Add application file

app.py

@@ -49,7 +49,7 @@ def html_coversion(gpt_content):
       processed_courses.append(processed_tuple)
 
   # Convert the processed list of tuples into a DataFrame
-  df = pd.DataFrame(processed_courses, columns=['Sr No', 'Course Name', 'Course Link', 'Description'])
+  df = pd.DataFrame(processed_courses, columns=['Course Name', 'Course Link'])
 
   # Convert the DataFrame to an HTML table
   html_table = df.to_html(index=False, escape=False)
@@ -76,29 +76,9 @@ def recommend_courses(user_skill, ed_qual):
     # Generate a text summary of the initial recommendations
     initial_recommendations_text = top_recommendations[['Course Name', 'Course Link']].to_string(index=False)
 
-    # Combine user input and initial recommendations for GPT prompt
-    gpt_prompt = f"Refine the following course recommendations based on user input:\n\n"\
-                 f"{user_input}\n\n"\
-                 f"Initial Recommendations:\n\n"\
-                 f"{initial_recommendations_text}"
-
-    # Use GPT to generate refined recommendations
-    gpt_response = client.chat.completions.create(
-            messages=[
-            {
-                "role": "system",
-                "content": gpt_prompt,
-            }
-        ],
-        model="gpt-3.5-turbo",
-        max_tokens=1000
-    )
-
-    # Assume GPT generates HTML-formatted final recommendations
-    gpt_content = gpt_response.choices[0].message.content #gpt_response['choices'][0]['text']
-
+    
     # Assume GPT generates HTML-formatted final recommendations
-    final_recommendations_html = html_coversion(gpt_content)
+    final_recommendations_html = html_coversion(initial_recommendations_text)
 
     return final_recommendations_html