Update app.py

app.py

@@ -1,20 +1,36 @@
 import os
 import pandas as pd
+import zipfile
+import requests
+import io
 from groq import Groq
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
-import gradio as gr
 import numpy as np
 
-# Initialize the Groq client (add your API key directly in the environment)
+# Initialize the Groq client
 client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 
-# Load the proprietary dataset from the backend folder
-dataset_path = "dataset/movie_dataset.csv"
-movies_df = pd.read_csv(dataset_path)
+# Load the proprietary dataset from GitHub
+def load_dataset_from_github(zip_url):
+    # Download the zip file
+    response = requests.get(zip_url)
+    if response.status_code == 200:
+        # Extract the zip file
+        with zipfile.ZipFile(io.BytesIO(response.content)) as z:
+            z.extractall("dataset")  # Extract to the 'dataset' folder
+        # Load the CSV file (assuming it's named 'movie_dataset.csv' inside the zip)
+        return pd.read_csv("dataset/movie_dataset.csv")
+    else:
+        raise Exception("Failed to download the dataset.")
+
+# URL of the ZIP file containing the dataset on GitHub
+zip_url = "https://github.com/YourUsername/movie-dataset/archive/refs/heads/main.zip"
+movies_df = load_dataset_from_github(zip_url)
 
 # Preprocess the dataset by creating summaries and vectors
 def preprocess_data(df):
+    # Combine relevant text columns to form a concise summary for each movie
     df['summary'] = df.apply(lambda row: f"{row['title']} ({row['release_date']}): {row['overview']} "
                                          f"Genres: {row['genres']} Keywords: {row['keywords']}", axis=1)
     return df
@@ -42,24 +58,30 @@ def generate_summary_with_groq(query, retrieved_text):
     )
     return chat_completion.choices[0].message.content
 
-# Gradio interface function for the application
-def rag_application(user_query):
-    # Retrieve relevant movie summaries
-    retrieved_movies = retrieve_similar_movies(user_query, movies_df, tfidf_matrix)
-    retrieved_summaries = " ".join(retrieved_movies['summary'].values)
-    
-    # Generate a summary response based on retrieved movies
-    generated_summary = generate_summary_with_groq(user_query, retrieved_summaries)
-    return generated_summary
-
-# Deploy using Gradio on Hugging Face
-interface = gr.Interface(
-    fn=rag_application,
-    inputs="text",
-    outputs="text",
-    title="Movie RAG-based Application",
-    description="Ask questions about movies. Proprietary dataset only accessible to the authorized user."
-)
+# Main interactive loop
+def rag_application():
+    print("Welcome to the Movie RAG-based Application!")
+    while True:
+        # Prompt user for a query
+        user_query = input("Ask a question about movies or type 'exit' to quit: ")
+        
+        if user_query.lower() in ['exit', 'no', 'quit']:
+            print("Exiting the application. Goodbye!")
+            break
+        
+        # Retrieve relevant movie summaries
+        retrieved_movies = retrieve_similar_movies(user_query, movies_df, tfidf_matrix)
+        retrieved_summaries = " ".join(retrieved_movies['summary'].values)
+        
+        # Generate a summary response based on retrieved movies
+        generated_summary = generate_summary_with_groq(user_query, retrieved_summaries)
+        print("Generated Summary:", generated_summary)
+        
+        # Ask if user wants to continue or exit
+        continue_query = input("Do you have another question? (yes/no): ")
+        if continue_query.lower() != 'yes':
+            print("Exiting the application. Goodbye!")
+            break
 
-if __name__ == "__main__":
-    interface.launch()
+# Run the application
+rag_application()