Upload 5 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY = "AIzaSyDuDsrNUG3OnOawsxaop-pYEjXFlCXUfws"

app.py

@@ -0,0 +1,78 @@
+import os
+import requests
+from bs4 import BeautifulSoup
+import sqlite3
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+
+# Database setup
+def create_database():
+    conn = sqlite3.connect('courses.db')
+    c = conn.cursor()
+    # Create table with an additional column 'price' to indicate free or paid
+    c.execute('''CREATE TABLE IF NOT EXISTS courses
+                 (id INTEGER PRIMARY KEY, title TEXT, description TEXT, price TEXT)''')
+    conn.commit()
+    conn.close()
+
+
+# Web scraping function to get course data from a specific page
+def scrape_courses_from_page(page_number):
+    url = f"https://courses.analyticsvidhya.com/collections/courses?page={page_number}"
+    response = requests.get(url)
+    soup = BeautifulSoup(response.text, 'html.parser')
+
+    courses = []
+
+    # Find all course items from the products__list
+    course_items = soup.find_all('li', class_='products__list-item')
+
+    for course_item in course_items:
+        # Extract the course title
+        title_tag = course_item.find('h3')
+        title = title_tag.text.strip() if title_tag else 'No title available'
+
+        # Extract course price
+        price_tag = course_item.find('span', class_='course-card__price')
+        price = price_tag.text.strip() if price_tag else "Price not available"
+
+        # Description is not always explicitly provided, using course body for more details
+        description_tag = course_item.find('h4')
+        description = description_tag.text.strip() if description_tag else 'No description available'
+
+        # Append course details (title, description, price)
+        courses.append((title, description, price))
+
+    return courses
+
+
+# Scrape all pages (total 8 pages) and insert data into the database
+def scrape_all_pages():
+    all_courses = []
+
+    # Loop through pages 1 to 8
+    for page in range(1, 9):
+        print(f"Scraping page {page}...")
+        courses = scrape_courses_from_page(page)
+        all_courses.extend(courses)
+
+    return all_courses
+
+
+# Insert scraped data into the database
+def insert_data_to_db(courses):
+    conn = sqlite3.connect('courses.db')
+    c = conn.cursor()
+    c.executemany('INSERT INTO courses (title, description, price) VALUES (?, ?, ?)', courses)
+    conn.commit()
+    conn.close()
+
+
+if __name__ == "__main__":
+    create_database()
+    all_courses = scrape_all_pages()
+    insert_data_to_db(all_courses)
+    print(f"Data from all pages has been successfully scraped and inserted into the database.")

main.py

@@ -0,0 +1,76 @@
+import os
+import sqlite3
+import streamlit as st
+import google.generativeai as genai
+from dotenv import load_dotenv
+
+# Load environment variables from .env
+load_dotenv()
+
+# Set up the Google API key for Gemini
+api_key = os.getenv("GOOGLE_API_KEY")
+if api_key is None:
+    st.error("GOOGLE_API_KEY not found in environment variables. Please check your .env file.")
+else:
+    # Configure Google Generative AI API
+    genai.configure(api_key=api_key)
+
+
+# Function to fetch all courses from the SQLite database
+def fetch_all_courses():
+    conn = sqlite3.connect('courses.db')
+    cur = conn.cursor()
+    cur.execute("SELECT title, description, price FROM courses")
+    rows = cur.fetchall()
+    conn.close()
+    return rows
+
+
+# Function to generate a response using Google Generative AI based on user prompt and available courses
+def generate_response(prompt, courses):
+    try:
+        # Prepare a detailed context prompt for the LLM
+        course_details = "\n".join(
+            [f"Title: {course[0]}, Description: {course[1]}, Price: {course[2]}" for course in courses])
+
+        genai_prompt = f"""
+        You are an expert assistant tasked with finding relevant courses based on user queries. 
+        Below are details of available courses:
+
+        {course_details}
+
+        Based on this information, respond to the user's query in the most relevant way:
+        {prompt}
+        """
+
+        # Generate a response using Google Generative AI
+        model = genai.GenerativeModel('gemini-pro')
+        response = model.generate_content([genai_prompt, prompt])
+        return response.text.strip()  # Return the natural language response
+    except Exception as e:
+        st.error(f"Error generating a response: {e}")
+        return None
+
+
+# Streamlit interface
+st.set_page_config(page_title="Smart Search for Courses")
+st.header("Find Relevant Courses on Analytics Vidhya")
+
+# User prompt input
+user_query = st.text_input("Enter your search query (e.g., 'Show me all free courses on machine learning'):")
+
+submit = st.button("Search")
+
+# Fetch all courses from the database
+courses = fetch_all_courses()
+
+# If user submits the query
+if submit and user_query:
+    # Generate a response from Google Generative AI
+    response = generate_response(user_query, courses)
+
+    if response:
+        st.subheader("Search Results:")
+        st.write(response)
+    else:
+        st.write("Could not generate a response. Please try again.")

requirements.txt

@@ -0,0 +1,7 @@
+requests
+beautifulsoup4
+gradio
+streamlit
+sqlite3
+python-dotenv
+openai