Update app.py

app.py

@@ -3,83 +3,107 @@ from sentence_transformers import SentenceTransformer, util
 from transformers import pipeline
 import torch
 import gradio as gr
-import os
+import os 
 
-# Load the dataset
+# Use the relative path where the CSV is uploaded
 csv_file_path = os.path.join(os.getcwd(), 'Analytics_Vidhya_Free_Course_data.csv')
+
+# Load the dataset
 df = pd.read_csv(csv_file_path, encoding='Windows-1252')
-df.fillna('', inplace=True)
 
-# Load the pre-trained model for embeddings
+# Load the pre-trained model for embeddings (using SentenceTransformers)
 model = SentenceTransformer('multi-qa-mpnet-base-dot-v1')
 
 # Combine title and description to create a full text for each course
-df['full_text'] = df.iloc[:, 0] + " " + df.iloc[:, 1] + " " + df['Instructor Name'] + " " + df['Rating'].astype(str) + " " + df['Category']
+df['full_text'] = df.iloc[:,0] + " " + df.iloc[:,1] + " " + df['Instructor Name'] + " " + str(df['Rating']) + " " + df['Category']
 
 # Convert full course texts into embeddings
 course_embeddings = model.encode(df['full_text'].tolist(), convert_to_tensor=True)
 
-# Load a model for text generation (e.g., BART)
-generator = pipeline('text2text-generation', model='facebook/bart-large-cnn')
-
+# Function to expand the query using paraphrasing
 def expand_query(query):
     paraphraser = pipeline('text2text-generation', model='Vamsi/T5_Paraphrase_Paws')
     expanded_queries = paraphraser(query, num_return_sequences=3, max_length=50, do_sample=True)
     return [q['generated_text'] for q in expanded_queries]
 
-def generate_description(query):
-    response = generator(query, max_length=100, num_return_sequences=1)
-    return response[0]['generated_text']
-
+# Function to search for the most relevant courses
 def search_courses(query, level_filter=None, category_filter=None, top_k=3):
+    # Step 1: Expand the query using paraphrasing
     expanded_queries = expand_query(query)
+
+    # Step 2: Initialize an array to store all similarities
     all_similarities = []
 
     for expanded_query in expanded_queries:
+        # Convert each expanded query into an embedding
         query_embedding = model.encode(expanded_query, convert_to_tensor=True)
+
+        # Compute cosine similarities between the query embedding and course embeddings
         similarities = util.pytorch_cos_sim(query_embedding, course_embeddings)[0]
+
+        # Append to the list of all similarities
         all_similarities.append(similarities)
 
+    # Step 3: Convert the list of tensors to a single tensor by taking the maximum similarity for each course
     aggregated_similarities = torch.max(torch.stack(all_similarities), dim=0)[0]
-    filtered_df = df.copy()
 
-    if level_filter and level_filter != "Nil":
+    # Step 4: Apply filters
+    filtered_df = df.copy()
+    if level_filter:
         filtered_df = filtered_df[filtered_df['Level of Difficulty'] == level_filter]
-    if category_filter and category_filter != "NIL":
+    if category_filter:
         filtered_df = filtered_df[filtered_df['Category'] == category_filter]
-
+    
     if filtered_df.empty:
         return "<p>No matching courses found.</p>"
-
+    
+    # Recalculate similarities for the filtered data
     filtered_similarities = aggregated_similarities[filtered_df.index]
+
+    # Step 5: Get top_k most similar courses
     top_results = filtered_similarities.topk(k=min(top_k, len(filtered_similarities)))
 
+    # Prepare the output as clickable links
     results = []
     for idx in top_results.indices:
         idx = int(idx)
         course_title = filtered_df.iloc[idx]['Course Title']
-        course_description = filtered_df.iloc[idx, 1]
-        course_url = filtered_df.iloc[idx, -1]
-        generated_description = generate_description(course_title + " " + course_description)
+        course_description = filtered_df.iloc[idx,1]
+        course_url = filtered_df.iloc[idx,-1]
+        
+        
+        # Format the result as a clickable hyperlink using raw HTML
         course_link = f'<a href="{course_url}" target="_blank">{course_title}</a>'
-        results.append(f"<strong>{course_link}</strong><br>{course_description}<br>{generated_description}<br><br>")
+        results.append(f"<strong>{course_link}</strong><br>{course_description}<br><br>")
 
+    # Combine all results into an HTML formatted list
     return "<ol>" + "".join([f"<li>{result}</li>" for result in results]) + "</ol>"
 
+# Create Gradio UI
 def create_gradio_interface():
     with gr.Blocks() as demo:
         gr.Markdown("#  Analytics Vidhya Free Courses")
         gr.Markdown("Enter your query and use filters to narrow down the search.")
+
+        # Input elements
         query = gr.Textbox(label=" Search for a course", placeholder="Enter course topic or description")
+
+        # Filters (in a collapsible form)
         with gr.Accordion(" Filters", open=False):
-            level_filter = gr.Dropdown(choices=["Beginner", "Intermediate", "Advanced", "Nil"], label=" Course Level", multiselect=False)
-            category_filter = gr.Dropdown(choices=["Data Science", "Machine Learning", "Deep Learning", "AI", "NLP", "NIL"], label=" Category", multiselect=False)
+            level_filter = gr.Dropdown(choices=["Beginner", "Intermediate", "Advanced"], label=" Course Level", multiselect=False)
+            category_filter = gr.Dropdown(choices=["Data Science", "Machine Learning", "Deep Learning", "AI", "NLP"], label=" Category", multiselect=False)
+
+        # Search button
         search_button = gr.Button("Search")
+
+        # Output HTML for displaying results
         output = gr.HTML(label="Search Results")
+
+        # On button click, trigger the search function
         search_button.click(fn=search_courses, inputs=[query, level_filter, category_filter], outputs=output)
 
     return demo
 
 # Launch Gradio interface
 demo = create_gradio_interface()
-demo.launch()
+demo.launch(share=True, debug=True)