Posts

Building an AI-Powered Search Engine Using LangChain and Agents

The rise of Generative AI has transformed how we interact with information. Large Language Models (LLMs) like Llama3-8b-8192 can process complex queries, but they lack real-time search capabilities. To address this, I built an AI-powered search engine using LangChain Agents , integrating Wikipedia, Arxiv, and DuckDuckGo search tools to provide real-time, context-aware responses . This project not only improves search accuracy but also showcases the power of Retrieval-Augmented Generation (RAG) —a technique that enhances LLMs by fetching live information before generating responses. 💡 How This Search Engine Works 🔹 Core Components Used This project integrates multiple AI and search technologies: Component Purpose LangChain Framework to build AI applications with LLMs Streamlit Web interface for interactive AI search DuckDuckGo API Fetches real-time web results Wikipedia API Retrieves encyclopedic knowledge Arxiv API Fetches academic research pap...
Post a Comment
Read more

Building detecting SMS Spam Using Text Classification Project

  In today’s world, spam messages flood our inboxes, making it difficult to distinguish between important and irrelevant texts. Companies often lose customers because they can't properly filter spam, which frustrates users. What if we could build a system that automatically identifies spam messages and flags them? This project solves that problem by building an SMS Spam Classifier that uses Natural Language Processing (NLP) techniques to automatically label SMS messages as spam or ham (not spam). Solution: Text Classification Using Bag of Words To solve this problem, we’ll break down the solution into several key steps: Data Preprocessing : We’ll clean the text data by converting everything to lowercase, removing unnecessary characters, and applying stopwords filtering (to remove common English words that don’t add much meaning, like “the”, “is”, “in”). Stemming will be used to reduce words to their root forms (e.g., "running" becomes "run"). Bag of Words M...
Post a Comment
Read more

Heart Failure Outcome Prediction: A Machine Learning Approach

 Introduction Heart disease is one of the leading causes of death worldwide, and heart failure (HF) is a critical condition that often leads to fatal outcomes if not managed properly. Early detection and preventive measures can significantly reduce the risk of heart failure-related complications. With the advancement of machine learning (ML), we can now use patient data to predict heart failure outcomes, helping healthcare providers make better decisions and improve patient care. In this project, I have developed a **Heart Failure Outcome Prediction** model using machine learning algorithms to predict whether a patient is at risk of heart failure based on key factors like age, blood pressure, cholesterol levels, and other medical data. Let me walk you through the process step by step. You can find the full project on my [GitHub repository]: Hearth-failure-outcome-prediction/Hearth_failure_outcome_prediction.ipynb at main · Faraz6180/Hearth-failure-outcome-prediction (github.com) --...
Post a Comment
Read more

Building an Iris Flower Classification App with Streamlit and Random Forest

In this project, we dive into creating a **machine learning web app** using **Streamlit** and the **Random Forest Classifier** to predict the species of an Iris flower. Streamlit is a Python library that makes it super easy to build interactive web applications without needing a lot of front-end development skills. We combined that with the power of machine learning to deliver a functional, real-time classification tool. ### Overview of the Project The **Iris dataset**, one of the most famous in the world of machine learning, contains three types of Iris flowers: - Iris Setosa - Iris Versicolor - Iris Virginica Each flower is described by four features: 1. **Sepal length** 2. **Sepal width** 3. **Petal length** 4. **Petal width** Using these features, we built an app that allows users to input the values of these features through a simple web interface and predict which type of Iris flower it is. ### Key Technologies 1. **Streamlit**: This library simplifies the creation of interactive...
Post a Comment
Read more