s what happens when you use a normal dict: You might mistype a key name ("usre_id" instead of "user_id") — no warnings. You might forget which fields a node expects — no hints. You only find out about issues at runtime, not during development. That’s where TypedDict shines. 💡 Now your editor (and LangGraph’s type system) can: 1. Warn you about missing or extra fields 2. Autocomplete field names 3. Make refactoring much safer 4. Keep large graphs consistent as they grow In short — TypedDict makes your LangGraph pipelines self-documenting and type-safe, reducing bugs before they even happen. If your LangGraph is getting complex, switching to TypedDicts is one of those small changes that pay off big in the long run. #LangGraph #LangChain #Python #AI #SoftwareEngineering #AIEngineering #GenAI #CleanCode #DeveloperTips #LLM

Thrilled toExcited to share the backend for my "ChoosingGameAI" project! 🤖 I built a Python API with FastAPI ⚡ that uses LangChain and Gemini to generate "choose-your-own-adventure" stories from a single theme. Key tech wins: 🔹 Used FastAPI BackgroundTasks for async AI generation and SQLAlchemy to model and save the branching story data. 🔹 The best part: Forcing the AI to return clean, nested JSON using LangChain's PydanticOutputParser. This made data handling seamless! A great learning experience in building a modern, AI-powered backend. Check out the repo: https://lnkd.in/gKGXWd_U #Python #BackendDeveloper #FastAPI #LangChain #GenerativeAI #Gemini #AI #SQLAlchemy #Pydantic #Developer

Building My Foundation in Python for AI In my recent Agentic AI class with Sir Syed Shah Meer Ali we dove deep into the fundamentals of Python programming — the core skill every AI developer needs. Topics Covered: Python Syntax, Statements, and Indentation Google Colab (Online IDE) & .ipynb notebooks Data Types → Strings, Integers, Floats Output, Type Checking & Casting Variable Assignment & Naming Conventions Writing Styles: camelCase | PascalCase | snake_case Variable Scope (Local vs Global) Hoisting Concepts in Variables & Functions Data Structures → Lists, Tuples, Sets, Dictionaries Each topic helped me understand how data flows and behaves inside Python, building a stronger base for upcoming Agentic AI projects. Excited for the next session — moving closer to building intelligent AI agents! #AgenticAI #Python #AI #LearningJourney #TechSkills #ArtificialIntelligence #ContinuousLearning #PythonProgramming #FutureOfWork

https://lnkd.in/gNPXYZm2 Python + AI series, we're diving into the hottest technology of 2025: MCP, Model Context Protocol. This open protocol makes it easy to extend AI agents and chatbots with custom functionality, to make them more powerful and flexible. how to use the Python FastMCP SDK to build an MCP server running locally and consume that server from chatbots like GitHub Copilot. Then we'll build our own MCP client to consume the server. Finally, we'll discover how easy it is to point AI agent frameworks like Langgraph and Microsoft agent-framework at MCP servers.