Delete app.py

app.py

@@ -1,283 +0,0 @@
-import gradio as gr
-import pandas as pd
-import numpy as np
-import spotipy
-from spotipy.oauth2 import SpotifyClientCredentials
-from sentence_transformers import SentenceTransformer
-import faiss
-import os
-import random
-import difflib
-import re
-import urllib.parse
-from langchain_community.llms import HuggingFaceEndpoint
-
-# ---------------------------------------------------------
-# 1. SETUP & AUTHENTICATION
-# ---------------------------------------------------------
-
-# Load Environment Variables from Space Settings
-SPOTIPY_CLIENT_ID = os.getenv("SPOTIPY_CLIENT_ID")
-SPOTIPY_CLIENT_SECRET = os.getenv("SPOTIPY_CLIENT_SECRET")
-HF_TOKEN = os.getenv("HF_TOKEN")
-
-# Setup Spotify
-auth_manager = SpotifyClientCredentials(client_id=SPOTIPY_CLIENT_ID, client_secret=SPOTIPY_CLIENT_SECRET)
-sp = spotipy.Spotify(auth_manager=auth_manager)
-
-# Setup LLM (Using Mistral-7B via Inference API - fast and free)
-repo_id = "mistralai/Mistral-7B-Instruct-v0.2"
-
-llm = HuggingFaceEndpoint(
-    repo_id=repo_id,
-    max_length=128,
-    temperature=0.5,
-    huggingfacehub_api_token=HF_TOKEN
-)
-
-# ---------------------------------------------------------
-# 2. DATA LOADING (The Safe Way)
-# ---------------------------------------------------------
-print("⏳ Loading Data...")
-
-# 1. Load CSV
-try:
-    df_combined = pd.read_csv("data.csv")
-    # Ensure text columns are strings to prevent errors
-    df_combined['text'] = df_combined['text'].astype(str)
-    df_combined['song'] = df_combined['song'].astype(str)
-    df_combined['artist'] = df_combined['artist'].astype(str)
-    print("✅ CSV Loaded")
-except Exception as e:
-    print(f"❌ Error loading data.csv: {e}")
-
-# 2. Load Embeddings (Crucial Step)
-print("⏳ Loading Embeddings from .npz...")
-try:
-    # Load the file you uploaded
-    data = np.load("df_embed.npz")
-    df_embeddings = data['df_embeddings']
-    print(f"✅ Embeddings Loaded. Shape: {df_embeddings.shape}")
-
-    # Create FAISS Index on CPU
-    # We use IndexFlatL2 which is exact, simple, and works everywhere
-    d = df_embeddings.shape[1]
-    index = faiss.IndexFlatL2(d)
-    index.add(df_embeddings)
-    print(f"✅ FAISS Index ready with {index.ntotal} vectors.")
-
-except Exception as e:
-    print(f"❌ Error loading df_embed.npz: {e}")
-    print("CRITICAL: Make sure you uploaded 'df_embed.npz' to the Files tab.")
-    # Create a dummy index so the app doesn't crash immediately, but search won't work
-    index = faiss.IndexFlatL2(768) 
-
-# 3. Load Model (Only needed to encode the USER query, not the database)
-print("⏳ Loading Sentence Transformer...")
