Update app.py

app.py

@@ -2,52 +2,72 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
 import torch
 import json
-import re
 
 title = "????AI ChatBot"
 description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
-examples = [["What courses under Engineering?"]]
+examples = [["How are you?"]]
 
 tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
 model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
-# Load courses data from JSON file
-def load_courses(file_path):
+# Course information
+course_info = {
+    "courses": {
+        "Engineering": ["Civil Engineering", "Mechanical Engineering", "Electrical Engineering", "Software Engineering", "etc."],
+        "Information Technology": ["Computer Science", "Information Systems", "Cybersecurity", "Data Science", "etc."],
+        "Business": ["Business Administration", "Accounting", "Finance", "Marketing", "Management", "etc."],
+        "Health Sciences": ["Nursing", "Pharmacy", "Health Information Management", "Public Health", "etc."],
+        "Design and Architecture": ["Architecture", "Industrial Design", "Visual Communication", "etc."],
+        "Science": ["Environmental Science", "Biotechnology", "Chemistry", "Physics", "etc."],
+        "Law": ["Law", "Legal Studies", "etc."],
+        "Arts and Social Sciences": ["Communication", "Education", "International Studies", "Sociology", "etc."],
+        "Built Environment": ["Urban Planning", "Construction Management", "Property Economics", "etc."],
+        "Creative Industries": ["Animation", "Photography", "Creative Writing", "Film and Television", "etc."]
+    }
+}
+
+def predict(input, history=[]):
+    # Check if the user is asking about courses
+    if "course" in input.lower():
+        # Extract the subject from the user input
+        for subject in course_info["courses"]:
+            if subject.lower() in input.lower():
+                return course_info["courses"][subject], history
+
+    # tokenize the new input sentence
+    new_user_input_ids = tokenizer.encode(input + 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)
+
+    # generate a response
+    history = model.generate(
+        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
+    ).tolist()
+
+    # convert the tokens to text, and then split the responses into lines
+    response = tokenizer.decode(history[0]).split("")
+    response = [(response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)]  # convert to tuples of list
+    return response, history
+
+def read_json_file(file_path): # read json file test
     with open(file_path, 'r') as file:
-        courses_data = json.load(file)
-    return courses_data
+        data = json.load(file)
+    return data
 
-courses_data = load_courses('uts_courses.json')
+def main():
+    # List of file names
+    file_names = ['fileone.json', 'filesecond.json', 'filethird.json', 'filefourth.json', 'filefifth.json']
 
-def predict(input, history=[]):
-    # Check if the input is related to courses
-    if re.match(r'what courses under (\w+)', input.strip().lower()):
-        # Extract the field of interest (e.g., Engineering, Information Technology, etc.)
-        match = re.match(r'what courses under (\w+)', input.strip().lower())
-        field = match.group(1).capitalize()  # Capitalize the field name
-        
-        if field in courses_data['courses']:
-            # Get the list of courses for the specified field
-            courses = courses_data['courses'][field]
-            response = f"The available courses in {field} are: {', '.join(courses)}"
-        else:
-            response = "I'm sorry, I couldn't find any courses related to that field."
-
-        return response, history
-    else:
-        # Tokenize the new input sentence
-        new_user_input_ids = tokenizer.encode(input + 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)
-
-        # Generate a response
-        history = model.generate(bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id).tolist()
-
-        # Convert the tokens to text
-        response = tokenizer.decode(history[0])
-
-        return response, history
+    # Read each JSON file and print its content
+    for file_name in file_names:
+        json_data = read_json_file(file_name)
+        print(f"Contents of {file_name}:")
+        print(json_data)
+        print()
+
+if __name__ == "__main__":
+    main()
 
 gr.Interface(
     fn=predict,