Python Voice Assistant Built with Flask

🚀 Regex Checker Web Application using Flask Developed a dynamic web application that allows users to input a test string and a regular expression, then instantly displays all matching substrings. This project deepened my expertise in Flask form handling, template rendering. It provided valuable hands-on experience in building interactive, user-friendly web applications with real-time data processing — enhancing both my backend and frontend development skills. github: https://lnkd.in/gRjPRYZn Innomatics Research Labs #Flask #Python #WebDevelopment #Regex #BackendDevelopment #FullStack #Programming #Debugging #Coding #TechProjects

Built a browser-based AI assistant that can execute both Python and JavaScript code directly in the browser - no server required. Key features: 🐍 Python with pandas & matplotlib - Full data analysis capabilities powered by Pyodide (Python compiled to WebAssembly) 📊 Inline chart rendering - Visualizations display directly in the chat 💾 Persistent sessions - Variables persist between executions for iterative analysis ⚡ Auto language selection - AI chooses Python for data/CSV tasks, JavaScript for simple calculations 🔄 Re-run & Edit - Modify and re-execute code blocks with one click ⏱️ Timeout protection - 60s execution limit prevents runaway code Tech stack: Pyodide (Python WASM), Boa Engine (JS sandbox), Web Workers for non-blocking execution Upload a CSV, ask a question, and watch it write & execute code to analyze your data - all running locally in your browser. #AIAgent #AITools #ModelContextProtocol #MCP #Python #JavaScript #WebAssembly #DataAnalysis #Pyodide

Bridging Flutter & Flask: Building a Full-Stack Regex Engine I’m thrilled to share my latest project—a Regex Matching Web App that combines a sleek Flutter UI with a powerful Flask backend. Inspired by Regex101, this project was a deep dive into building a seamless communication bridge between a cross-platform frontend and Python’s robust logic. 🛠️ The Tech Stack: Frontend (Flutter): Crafted a responsive, intuitive UI to handle user inputs and display matches dynamically. Backend (Flask): Built a RESTful logic layer to process regular expressions using Python’s re module. The Bridge: Managed the data flow between the two to ensure real-time feedback and instant pattern validation. Key Features: 🔹 Dynamic match highlighting 🔹 Robust error handling for invalid regex patterns 🔹 Clean, modular architecture Special thanks to Innomatics Research Labs for the guidance and the opportunity to sharpen my full-stack skills! github link -> https://lnkd.in/gQ7fpggM #FullStack #Flutter #Flask #Python #WebDevelopment #Regex #InnomaticsResearchLabs

I’ve been spending some personal time exploring the ETABS API and building a small standalone UI using Python to see how structural analysis models can be inspected and interacted with programmatically. The goal isn’t to replace ETABS, but to treat the model as a data source that can be queried, filtered, and visualized outside the native interface. Shown here: API-based extraction of framing elements, interactive visualization, and early section-level inspection hooks. Still very much a work in progress, but a useful exploration of more transparent, extensible structural workflows. (Demonstration uses generic models and independently written code.) #StructuralEngineering #ETABS #Python #API

JavaScript’s monopoly on the Edge is officially over. For years, if you wanted true speed at the edge, you were effectively forced to use JavaScript. Trying to run Python? You were usually hit with painful cold starts that killed the user experience. But WebAssembly (WASM) just flipped the script. New serverless platforms are now leveraging WASM to offer Python first-class support. This opens a massive door for developers: • Access the rich Python ecosystem (Data Science & AI) • Deploy complex logic directly at the edge • Achieve near-instant startup times We break down how this architecture works and what it means for your stack in today's daily audio newsletter. Grab the full breakdown (and the script) at the link in the comments. 👇 #webassembly #EdgeComputing #serverless #Python

🛍️ E-commerce Recommendation System with Matrix Factorization I just built a product recommendation system using Python and Streamlit! Instead of simple filters, this app uses Matrix Factorization (SVD) to understand hidden patterns in product data like price, gender, and ratings to suggest the most relevant items. Key Tech: 🔹 Algorithm: Truncated SVD (Matrix Factorization) 🔹 Similarity: Cosine Similarity for precise matching 🔹 Frontend: Streamlit for an interactive UI github : https://lnkd.in/gSYuiKDX #Python #MachineLearning #SVD #DataScience #Streamlit #AI

Harnessing Python to perform web searches is unlocking new possibilities in data gathering and automation. By combining powerful libraries like DDGS and httpx, we can seamlessly search, fetch, and process web content programmatically. 🔍 Mastering these tools not only streamlines research but also empowers developers to build tailored search solutions that efficiently parse and rank information. The future of intelligent data retrieval lies in integrating smart algorithms with flexible coding frameworks. The key? A blend of creativity, technical skill, and the drive to innovate. Let’s keep pushing the boundaries of what’s possible with Python. 🚀 #PythonDevelopment #WebSearch #DataAutomation #TechInnovation #Coding #AI

Build QnA Chatbot using Python, Langchain, Gemini, Streamlit GenAI - Prompt Engineering, LLM's with LangChain - Building Q&A Chatbot with LangChain - String Parser, Chaining, Custom Functions, LLMs - Static vs Dynamic Prompts - ChatPromptTemplate - How can i generate o/p without using content & using functions how we generate output ? - Introduced LangChain - Gemini API - stored messages in session state, local Storage - streamlit backend memory - streamlit to run website / web interface UI,UX - .env file - activated virtual env #Python #LangChain #Gemini #Streamlit #GenAI #LLMs

Built a Personality Predictor Web App as an ML project. It predicts whether a person is Introvert, Extrovert, or Ambivert using a Logistic Regression algorithm. 🔹 Features: Normal prediction mode Detailed personality prediction Simple UI Built using HTML, CSS, JavaScript + Machine Learning Deployed as a web application 🔹 Tech Stack: Python | Sklearn | HTML | CSS | JavaScript Live Demo: 👉 https://lnkd.in/gqtY278s This project helped me understand the practical side of ML model integration with web development, model deployment, and user interaction design. #MachineLearning #WebDevelopment #LogisticRegression #Python #MLProject