-embedder = SentenceTransformer('all-mpnet-base-v2')
-
-GENERIC_ARTISTS = ["religious music", "christmas songs", "various artists", "soundtrack", "unknown", "traditional"]
-
-# ---------------------------------------------------------
-# 3. HELPER FUNCTIONS
-# ---------------------------------------------------------
-def clean_metadata(text):
-    text = str(text)
-    text = text.replace("X-mas", "Xmas").replace("x-mas", "xmas")
-    text = re.sub(r'\([^)]*\)', '', text)
-    return text.strip()
-
-def normalize_text(text):
-    return re.sub(r'[^a-zA-Z0-9\s]', '', str(text).lower())
-
-def get_best_spotify_match(artist, title):
-    artist_clean = clean_metadata(artist)
-    title_clean = clean_metadata(title)
-    query = f"{artist_clean} {title_clean}"
-    
-    try:
-        results = sp.search(q=query, type='track', limit=5, market='US')
-        items = results['tracks']['items']
-    except:
-        return None, None
-
-    if not items: return None, None
-
-    best_match = None
-    best_score = 0.0
-    target_artist = normalize_text(artist)
-
-    for item in items:
-        track_artists = " ".join([normalize_text(a['name']) for a in item['artists']])
-        score = difflib.SequenceMatcher(None, target_artist, track_artists).ratio()
-        
-        found_title = normalize_text(item['name'])
-        t_score = difflib.SequenceMatcher(None, normalize_text(title), found_title).ratio()
-        
-        final_score = (score * 0.6) + (t_score * 0.4)
-
-        if final_score > best_score:
-            best_score = final_score
-            best_match = item
-
-    if best_match:
-        url = best_match['external_urls']['spotify']
-        img = best_match['album']['images'][0]['url'] if best_match['album']['images'] else None
-        return url, img
-    return None, None
-
-def get_theme_colors(query):
-    palettes = [
-        {"name": "Spotify Classic", "accent": "#1DB954", "bg_grad": "linear-gradient(135deg, #103018 0%, #000000 100%)", "text": "#1DB954", "btn_text": "#000000"},
-        {"name": "Midnight Purple", "accent": "#D0BCFF", "bg_grad": "linear-gradient(135deg, #240046 0%, #000000 100%)", "text": "#D0BCFF", "btn_text": "#000000"},
-        {"name": "Sunset Orange",   "accent": "#FF9900", "bg_grad": "linear-gradient(135deg, #4a1c05 0%, #000000 100%)", "text": "#FFB347", "btn_text": "#000000"},
-        {"name": "Ocean Blue",      "accent": "#00E5FF", "bg_grad": "linear-gradient(135deg, #001f3f 0%, #000000 100%)", "text": "#7FDBFF", "btn_text": "#000000"},
-        {"name": "Neon Pink",       "accent": "#FF4081", "bg_grad": "linear-gradient(135deg, #3a0000 0%, #000000 100%)", "text": "#FF80AB", "btn_text": "#000000"},
-    ]
-    hash_int = int(hashlib.md5(query.encode()).hexdigest(), 16)
-    return palettes[hash_int % len(palettes)]
-
-def get_random_vibe():
-    vibes = [
-        "A cyberpunk chase scene through Tokyo neon rain",
-        "Drinking coffee on a porch while it storms outside",
-        "The feeling of realizing you are falling out of love",
-        "A villain explaining their plan while drinking wine",
-        "Driving a convertible down the coast at sunset",
-        "Waking up in a spaceship alone"
-    ]
-    return random.choice(vibes)
-
-import hashlib
-
-# ---------------------------------------------------------
-# 4. SEARCH LOGIC
-# ---------------------------------------------------------
-def harmonifind_search(user_query, k=7, use_llama=True):
-    search_query = user_query
-    
-    if use_llama:
-        try:
-            # We use the inference API here - Safe for CPU spaces
-            prompt = f"User Query: '{user_query}'\nOutput exactly 5 descriptive keywords regarding the mood, instruments, or genre. Do not output full sentences. Keywords:"
-            raw_response = llm.invoke(prompt)
-            keywords = raw_response.replace("\n", " ").strip()
-            print(f"🧠 AI Keywords: {keywords}")
-            search_query = f"{user_query} {keywords}"
-        except Exception as e:
-            print(f"⚠️ AI skipped: {e}")
-
-    # Encode user query using the local CPU model
-    q_vec = embedder.encode([search_query])
-    
-    # Search the Pre-loaded Index
-    distances, indices = index.search(q_vec, k)
-    
-    results_df = df_combined.iloc[indices[0]].copy()
-
-    scores = []
-    for dist in distances[0]:
-        scores.append(int(max(0, min(100, (1 - (dist / 1.5)) * 100))))
-    results_df['match_score'] = scores
-
-    print("🎵 Fetching Spotify metadata...")
