Update app.py

app.py

@@ -2,7 +2,6 @@ import gradio as gr
 from sentence_transformers import SentenceTransformer, util
 import openai
 import os
-import random
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
@@ -11,6 +10,28 @@ filename = "output_topic_details.txt"  # Path to the file storing song-specific
 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 catering to Gen Z taste in music."
+# 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 []
 
@@ -19,45 +40,62 @@ 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.
     """
@@ -69,84 +107,59 @@ def find_relevant_segment(user_query, segments):
         "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}"
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-    if mood in songs_by_mood:
-        song = random.choice(songs_by_mood[mood]["description"])
-        topic = songs_by_mood[mood]["topic"]
-        return {"song": song, "description": description}
-    else:
-        return {"error": "Mood not recognized"}
-        
 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
-        recommendation = recommend_songs_based_on_mood(mood)
-        if "error" in recommendation:
-            response = recommendation["error"]
-
-
+        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!
+# :musical_note: 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
+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) 
+demo.launch(share=True)