Add application file

app.py

@@ -0,0 +1,132 @@
+# -*- coding: utf-8 -*-
+"""Skill Transformation Journey.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/11XAXUP2fzy553V9v0x-gxJXcXL3uHJcw
+"""
+
+# Commented out IPython magic to ensure Python compatibility.
+# %pip install openai
+
+# Commented out IPython magic to ensure Python compatibility.
+# %pip install gradio
+
+import gradio as gr
+import re
+import openai
+from openai import OpenAI
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import linear_kernel
+
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key="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",
+)
+
+# Specify the sheet name in the Excel file
+excel_file_path = "/content/drive/MyDrive/Skill Transformation Journey/AI Integrations in SWAYAM_V1.0.xlsx"
+sheet_name = "Shortlisted Courses"  # Replace with the actual sheet name
+
+# Read the Excel file into a Pandas DataFrame
+courses_df = pd.read_excel(excel_file_path, sheet_name=sheet_name)
+
+# Function to recommend courses based on user input using GPT and TF-IDF
+def recommend_courses(user_skill, ed_qual):#, #primary_skill_1):
+    # Combine user's input into a single string for TF-IDF
+    user_input = f"{user_skill} {ed_qual}"
+
+    # Use TF-IDF and cosine similarity for initial course recommendations
+    user_vector = tfidf_vectorizer.transform([user_input])
+    cosine_similarities = linear_kernel(user_vector, tfidf_matrix)
+
+    # Get initial course recommendations based on similarity scores
+    recommendations = courses_df.copy()
+    recommendations['Similarity'] = cosine_similarities[0]
+
+    # Sort by similarity and get top recommendations
+    top_recommendations = recommendations.sort_values(by='Similarity', ascending=False).head(5)
+
+    # 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)
+
+    return final_recommendations_html
+
+# Create a TF-IDF vectorizer
+tfidf_vectorizer = TfidfVectorizer(stop_words='english')
+tfidf_matrix = tfidf_vectorizer.fit_transform(courses_df['Course Name'].fillna(''))
+
+user_skill = "psychology"
+
+ed_qual = "B.Tech/B.Sc"
+
+html = recommend_courses(user_skill, ed_qual)
+
+html
+
+def html_coversion(gpt_content):
+
+  # Provided data in text format
+  data_text = gpt_content
+
+  # Extract course details using a modified regular expression
+  courses = re.findall(r'(\d+)\. (.*?):\n\s*- Course Link: \[([^\]]+)\]\(([^)]+)\)\n\s*- Description: ([^\n]+)', data_text)
+
+  # Process each tuple to remove the second occurrence of the course link
+  processed_courses = []
+  for course_tuple in courses:
+      # Find the index of the second occurrence of the course link
+      index_of_second_occurrence = course_tuple.index(course_tuple[2], course_tuple.index(course_tuple[2]) + 1)
+      # Remove the second occurrence of the course link from the tuple
+      processed_tuple = course_tuple[:index_of_second_occurrence] + course_tuple[index_of_second_occurrence + 1:]
+      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'])
+
+  # Convert the DataFrame to an HTML table
+  html_table = df.to_html(index=False, escape=False)
+
+  # Print or save the HTML table
+  return html_table
+
+# Gradio Interface with dynamically generated dropdown options
+iface = gr.Interface(
+    fn=recommend_courses,
+    inputs=[
+        gr.Textbox("text", label="Enter expected skill"),
+        gr.Dropdown(["B.Tech/B.Sc", "M.Tech/M.Sc", "Management"], label="Highest Educational Qualification"),
+    ],
+    outputs="html",
+    live=True
+)
+
+# Launch the Gradio interface and save the output to an HTML file
+iface.launch(share=True)
+