Update app.py

app.py

@@ -4,82 +4,67 @@ import pandas as pd
 import gradio as gr
 import os
 from groq import Groq
-import creds  # Assuming creds.py holds your API key as creds.api_key
+import creds  # Ensure creds.py contains `api_key` as `creds.api_key`
 
-# 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')
+# Step 1: Scrape free courses from Analytics Vidhya
+def scrape_courses():
+    url = "https://courses.analyticsvidhya.com/pages/all-free-courses"
+    response = requests.get(url)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    courses = []
 
-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')
+    for course_card in soup.find_all('header', class_='course-card__img-container'):
+        img_tag = course_card.find('img', class_='course-card__img')
         
-        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
+        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
-            })
+                courses.append({
+                    'title': title,
+                    'image_url': image_url,
+                    'course_link': course_link
+                })
 
-# Step 2: Create DataFrame
-df = pd.DataFrame(courses)
+    return pd.DataFrame(courses)
 
-# Step 3: Initialize the Groq client and set the API key
-client = Groq(api_key=creds.api_key)  # Properly passing the API key
+# Initialize course DataFrame
+df = scrape_courses()
+
+# Step 2: Initialize the Groq client and set the API key
+client = Groq(api_key=creds.api_key)
 
 def search_courses(query):
     try:
         print(f"Searching for: {query}")
-        print(f"Number of courses in database: {len(df)}")
-
-        # 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]
+        prompt = f"""Given the query: "{query}"
+        Rank the following courses based on relevance to the query, prioritizing Analytics Vidhya courses.
+        Provide a relevance score (0-1) for each course, returning only those with a score >= 0.5.
         
         Courses:
         {df['title'].to_string(index=False)}
         """
 
-        print("Sending request to Groq...")
-        # Get response from Groq
         response = client.chat.completions.create(
-            model="mixtral-8x7b-32768",  # Use the appropriate model
+            model="mixtral-8x7b-32768",
             messages=[{"role": "system", "content": "You are an AI assistant specialized in course recommendations."},
                       {"role": "user", "content": prompt}],
             temperature=0.2,
             max_tokens=1000
         )
-        print("Received response from Groq")
 
-        # Parse Groq's response
         results = []
-        print("Groq response content:")
-        print(response.choices[0].message.content)
-        
         for line in response.choices[0].message.content.split('\n'):
             if line.startswith('Title:'):
                 title = line.split('Title:')[1].strip()
-                print(f"Found title: {title}")
             elif line.startswith('Relevance:'):
                 relevance = float(line.split('Relevance:')[1].strip())
-                print(f"Relevance for {title}: {relevance}")
                 if relevance >= 0.5:
                     matching_courses = df[df['title'] == title]
                     if not matching_courses.empty:
@@ -90,11 +75,7 @@ def search_courses(query):
                             'course_link': course['course_link'],
                             'score': relevance
                         })
-                        print(f"Added course: {title}")
-                    else:
-                        print(f"Warning: Course not found in database: {title}")
 
-        print(f"Number of results found: {len(results)}")
         return sorted(results, key=lambda x: x['score'], reverse=True)[:10]  # Return top 10 results
 
     except Exception as e:
@@ -128,71 +109,19 @@ def gradio_search(query):
 
 # Custom CSS for the Gradio interface
 custom_css = """
-body {
-    font-family: Arial, sans-serif;
-    background-color: #f0f2f5;
-}
-h1, h2, p, .container .examples {
-    color: #333;  /* Darker color for better visibility */
-}
-.container {
-    max-width: 800px;
-    margin: 0 auto;
-    padding: 20px;
-}
-.results-container {
-    display: flex;
-    flex-wrap: wrap;
-    justify-content: space-between;
-}
-.course-card {
-    background-color: white;
-    border-radius: 8px;
-    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
-    margin-bottom: 20px;
-    overflow: hidden;
-    width: 48%;
-    transition: transform 0.2s;
-}
-.course-card:hover {
-    transform: translateY(-5px);
-}
-.course-image {
-    width: 100%;
-    height: 150px;
-    object-fit: cover;
-}
-.course-info {
-    padding: 15px;
-}
-.course-info h3 {
-    margin-top: 0;
-    font-size: 18px;
-    color: #333;
-}
-.course-info p {
-    color: #666;
-    font-size: 14px;
-    margin-bottom: 10px;
-}
-.course-link {
-    display: inline-block;
-    background-color: #007bff;
-    color: white;
-    padding: 8px 12px;
-    text-decoration: none;
-    border-radius: 4px;
-    font-size: 14px;
-    transition: background-color 0.2s;
-}
-.course-link:hover {
-    background-color: #0056b3;
-}
-.no-results {
-    text-align: center;
-    color: #666;
-    font-style: italic;
-}
+body { font-family: Arial, sans-serif; background-color: #f0f2f5; }
+h1, h2, p, .container .examples { color: #333; }
+.container { max-width: 800px; margin: 0 auto; padding: 20px; }
+.results-container { display: flex; flex-wrap: wrap; justify-content: space-between; }
+.course-card { background-color: white; border-radius: 8px; box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1); margin-bottom: 20px; overflow: hidden; width: 48%; transition: transform 0.2s; }
+.course-card:hover { transform: translateY(-5px); }
+.course-image { width: 100%; height: 150px; object-fit: cover; }
+.course-info { padding: 15px; }
+.course-info h3 { margin-top: 0; font-size: 18px; color: #333; }
+.course-info p { color: #666; font-size: 14px; margin-bottom: 10px; }
+.course-link { display: inline-block; background-color: #007bff; color: white; padding: 8px 12px; text-decoration: none; border-radius: 4px; font-size: 14px; transition: background-color 0.2s; }
+.course-link:hover { background-color: #0056b3; }
+.no-results { text-align: center; color: #666; font-style: italic; }
 """
 
 # Gradio interface