-    s_urls, s_imgs = [], []
-    for _, row in results_df.iterrows():
-        u, i = get_best_spotify_match(row['artist'], row['song'])
-        s_urls.append(u)
-        s_imgs.append(i)
-    
-    results_df['spotify_url'] = s_urls
-    results_df['image'] = s_imgs
-    return results_df
-
-# ---------------------------------------------------------
-# 5. UI GENERATOR
-# ---------------------------------------------------------
-def gradio_interface_fn(query):
-    if not query: return ""
-    df_results = harmonifind_search(query, k=7, use_llama=True)
-    theme = get_theme_colors(query)
-
-    share_text = urllib.parse.quote(f"Listening to '{query}' via HarmoniFind 🎵")
-    share_url_x = f"https://twitter.com/intent/tweet?text={share_text}"
-
-    html = f"""
-    <style>
-        @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700;800&display=swap');
-        .hf-container {{
-            background: {theme['bg_grad']}; color: white; font-family: 'Inter', sans-serif;
-            border-radius: 24px; padding: 40px; box-shadow: 0 20px 60px rgba(0,0,0,0.8);
-        }}
-        .hf-header {{ border-bottom: 1px solid rgba(255,255,255,0.1); padding-bottom: 20px; margin-bottom: 20px; display: flex; justify-content: space-between; align-items: flex-end; }}
-        .hf-title {{ font-size: 2rem; font-weight: 800; margin: 0; }}
-        .hf-meta {{ font-size: 0.9rem; opacity: 0.7; text-transform: uppercase; }}
-        .track-row {{ display: flex; align-items: center; background: rgba(0,0,0,0.2); margin-bottom: 15px; padding: 15px; border-radius: 12px; gap: 20px; }}
-        .track-row:hover {{ background: rgba(255,255,255,0.1); }}
-        .cover-img {{ width: 70px; height: 70px; border-radius: 8px; object-fit: cover; }}
-        .info-col {{ flex-grow: 1; }}
-        .song-name {{ font-weight: 700; font-size: 1.1rem; display: block; }}
-        .play-btn {{ background: {theme['accent']}; color: {theme['btn_text']}; padding: 10px 25px; border-radius: 50px; text-decoration: none; font-weight: 800; }}
-    </style>
-
-    <div class="hf-container">
-        <div class="hf-header">
-            <div>
-                <h1 class="hf-title">"{query}"</h1>
-                <div class="hf-meta">Vibe: {theme['name']}</div>
-            </div>
-            <a href="{share_url_x}" target="_blank" style="color:white; text-decoration:none; opacity:0.7;">Share on X ↗</a>
-        </div>
-    """
-
-    for _, row in df_results.iterrows():
-        img_url = row['image'] if row['image'] else "https://via.placeholder.com/150"
-        btn = f'<a href="{row["spotify_url"]}" target="_blank" class="play-btn">PLAY</a>' if row['spotify_url'] else '<span style="opacity:0.5">No Link</span>'
-        
-        html += f"""
-        <div class="track-row">
-            <div style="font-weight:800; font-size:1.2rem; min-width:50px; text-align:center; color:{theme['text']}">{row['match_score']}%</div>
-            <img src="{img_url}" class="cover-img">
-            <div class="info-col">
-                <span class="song-name">{row['song']}</span>
-                <span style="opacity:0.8">{row['artist']}</span>
-            </div>
-            {btn}
-        </div>
-        """
-    html += "</div>"
-    return html
-
-# ---------------------------------------------------------
-# 6. LAUNCH
-# ---------------------------------------------------------
-css = """
-.search-row { align-items: center !important; gap: 15px !important; }
-.search-input textarea { font-size: 1.1rem !important; }
-.action-btn { height: 50px !important; border-radius: 12px !important; font-weight: bold !important; }
-"""
-
-#theme = gr.themes.Soft(primary_hue="zinc", neutral_hue="zinc").set(
-    #body_background_fill="#000000", block_background_fill="#121212", block_border_width="0px"
-#)
-
-with gr.Blocks(css=css, title="HarmoniFind") as demo:
-    gr.HTML("""
-    <div style="text-align:center; padding: 40px 0; color:white;">
-        <h1 style="font-size: 3rem; font-weight:900; background: -webkit-linear-gradient(45deg, #eee, #999); -webkit-background-clip: text; -webkit-text-fill-color: transparent;">HarmoniFind</h1>
-        <p style="opacity: 0.6;">AI-Powered Semantic Music Discovery</p>
-    </div>
-    """)
-
-    with gr.Row(elem_classes="search-row"):
-        input_box = gr.Textbox(show_label=False, placeholder="Describe a vibe (e.g. 'Driving fast at night')...", scale=10, elem_classes="search-input")
-        surprise_btn = gr.Button("🎲", scale=1, variant="secondary", elem_classes="action-btn")
-        search_btn = gr.Button("Search", scale=2, variant="primary", elem_classes="action-btn")
-
-    out = gr.HTML()
-
-    input_box.submit(gradio_interface_fn, input_box, out)
-    search_btn.click(gradio_interface_fn, input_box, out)
-    surprise_btn.click(lambda: get_random_vibe(), None, input_box)
-
-demo.queue().launch()