app.py

import gradio as gr
from sentence_transformers import SentenceTransformer, util
import openai
import os

os.environ["TOKENIZERS_PARALLELISM"] = "false"

# Initialize paths and model identifiers for easy configuration and maintenance
filename = "output_topic_details.txt"  # Path to the file storing college-specific details
retrieval_model_name = 'output/sentence-transformer-finetuned/'

openai.api_key = os.environ["OPENAI_API_KEY"]

system_message = "You are a college consultant chatbot specialized in but not limited to providing information on the demographic, college information, college admisions, tuition, and college location."
# Initial system message to set the behavior of the assistant
messages = [{"role": "system", "content": system_message}]


# Attempt to load the necessary models and provide feedback on success or failure
try:
    retrieval_model = SentenceTransformer(retrieval_model_name)
    print("Models loaded successfully.")
except Exception as e:
    print(f"Failed to load models: {e}")

def load_and_preprocess_text(filename):
    """
    Load and preprocess text from a file, removing empty lines and stripping whitespace.
    """
    try:
        with open(filename, 'r', encoding='utf-8') as file:
            segments = [line.strip() for line in file if line.strip()]
        print("Text loaded and preprocessed successfully.")
        return segments
    except Exception as e:
        print(f"Failed to load or preprocess text: {e}")
        return []

segments = load_and_preprocess_text(filename)

def find_relevant_segment(user_query, segments):
    """
    Find the most relevant text segment for a user's query using cosine similarity among sentence embeddings.
    This version finds the best match based on the content of the query.
    """
    try:
        # Lowercase the query for better matching
        lower_query = user_query.lower()
        
        # Encode the query and the segments
        query_embedding = retrieval_model.encode(lower_query)
        segment_embeddings = retrieval_model.encode(segments)
        
        # Compute cosine similarities between the query and the segments
        similarities = util.pytorch_cos_sim(query_embedding, segment_embeddings)[0]
        
        # Find the index of the most similar segment
        best_idx = similarities.argmax()
        
        # Return the most relevant segment
        return segments[best_idx]
    except Exception as e:
        print(f"Error in finding relevant segment: {e}")
        return ""

def generate_response(user_query, relevant_segment):
    """
    Generate a response emphasizing the bot's capability in providing college information.
    """
    try:
        user_message = f"Here's the information on college: {relevant_segment}"

        # Append user's message to messages list
        messages.append({"role": "user", "content": user_message})
        
        response = openai.ChatCompletion.create(
            model="gpt-4o",
            messages=messages,
            max_tokens=600,
            temperature=0.7,
            top_p=1,
            frequency_penalty=0.5,
            presence_penalty=0.5,
            stop=None
        )
       

        # Extract the response text
        output_text = response['choices'][0]['message']['content'].strip()
        
        # Append assistant's message to messages list for context
        messages.append({"role": "assistant", "content": output_text})
        
        return output_text
        
    except Exception as e:
        print(f"Error in generating response: {e}")
        return f"Error in generating response: {e}"

def query_model(question):
    """
    Process a question, find relevant information, and generate a response.
    """
    if question == "":
        return "Welcome to Collete! Ask me anything about college admissions, college fit or college testing."
    relevant_segment = find_relevant_segment(question, segments)
    if not relevant_segment:
        return "Could not find specific information. Please refine your question."
    response = generate_response(question, relevant_segment)
    return response

# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
# 🏫 Welcome to Collete!
## Your AI-driven assistant for all college-related queries. Created by Abigail, Reet, and Sora of the 2024 Kode With Klossy DC Camp. 
"""

topics = """
### 
  Collete wants to know what features you value in a college and she will give you some colleges that are a good fit for you. She specializes in colleges in the DMV.
  
  A sample input is: I live in Virginia and I am looking for a college that has a max tuition of 50k.

  You can also ask Collete about these topics concerning college and college admissions:
   - Applications
   - College life
   - Testing for college
   - College fit
"""

def display_image():
    return "aestheticCampus.png"

# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme='freddyaboulton/test-blue') as demo:
    gr.Image(display_image(), show_label = False, show_share_button = False, show_download_button = False)
    gr.Markdown(welcome_message)  # Display the formatted welcome message
    with gr.Row():
        with gr.Column():
            gr.Markdown(topics)  # Show the topics on the left side
    with gr.Row():
        with gr.Column():
            question = gr.Textbox(label="Your question", placeholder="What do you want to ask about?")
            answer = gr.Textbox(label="Collete's Response", placeholder="Collete will respond here...", interactive=False, lines=10)
            submit_button = gr.Button("Submit")
            submit_button.click(fn=query_model, inputs=question, outputs=answer)
    

# Launch the Gradio app to allow user interaction
demo.launch(share=True)