Update README.md

README.md

@@ -11,54 +11,70 @@ license: mit
 short_description: LLM based search tool for free courses on Analytics Vidhya
 ---
 
-# 📚 Analytics Vidhya Smart Search Tool
+# 📚 Analytics Vidhya Free Courses Search App
 
-This project uses a **Large Language Model (LLM)** to help users find the most relevant free courses on Analytics Vidhya’s platform. Powered by **Groq's LLM**, the tool intelligently processes user queries and ranks courses by relevance, ensuring an advanced and intuitive search experience.
+This project is a **Streamlit-based web application** designed to help users find the most relevant free courses on Analytics Vidhya’s platform. Using **Hugging Face’s `all-MiniLM-L6-v2`** for embeddings and **FAISS** for fast similarity search, the tool provides an efficient and intuitive search experience.
 
 ## 🌟 Key Features
 
-- **Smart LLM-Powered Search**: Queries are processed by Groq's LLM to deliver relevant courses based on user input.
-- **Real-time Course Data**: The app scrapes and updates data directly from Analytics Vidhya's free courses page.
-- **Ranked Recommendations**: Each course is scored for relevance, with only the most relevant results displayed.
-- **Streamlit UI**: Built with Streamlit for a clean and user-friendly interface.
-- **Deployed on Hugging Face**: Accessible via Hugging Face Spaces for easy use and sharing.
+- **Embeddings for Smart Search**: Course titles are converted into embeddings using Hugging Face’s `all-MiniLM-L6-v2` model, enabling accurate matching with user queries.
+- **Real-time Course Data**: The app scrapes and updates course data directly from Analytics Vidhya's free courses page.
+- **Ranked Recommendations**: Each course is ranked based on its relevance to the user query, displaying only the top results.
+- **User-Friendly Interface**: Built with Streamlit, the app offers a clean and intuitive interface for easy navigation.
+- **Fast Similarity Search**: Uses FAISS to quickly retrieve the top relevant courses based on query embeddings.
 
 ## 🧠 How It Works
 
 1. **Web Scraping**: The tool scrapes course titles, images, and URLs from Analytics Vidhya.
-2. **LLM-Driven Search**: Groq's LLM analyzes the user query and ranks the courses based on relevance.
-3. **Results Display**: Top results are shown with course titles, images, and relevance scores.
+2. **Embedding Generation**: Course titles are transformed into embeddings using the `all-MiniLM-L6-v2` model from Hugging Face.
+3. **Similarity Search**: FAISS is employed to efficiently search for the closest matches to the user’s query embedding.
+4. **Results Display**: The top 10 relevant courses are displayed with their titles, images, and relevance scores.
 
 ## 🚀 Technologies
 
 - **Python**: Backend processing.
-- **Streamlit**: UI framework.
-- **BeautifulSoup**: For web scraping.
-- **Groq LLM**: Powering smart search.
-- **Pandas**: Data management.
-- **Hugging Face Spaces**: Deployment.
+- **Streamlit**: UI framework for building the web application.
+- **BeautifulSoup**: For web scraping to gather course data.
+- **Hugging Face Transformers**: For generating embeddings using the `all-MiniLM-L6-v2` model.
+- **FAISS**: For fast similarity search across course embeddings.
+- **Pandas**: For data management and manipulation.
 
-## 🛠️ How to Run
 
-1. Clone the repo:
+## 💡 Usage
+
+1. **Scraping Course Data**: The app will scrape all free courses from Analytics Vidhya. If the `scraped.csv` file doesn’t exist, it will automatically scrape and save the data.
+2. **Search for Courses**: Users can enter keywords related to their desired courses and press the **Search** button. The app will return the top 10 most relevant courses based on their query.
+3. **View Results**: Each result will display the course title, image, relevance score, and a link to the course page.
+
+## 🛠️ Future Improvements
+
+- **Enhanced Filtering Options**: Add filters for difficulty level, course duration, etc.
+- **User Feedback**: Implement a mechanism for users to rate the relevance of displayed courses.
+- **Dynamic Scraping**: Optimize the scraping process to handle changes in course listings.
+
+
+## 📥 Installation and Setup
+
+1. **Clone the Repository**
    ```bash
    git clone https://huggingface.co/spaces/metechmohit/Smart_Search_LLM
-   cd /Smart_Search_LLM
+   cd\Smart_Search_LLM
    ```
 
-2. Install dependencies:
+2. **Set Up Virtual Environment**
    ```bash
-   pip install -r requirements.txt
+   python -m venv myenv
+   source myenv/bin/activate   # On Windows, use myenv\Scripts\activate
    ```
 
-3. Add your **Groq API key** to a `.env` file:
-   ```
-   GROQ_API_KEY=your-groq-api-key
+3. **Install Dependencies**
+   ```bash
+   pip install -r requirements.txt
    ```
 
-4. Run the app:
+4. **Run the Application**
    ```bash
-   streamlit run streamlit_app.py
+   streamlit run app.py
    ```
 
 ## 🌐 Deployed Version