Update app.py

app.py

@@ -1,59 +1,40 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer
-import gradio as gr
 import torch
 import json
 
-title = "Smart AI ChatBot"
-description = "A conversational model capable of intelligently answering questions (DialoGPT)"
-examples = [["How are you?"], ["What's the weather like?"]]
-
 # Load DialoGPT model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
 model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
-# Known question-answer pairs, you can add more as per your requirement
-known_questions_answers = {
-    "How are you?": "I'm fine, thank you for asking.",
-    "What's the weather like?": "The weather is nice today, sunny and warm.",
-    "What's your name?": "I am Smart AI ChatBot.",
-    "Do you speak English?": "I can understand and respond to English questions.",
-}
+# Load courses data from JSON file
+with open("uts_courses.json", "r") as file:
+    courses_data = json.load(file)
 
-def predict(input_text, chatbot_state):
-    response = None
-    history = chatbot_state
-    
-    # Check if the input question is in the known question-answer pairs
-    if input_text in known_questions_answers:
-        response = known_questions_answers[input_text]
+def generate_response(user_input):
+    if user_input.lower() == "help":
+        return "I can help you with information about UTS courses. Feel free to ask!"
+    elif user_input.lower() == "exit":
+        return "Goodbye!"
+    elif user_input.lower() == "list courses":
+        course_list = "\n".join([f"{category}: {', '.join(courses)}" for category, courses in courses_data["courses"].items()])
+        return f"Here are the available courses:\n{course_list}"
+    elif user_input.lower() in courses_data["courses"]:
+        return f"The courses in {user_input} are: {', '.join(courses_data['courses'][user_input])}"
     else:
-        # Tokenize the new user input sentence
-        new_user_input_ids = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors="pt")
-        # Append the new user input tokens to the chat history
-        bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+        # Tokenize the user input
+        input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
         # Generate a response
-        history = model.generate(
-            bot_input_ids, max_length=400, pad_token_id=tokenizer.eos_token_id
-        ).tolist()
-        # Convert tokens to text, and split the response into lines
-        response = tokenizer.decode(history[0], skip_special_tokens=True)
-    
-    return response, history
-
-def main():
-    # You can add logic here to read known question-answer pairs, for example, from a JSON file
-    pass
-
-textbox_output = gr.outputs.Textbox(label="Chatbot Response")
-state_input = "text"
-state_output = "state"
+        response_ids = model.generate(input_ids, max_length=100, pad_token_id=tokenizer.eos_token_id)
+        # Decode the response
+        response = tokenizer.decode(response_ids[0], skip_special_tokens=True)
+        return response
 
-gr.Interface(
-    fn=predict,
-    title=title,
-    description=description,
-    examples=examples,
-    inputs=["text", state_input],
-    outputs=[textbox_output, state_output],
-    theme="finlaymacklon/boxy_violet",
-).launch()
+if __name__ == "__main__":
+    print("Welcome to the UTS Course Chatbot!")
+    print("Type 'help' to see available commands and 'exit' to quit.")
+    while True:
+        user_input = input("You: ")
+        response = generate_response(user_input)
+        print("Chatbot:", response)
+        if user_input.lower() == "exit":
+            break