Update app.py

app.py

@@ -1,14 +1,5 @@
 import json
-from transformers import pipeline
-import nltk
-from nltk.corpus import stopwords
-from nltk.tokenize import word_tokenize
-from nltk.stem import WordNetLemmatizer
-
-# Download NLTK resources
-nltk.download('punkt')
-nltk.download('wordnet')
-nltk.download('stopwords')
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 
 # Load the JSON data from the file
 with open('uts_courses.json') as f:
@@ -17,48 +8,26 @@ with open('uts_courses.json') as f:
 # Load the question-answering pipeline
 qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
 
-# Define stop words and lemmatizer
-stop_words = set(stopwords.words('english'))
-lemmatizer = WordNetLemmatizer()
+# Load tokenizer and model for dialog generation
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
-# Function to preprocess user input
-def preprocess_input(user_input):
-    tokens = word_tokenize(user_input.lower())
-    filtered_tokens = [lemmatizer.lemmatize(word) for word in tokens if word.isalnum() and word not in stop_words]
-    return " ".join(filtered_tokens)
+# Function to generate response using dialog generation model
+def generate_dialog_response(user_input):
+    input_text = user_input + tokenizer.eos_token
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
 
-# Function to find courses by field of study
-def find_courses_by_field(field):
-    if field in data['courses']:
-        return data['courses'][field]
-    else:
-        return []
+    # Generate response
+    response_ids = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    response_text = tokenizer.decode(response_ids[0], skip_special_tokens=True)
 
-# Function to handle user input and generate responses
-def generate_response(user_input):
-    user_input = preprocess_input(user_input)
-    if user_input == 'exit':
-        return "Exiting the program."
-    elif "courses" in user_input and "available" in user_input:
-        field = user_input.split("in ")[1]
-        courses = find_courses_by_field(field)
-        if courses:
-            response = f"Courses in {field}: {', '.join(courses)}"
-        else:
-            response = f"No courses found in {field}."
-    else:
-        answer = qa_pipeline(question=user_input, context=data)
-        response = answer['answer']
-    return response
+    return response_text
 
 # Function to interactively retrieve user input
 def get_user_input():
-    try:
-        # Print prompt and retrieve user input
-        print("You: ", end="")
-        return input()
-    except EOFError:
-        return "exit"
+    # Print prompt and retrieve user input
+    print("You: ", end="")
+    return input()
 
 # Main function to interact with the user
 def main():
@@ -68,12 +37,21 @@ def main():
     try:
         while True:
             user_input = get_user_input()
-            response = generate_response(user_input)
-            print("Bot:", response)
-            if response == "Exiting the program.":
+            if user_input.lower() == 'exit':
+                print("Bot: Exiting the program.")
                 break
-    except EOFError:
-        print("An error occurred while processing input. Exiting the program.")
+            elif "courses" in user_input.lower() and "available" in user_input.lower():
+                field = user_input.split("in ")[1]
+                courses = data['courses'].get(field, [])
+                if courses:
+                    response = f"Courses in {field}: {', '.join(courses)}"
+                else:
+                    response = f"No courses found in {field}."
+            else:
+                response = generate_dialog_response(user_input)
+            print("Bot:", response)
+    except KeyboardInterrupt:
+        print("\nBot: Exiting the program.")
 
 if __name__ == "__main__":
     main()