App added

app.py

@@ -0,0 +1,140 @@
+import re
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import streamlit as st
+from groq import Groq
+import os
+from dotenv import load_dotenv
+
+# Step 1: Scrape the free courses from Analytics Vidhya
+url = "https://courses.analyticsvidhya.com/pages/all-free-courses"
+response = requests.get(url)
+soup = BeautifulSoup(response.content, 'html.parser')
+
+courses = []
+
+# Extracting course title, image, and course link
+for course_card in soup.find_all('header', class_='course-card__img-container'):
+    img_tag = course_card.find('img', class_='course-card__img')
+    
+    if img_tag:
+        title = img_tag.get('alt')
+        image_url = img_tag.get('src')
+        
+        link_tag = course_card.find_previous('a')
+        if link_tag:
+            course_link = link_tag.get('href')
+            if not course_link.startswith('http'):
+                course_link = 'https://courses.analyticsvidhya.com' + course_link
+
+            courses.append({
+                'title': title,
+                'image_url': image_url,
+                'course_link': course_link
+            })
+
+# Step 2: Create DataFrame
+df = pd.DataFrame(courses)
+
+load_dotenv()
+client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+
+def search_courses(query):
+    try:
+        # Prepare the prompt for Groq
+        prompt = f"""Given the following query: "{query}"
+        Please analyze the query and rank the following courses based on their relevance to the query. 
+        Prioritize courses from Analytics Vidhya. Provide a relevance score from 0 to 1 for each course.
+        Only return courses with a relevance score of 0.5 or higher.
+        Return the results in the following format:
+        Title: [Course Title]
+        Relevance: [Score]
+        
+        Courses:
+        {df['title'].to_string(index=False)}
+        """
+
+        # Get response from Groq
+        response = client.chat.completions.create(
+            model="llama-3.2-1b-preview",
+            messages=[
+                {"role": "system", "content": "You are an AI assistant specialized in course recommendations."},
+                {"role": "user", "content": prompt}
+            ],
+            temperature=0.2,
+            max_tokens=1000
+        )
+
+        # Parse Groq's response
+        results = []
+        matches = re.findall(r'\*\*(.+?)\*\*\s*\(Relevance Score: (0\.\d+)\)', response.choices[0].message.content)
+        
+        for title, score in matches:
+            title = title.strip()
+            score = float(score)
+            if score >= 0.5:
+                matching_courses = df[df['title'].str.contains(title[:30], case=False, na=False)]
+                if not matching_courses.empty:
+                    course = matching_courses.iloc[0]
+                    results.append({
+                        'title': course['title'],  # Use the full title from the database
+                        'image_url': course['image_url'],
+                        'course_link': course['course_link'],
+                        'score': score
+                    })
+        return sorted(results, key=lambda x: x['score'], reverse=True)[:10]  # Return top 10 results
+
+    except Exception as e:
+        st.error(f"An error occurred in search_courses: {str(e)}")
+        return []
+
+def display_search_results(result_list):
+    if result_list:
+        for item in result_list:
+            course_title = item['title']
+            course_image = item['image_url']
+            course_link = item['course_link']
+            relevance_score = round(item['score'] * 100, 2)
+
+            st.image(course_image, use_column_width=True)
+            st.write(f"### {course_title}")
+            st.write(f"Relevance: {relevance_score}%")
+            st.markdown(f"[View Course]({course_link})", unsafe_allow_html=True)
+    else:
+        st.write("No results found. Please try a different query.")
+
+#Streamlit UI
+
+st.title("Analytics Vidhya Free Courses🔍")
+st.image("original.png")
+st.markdown("#### 🔍🌐 Get the most appropriate course as per your learning requirement.")
+st.markdown("<hr style='border:1px solid #eee;'>", unsafe_allow_html=True)
+
+query = st.text_input(
+    "Enter course related keywords...", 
+    placeholder="e.g., machine learning, data science, python",
+    help="Type in a keyword to find related free courses"
+)
+
+search_button = st.button("Search")
+
+# Search results section
+if search_button and query:
+    st.write("Collecting courses......")
+    result_list = search_courses(query)
+    
+    # Display search results if available
+    if result_list:
+        st.markdown(f"### Top results for: {query}")
+        display_search_results(result_list)
+    else:
+        st.write("No results found. Please try a different keyword.")
+else:
+    st.write("Please enter a search query to find relevant courses.")
+
+# Footer with subtle text
+st.markdown(
+    "<p style='text-align:center; color:grey;'>Made by @metechmohit </p>",
+    unsafe_allow_html=True
+)

requirements.txt

@@ -0,0 +1,7 @@
+streamlit==1.39.0
+requests==2.32.3
+pandas==2.2.3
+beautifulsoup4==4.12.3
+groq==0.11.0
+python-dotenv
+#gradio==4.44.1