Python

Hi everyone (if someone’s there). Extracting text from images has never been easier, thanks to advanced AI models like Llama 3.2 Vision. In this guide, we’ll walk through building a simple yet powerful OCR (Optical Character Recognition) tool using Python, Streamlit, and Ollama’s AI models. Why Use Llama 3.2 Vision for OCR? Unlike traditional OCR methods, which rely on predefined character recognition techniques, Llama 3.2 Vision leverages AI to not only extract text but also present it in a structured and readable format....

Hi everyone (if someone’s there). There’s something magical about teaching computers to understand not just our words, but our intent. I recently made a chatbot with Google’s Gemini 2.0 Flash model - and the best part? You can create it too. Let me walk you through this project that blend cutting-edge AI with practical applications. 1. The Spreadsheet Whisperer Behind the Curtain This chatbot project came from a simple question: “Why can’t I just make a chatbot to ask questions about any sort of data I give it and ask questions about it?...

Hi everyone (if someone’s there). In today’s data-driven world, Excel spreadsheets remain the workhorse of business analytics. But what if you could chat with your financial reports or sales data like you’d converse with a colleague? In this post, we’ll explore how I built a completely local AI assistant that understands Excel files using cutting-edge open-source tools. The Tech Stack Breakdown This program combines several powerful technologies= Ollama for running the Llama3....

Hi everyone (if someone’s there). In this post, I’ll walk you through the core components of a smart data analysis platform built with Streamlit, Groq API, and PandasAI. Instead of overwhelming you with one huge block of code, I’ll break the project into smaller, digestible chunks. This approach makes it easier to understand how each part works and how they all come together to create an interactive, AI-powered data exploration tool....

Hi everyone (if someone’s there). In the evolving landscape of AI-powered content creation, this news generator represents a significant leap forward. By combining CrewAI’s multi-agent framework with Cohere’s powerful Command R7B language model, the system automates the entire process of researching and writing comprehensive articles on any given topic. Let’s explore how this innovative application works and how you can implement it yourself. How the System Works The application follows a sophisticated two-stage process that mimics human journalistic workflows....

Hello everyone (if someone’s there). This project 🦙 Llama OCR - Image Text Extraction Tool was made to show you how to run Llama 3.2 Vision Model on your own computer. For more information on the working of this project and how to run this program on your local machine, read this blog

Hello everyone (if someone’s there). This project Gemini Flash 2.0 MultiModal Chatbot was made to check how this new model by Google works. Nothing serious. For more information on the working of this project and how to run this program on your local machine, read this blog

Hello everyone (if someone’s there). This project, RAG over Excel with IBM Dockling and Llama 3.2, was made to help you extract details from an Excel file using some of the best technologies that IBM and Meta made, namely, respectively, Docling and Llama 3.2 Model on your own computer. For more information on the workings of this project and how to run this program on your local machine, read this blog

Hello everyone (if someone’s there). This project, MarkAI RAG, was made using GROQ API, Microsoft MarkItDown and PandasAI for smart document querying (RAG) on your own computer. For more information on the working of this project and how to run this program on your local machine, read this blog

Hello everyone (if someone’s there). This project, AI NEWS GENERATOR, will help you generate amazing and comprehensive news and/or blog posts using multiple Large Language Models. For more information on the working of this project and how to run this program on your local machine, read this blog