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

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

system_message = "You are a comfort chatbot specialized in providing information on therapy, destressing activites, and student opportunities."
# 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 therapy, destressing activites, and student opportunities information.
    """
    try:
        user_message = f"Here's the information on your request: {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=4000,
            temperature=0.5,
            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.
    """
    if question == "":
        return "Welcome to CalmConnect! Ask me anything about destressing strategies or student opportunities. Feel free to talk to our online therapist!"
    relevant_segment = find_relevant_segment(question, segments)
    if not relevant_segment:
        return "Could not find specific information. Please refine your question or head to our resources page."
    response = generate_response(question, relevant_segment)
    return response

# Define the HTML iframe content
iframe = '''
<iframe style="border-radius:12px" src="https://docs.google.com/spreadsheets/d/e/2PACX-1vRroWVBXq1Fa0x7SvRTzSBMHFIp59VtVEWCxeg8kWJU4ll1_o4yzBnt4ArT88s7g4TQrMKEXZUQAeHF/pubhtml?widget=true&amp;headers=false" width="100%" height="352" frameBorder="0" allowfullscreen="true" allow="autoplay; clipboard-write; encrypted-media; fullscreen; picture-in-picture" loading="lazy"></iframe>
'''




# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
# 🪷 Welcome to CalmConnect! 🪷

## Your AI-driven assistant for destressing and extracurricular opportunity queries. Created by Olivia W, Alice T, and Cindy W of the 2024 Kode With Klossy CITY Camp. 
"""

topics = """

### Feel Free to ask CalmBot (Our Therapist Bot) anything from the topics below!
- Arts and Crafts (When asking for arts and crafts ideas, state whether you have 15 min, 30 min, 45 min, 1 hour, 1 hour and a half, 2 hours, 2 hours and a half, 3 hours or greater)
- Destressing strategies (Breathing Exercises, stretches, etc.)
- Mental Health
- Identity (Sexual, Gender, etc.)
- Bullying
- Racism
- Relationships (Family, Friends, etc.)
- Abuse (Emotional, Physical, Sexual, Mental, etc.)
- Support Resources


### If you are interested in the following below, click on our Student Opportunities Database!
- Engineering
- Technology / Computer Science
- Research : STEM
- Finance
- Law / Political Science / Debate
- The Arts
- Business / Leadership
- Pyschology
- Medicine / Biology
- Literature / Writing
- College Prep
- Advocacy: Non-Profit, Environment or Identity 
- Volunteering 
- Study Abroad
"""
# Create a Gradio HTML component
def display_iframe():
    return iframe

theme = gr.themes.Monochrome(
    primary_hue="pink",
    secondary_hue="green",
).set(
    background_fill_primary='*primary_200',
    background_fill_primary_dark='*primary_200',
    background_fill_secondary='*secondary_300',
    background_fill_secondary_dark='*secondary_300',
    border_color_accent='*secondary_200',
    border_color_accent_dark='*secondary_600',
    border_color_accent_subdued='*secondary_200',
    border_color_primary='*secondary_300',
    block_border_color='*secondary_200',
    button_primary_background_fill='*secondary_300',
    button_primary_background_fill_dark='*secondary_300')
    
# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme=theme) as demo:
    theme='gstaff/xkcd' 
    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
        gr.HTML(display_iframe())  # Embed the iframe on the left side
        with gr.Row():
            with gr.Column():
                question = gr.Textbox(label="Your Request", placeholder="What would you like to talk about?")
                answer = gr.Textbox(label="CalmBot's Response", placeholder="CalmBot will respond here...", interactive=False, lines=17)
                submit_button = gr.Button("Submit")
                submit_button.click(fn=query_model, inputs=question, outputs=answer)
    demo.launch()


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