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_interior_details.txt"  # Path to the file storing interior_design-specific details
retrieval_model_name = 'output/sentence-transformer-finetuned/'

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

# 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 interior design information.
    """
    try:
        system_message = "You are Tessy who is designed to help find interior design inspiration and guide the users transform their living space."
        user_message = f"Here's the information on interior design: {relevant_segment}"
        messages = [
            {"role": "system", "content": system_message},
            {"role": "user", "content": user_message}
        ]
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            max_tokens=500,
            temperature=0.2,
            top_p=1,
            frequency_penalty=0,
            presence_penalty=0
        )
        return response['choices'][0]['message']['content'].strip()
    except Exception as e:
        print(f"Error in generating response: {e}")
        return f"Error in generating response: {e}"

def get_pinterest_link(question):
    """
    Check if the question contains a keyword and return the corresponding Pinterest link.
    """
    keyword_links = {
        "design": "Here is a link to the Pinterest board to help you get started. Copy the link that will direct you to the Pinterest board that will take you on your to be inspired and get and an idea of what you would like to incorportae to your living space: https://www.pinterest.com/yadavanushka2205",
    }
    
    for keyword, link in keyword_links.items():
        if keyword in question.lower():
            return link
    

def query_model(question):
    """
    Process a question, find relevant information, and generate a response.
    """

    pinterest_link = get_pinterest_link(question)
    if pinterest_link:
        return f"Here is a link to the Pinterest board to help you get started and find inspiration for your style! Just copy this link to get to the board: {pinterest_link}"

    if question == "":
        return "Welcome to Designare! Ask me anything about different styles or inspiration for interior design."
    
    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 Designare!

## I am Tessy and I am here to help you with your interior design journey. Created by Anushka, Prani, Gigi, and Jewel of the 2024 Kode With Klossy St. Louis Camp. 
"""

topics = """
### Feel Free to ask me anything from the topics below!
- What is interior design
- Different aestheticts 
- Styles
- Inspiration
- Color guide
- Get me started
"""

# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme='JohnSmith9982/small_and_pretty') as demo:
    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="Tessy Response", placeholder="Tessy 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)