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 literature-specific details
retrieval_model_name = 'output/sentence-transformer-finetuned/'

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

system_message = "You are a literature chatbot specialized in providing information on the context behind classic literature. You will provide basic answers initially, and then, instead of going into deeper detail, encourage students to think deeply about the literature they are reading with leading questions. These questions should also guide the reader as to what they should notice or pay attention to as they continue reading."
# 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 literature information.
    """
    try:
        user_message = f"Here's the information on your book: {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=500,
            temperature=0.2,
            top_p=1,
            frequency_penalty=0.5,
            presence_penalty=0.5,
        )
        
        # 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 using inputted book title. 
    """
    if question == "":
        return "Welcome to LitBot! Ask me anything about literature, book themes, and the historical context behind your book."
    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 LitBot!

## An AI-driven assistant for all literature-related queries, LitBot is your new trusted reading guide! Created by Katie, Madeline, and Tiffany of the 2024 Kode With Klossy Los Angeles Camp. 
"""

topics = """
### You can ask anything from the topics below!
- Themes
- Historical Context
- Symbolism
- Potential Reading Challenges
- Controversies
- Book Background Information
"""
books = """
### Feel free to ask about any of these books:
- The Great Gatsby
- The Crucible
- Fahrenheit 451
- Of Mice and Men
- To Kill a Mockingbird
- Romeo and Juliet
- The Catcher in the Rye
- Pride and Prejudice
- Lord of the Flies
- Hamlet
"""
warn = """
### Make sure to put the name of the book you are asking about in your question.
"""
space = """
###
"""


# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme='katiiegomez/litbot-revamped') as demo:
    gr.Markdown(welcome_message)  # Display the formatted welcome message
    with gr.Row():
       # with gr.Column():
            gr.Markdown(books)  # Show the topics on the left side
            gr.Markdown(topics)
    with gr.Row():
        with gr.Column():
            gr.Markdown(warn)
            # book = gr.Dropdown(
            #     ["The Great Gatsby", "The Crucible", "Fahrenheit 451", "Of Mice and Men", "To Kill a Mockingbird", "Romeo and Juliet", "The Catcher in the Rye", "Pride and Prejudice", "Lord of the Flies", "Hamlet"],
            #     label = "Choose a book!",
            #     interactive = True )
            question = gr.Textbox(label="Your question", placeholder="What do you want to ask about?")
            gr.Markdown(space)
            submit_button = gr.Button("Submit")
            answer = gr.Textbox(label="LitBot Response", placeholder="LitBot will respond here...", interactive=False, lines=30)
            submit_button.click(fn=query_model, inputs=question, outputs=answer)
            
    
# Launch the Gradio app to allow user interaction
demo.launch(share=True)