Update app.py

app.py

@@ -4,6 +4,8 @@ import pandas as pd
 import gradio as gr
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
+import os
+from groq import Groq
 import creds  # Assuming creds.py holds your API key as creds.api_key
 
 # Step 1: Scrape the free courses from Analytics Vidhya
@@ -36,40 +38,42 @@ for course_card in soup.find_all('header', class_='course-card__img-container'):
 # Step 2: Create DataFrame
 df = pd.DataFrame(courses)
 
-# Step 3: Text Processing for Improved Relevance
-def preprocess_text(text):
-    text = text.lower()
-    text = text.replace("-", " ")
-    return text
+# Step 3: Initialize the Groq client and set the API key
+client = Groq(api_key=creds.api_key)
 
-df['processed_title'] = df['title'].apply(preprocess_text)
+def search_courses(query):
+    try:
+        # Step 4: Preprocessing query and course titles for TF-IDF
+        course_titles = df['title'].tolist()
+        course_titles.append(query)  # Add the query to the list of titles
 
-# Step 4: Generate TF-IDF Vectors for Titles
-vectorizer = TfidfVectorizer(stop_words='english')
-tfidf_matrix = vectorizer.fit_transform(df['processed_title'])
+        # Using TF-IDF to vectorize the course titles and query
+        tfidf_vectorizer = TfidfVectorizer(stop_words='english')
+        tfidf_matrix = tfidf_vectorizer.fit_transform(course_titles)
 
-def search_courses(query):
-    # Process query and generate its TF-IDF vector
-    processed_query = preprocess_text(query)
-    query_vector = vectorizer.transform([processed_query])
-    
-    # Calculate cosine similarity
-    similarities = cosine_similarity(query_vector, tfidf_matrix).flatten()
-    df['relevance_score'] = similarities
-    
-    # Filter and sort courses based on relevance score
-    relevant_courses = df[df['relevance_score'] >= 0.3].sort_values(by='relevance_score', ascending=False)
-    results = []
-    
-    for _, course in relevant_courses.iterrows():
-        results.append({
-            'title': course['title'],
-            'image_url': course['image_url'],
-            'course_link': course['course_link'],
-            'score': course['relevance_score']
-        })
-    
-    return results[:10]
+        # Compute cosine similarity between the query and course titles
+        cosine_similarities = cosine_similarity(tfidf_matrix[-1:], tfidf_matrix[:-1]).flatten()
+
+        # Get the top 10 relevant courses based on cosine similarity
+        top_indices = cosine_similarities.argsort()[-10:][::-1]
+        
+        # Step 5: Build results
+        results = []
+        for index in top_indices:
+            relevance = cosine_similarities[index]
+            if relevance >= 0.5:  # Only consider courses with at least 50% relevance
+                course = df.iloc[index]
+                results.append({
+                    'title': course['title'],
+                    'image_url': course['image_url'],
+                    'course_link': course['course_link'],
+                    'score': round(relevance * 100, 2)  # Show relevance as percentage
+                })
+        
+        return results if results else []
+
+    except Exception as e:
+        return []
 
 def gradio_search(query):
     result_list = search_courses(query)
@@ -80,7 +84,7 @@ def gradio_search(query):
             course_title = item['title']
             course_image = item['image_url']
             course_link = item['course_link']
-            relevance_score = round(item['score'] * 100, 2)
+            relevance_score = item['score']
             
             html_output += f'''
             <div class="course-card">
@@ -100,8 +104,8 @@ def gradio_search(query):
 custom_css = """
 body {
     font-family: Arial, sans-serif;
-    background-color: #121212;
-    color: #E0E0E0;
+    background-color: #121212;  /* Dark background */
+    color: #E0E0E0;  /* Light text color for dark background */
 }
 .container {
     max-width: 800px;
@@ -115,7 +119,7 @@ body {
     justify-content: space-between;
 }
 .course-card {
-    background-color: #1E1E1E;
+    background-color: #1E1E1E;  /* Darker card background */
     border-radius: 8px;
     box-shadow: 0 2px 4px rgba(0, 0, 0, 0.5);
     margin-bottom: 20px;
@@ -137,10 +141,10 @@ body {
 .course-info h3 {
     margin-top: 0;
     font-size: 18px;
-    color: #E0E0E0;
+    color: #E0E0E0;  /* Light text color */
 }
 .course-info p {
-    color: #B0B0B0;
+    color: #B0B0B0;  /* Slightly darker text color for contrast */
     font-size: 14px;
     margin-bottom: 10px;
 }
@@ -173,11 +177,10 @@ iface = gr.Interface(
     description="Find the most relevant courses from Analytics Vidhya based on your query.",
     theme="huggingface",
     css=custom_css,
-    examples=[
-        ["machine learning for beginners"],
-        ["advanced data visualization techniques"],
-        ["python programming basics"], 
-        ["Business Analytics"]
+    examples=[["machine learning for beginners"],
+              ["advanced data visualization techniques"],
+              ["python programming basics"], 
+              ["Business Analytics"]
     ],
 )