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

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

system_message = "You are a song chatbot specialized in providing song recommendations based on mood."
# 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 song recommendations.
    """
    try:
        user_message = f"Here's the information on songs: {relevant_segment}"

        # Append user's message to messages list
        messages.append({"role": "user", "content": user_message})
        
        # Use OpenAI's API to generate a response based on the user's query and system messages
        response = openai.ChatCompletion.create(
            model="gpt-3.5-turbo",
            messages=messages,
            max_tokens=150,
            temperature=0.2,
            top_p=1,
            frequency_penalty=0,
            presence_penalty=0
        )
        
        # 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 recommend_songs_based_on_mood(mood):
    """
    Recommend songs based on the user's mood query.
    """
    # Example logic to recommend songs based on mood (replace with your actual logic)
    recommended_songs = [
        "Song A",
        "Song B",
        "Song C",
        "Song D",
        "Song E"
    ]
    
    # Format the recommendation list as a string
    recommended_songs_str = "\n- " + "\n- ".join(recommended_songs)
    
    return f"Here are some songs you might like based on '{mood}' mood:{recommended_songs_str}"

def query_model(user_query):
    """
    Process a user's query, find relevant information, and generate a response.
    """
    if user_query == "":
        return "Welcome to SongBot! Ask me for song recommendations based on mood."
    
    # Example logic to identify if the user query is related to song recommendations based on mood
    if "recommend" in user_query.lower() and ("song" in user_query.lower() or "music" in user_query.lower()):
        mood = user_query.lower().split("recommend", 1)[1].strip()  # Extract mood from query
        response = recommend_songs_based_on_mood(mood)
    else:
        relevant_segment = find_relevant_segment(user_query, segments)
        if not relevant_segment:
            response = "Could not find specific information. Please refine your question."
        else:
            response = generate_response(user_query, relevant_segment)
    
    return response

# Define the welcome message and specific topics the chatbot can provide information about
welcome_message = """
# 🎵 Welcome to Song Seeker!
## Your AI-driven assistant for music curation. Created by Fenet, Lia, and Zamira of the 2024 Kode With Klossy DC Camp.
"""

topics = """
### Feel free to ask me for song recommendations based on mood!
- Happy songs
- Sad songs
- Chill songs
- Angry songs
- Workout songs
"""

# Setup the Gradio Blocks interface with custom layout components
with gr.Blocks(theme='dabble') 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 mood (e.g., happy, sad)", placeholder="What mood are you in?")
            answer = gr.Textbox(label="SongBot Response", placeholder="SongBot 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)