Update app.py

app.py

@@ -1,23 +1,35 @@
 import pandas as pd
 from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity  # Ensure scikit-learn is installed
+from sklearn.metrics.pairwise import cosine_similarity
 import gradio as gr
 
-# Load the dataset
-df = pd.read_csv('/content/courses.csv')  # Replace with the actual path to courses.csv
+# Debug: Print start of application
+print("Starting the application...")
+
+# Load the dataset from the same directory
+print("Loading dataset...")
+df = pd.read_csv('courses.csv')  # Assuming courses.csv is in the same directory as app.py
+print(f"Dataset loaded. Number of rows: {df.shape[0]}")
 
 # Load a pre-trained sentence transformer model
+print("Loading Sentence Transformer model...")
 model = SentenceTransformer('all-MiniLM-L6-v2')
+print("Model loaded successfully.")
 
 # Create a combined column for embedding (e.g., title + description + keywords)
+print("Generating embeddings for courses...")
 df['combined_text'] = df['title'] + " " + df['description'] + " " + df['keywords']
 course_embeddings = model.encode(df['combined_text'].tolist(), convert_to_tensor=True)
+print("Embeddings generated successfully.")
 
 def search_courses(user_query):
+    print(f"Received query: {user_query}")
+    
     # Encode the user query
     query_embedding = model.encode(user_query, convert_to_tensor=True)
 
     # Compute cosine similarities between the query and each course embedding
+    print("Calculating cosine similarities...")
     similarities = cosine_similarity(
         query_embedding.cpu().detach().numpy().reshape(1, -1),
         course_embeddings.cpu().detach().numpy()
@@ -25,9 +37,10 @@ def search_courses(user_query):
 
     # Get indices of top matching courses (top 5 results)
     top_matches = similarities.argsort()[0][-5:][::-1]
-
+    
     # Retrieve top matching courses
     results = [{"title": df.iloc[i]["title"], "description": df.iloc[i]["description"]} for i in top_matches]
+    print(f"Found {len(results)} results.")
     return results
 
 # Define Gradio function for user interaction
@@ -36,6 +49,7 @@ def gradio_search(query):
     return results
 
 # Set up Gradio interface
+print("Setting up Gradio interface...")
 iface = gr.Interface(
     fn=gradio_search,
     inputs="text",
@@ -45,4 +59,8 @@ iface = gr.Interface(
 )
 
 # Launch the app (for local testing or deploying in Hugging Face Spaces)
+print("Launching the app...")
 iface.launch()
+
+# Debug: Print end of application
+print("Application launched successfully.")