app.py

import gradio as gr
from sentence_transformers import SentenceTransformer, util
import openai
import os
import re
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 song recommendation 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 preprocess_text(text):
    """
    Preprocess text by lowercasing and removing special characters.
    """
    text = text.lower()
    text = re.sub(r'[^a-z0-9\s]', '', text)
    return text

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 = [preprocess_text(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_segments(user_query, segments, top_k=5):
    try:
        # Preprocess and lowercase the query for better matching
        lower_query = preprocess_text(user_query)
        # 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 indices of the top-k most similar segments
        top_k_indices = similarities.topk(top_k).indices
        # Return the most relevant segments
        return [segments[idx] for idx in top_k_indices]
    except Exception as e:
        print(f"Error in finding relevant segments: {e}")
        return []


def generate_response(user_query, relevant_segments):
    """
    Generate a response providing song recommendations based on mood.
    """
    try:
        system_message = "You are a music recommendation chatbot designed to suggest songs based on mood, catering to Gen Z's taste in music."
        user_message = f"User query: {user_query}. Recommended songs: {', '.join(relevant_segments)}"
        messages = [
            {"role": "system", "content": system_message},
            {"role": "user", "content": user_message}
        ]
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            max_tokens=150,
            temperature=0.7,
            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 the Song Recommendation Bot! Ask me for song recommendations based on your mood."
    relevant_segments = find_relevant_segments(question, segments)
    if not relevant_segments:
        return "Could not find specific song recommendations. Please refine your question."
    response = generate_response(question, relevant_segments)
    return response

# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
# 🎶: Welcome to SongSeeker!
## I am here to help you find the perfect songs based on your mood!
"""
topics = """
### Feel free to ask me for song recommendations for:
- Sad mood
- Happy mood
- Angry mood
- Workout
- Chilling
- Study
- Eating a meal
- Nostalgic
- Self care
"""

# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(css="custom.css") 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's your mood or activity?")
            answer = gr.Textbox(label="Song Recommendations", placeholder="Your recommendations will appear 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)