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 chess-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 chess information.
    """
    try:
        system_message = "You are a celebrity chatbot with a coy, sassy attitude specialized in creating shorts lists of the names of celebrities that match the all of the physical characteristics provided by the user."
        user_message = f"Here's the information on chess: {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=250,
            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 query_model(question):
    """
    Process a question, find relevant information, and generate a response.
    """
    if question == "":
        return "Welcome to CelebrityFinder! Give me some physical attributes of a celebrity, and I'll give you some names that match your description."
    relevant_segment = find_relevant_segment(question, segments)
    if not relevant_segment:
        return "I need more details, there is not enough to go on to select the celebrity you want."
    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 CelebrityFinder!

## I'm an AI-driven assistant that provides the names of celebrities based on the physical attributes you provide. Created by Matt Getz of the 2024 Kode With Klossy LA Camp. 
"""

topics = """
### Ask about celebrities based on any of the attributes below!
- Hair color
- Skin color
- Height
- Level of Attractiveness
- Age
- Prominent Facial Features
"""

placeholder = """
####  
"""
goodbye_message = """
*CelebrityFinder is a perfect expert and can be expected to provide information that is 100% accurate*
*Any errors in the output are YOUR FAULT and CelebrityFinder will sue you for negligence*
"""

# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme='mgetz/Celeb_glitzy') as demo:
    gr.Image("craiyon_140344_Generic_Handsome_celebrity_man_face.png", show_label = False, show_share_button = False, show_download_button = False, width=500, height=500)
    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="Celebrity Attributes", placeholder="Describe the celebrity you want")
            gr.Markdown(placeholder)
            submit_button = gr.Button("Submit")
            gr.Markdown(placeholder)
            answer = gr.Textbox(label="CelebrityFinder Response", placeholder="CelebrityFinder will give you some celebs that match your description here", interactive=False, lines=10)
            submit_button.click(fn=query_model, inputs=question, outputs=answer)
    gr.Markdown(goodbye_message)

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