Create app.py

app.py

@@ -0,0 +1,165 @@
+"""
+HarmoniFind Gradio Backend
+Deploy this to Hugging Face Spaces or run locally
+
+To deploy to Hugging Face Spaces:
+1. Create account at https://huggingface.co
+2. Create new Space with Gradio SDK
+3. Upload this file as app.py
+4. Upload your embeddings and index files
+5. Copy the Space URL to your frontend config
+"""
+
+import gradio as gr
+import numpy as np
+from sentence_transformers import SentenceTransformer
+import json
+
+# ============= CONFIGURATION =============
+MODEL_NAME = 'all-mpnet-base-v2'
+MIN_SIMILARITY_THRESHOLD = 0.5
+TOP_K_RESULTS = 10
+
+# ============= LOAD YOUR DATA HERE =============
+# TODO: Replace these with your actual data loading
+# Load your FAISS index, song metadata, and embeddings
+
+# Example structure for your song metadata:
+# songs_metadata = [
+#     {
+#         "title": "Song Title",
+#         "artist": "Artist Name", 
+#         "lyrics": "Full lyrics text...",
+#         "spotify_url": "https://open.spotify.com/track/..."
+#     },
+#     ...
+# ]
+
+# For demo purposes, using mock data:
+songs_metadata = [
+    {
+        "title": "Rise Up",
+        "artist": "Andra Day",
+        "lyrics": "You're broken down and tired, Of living life on a merry go round...",
+        "spotify_url": "https://open.spotify.com/track/4fSlpKIGm3xa5Q0h7r0qVL"
+    },
+    {
+        "title": "Stronger",
+        "artist": "Kelly Clarkson",
+        "lyrics": "What doesn't kill you makes you stronger...",
+        "spotify_url": "https://open.spotify.com/track/0WqIKmW4BTrj3eJFmnCKMv"
+    },
+    {
+        "title": "Fight Song",
+        "artist": "Rachel Platten",
+        "lyrics": "This is my fight song, Take back my life song...",
+        "spotify_url": "https://open.spotify.com/track/4PXLm6TfjCvQsn9PkW78eN"
+    }
+]
+
+# ============= INITIALIZE MODEL =============
+print("Loading sentence transformer model...")
+model = SentenceTransformer(MODEL_NAME)
+
+# TODO: Load your FAISS index
+# import faiss
+# index = faiss.read_index('path_to_your_index.faiss')
+
+# TODO: Load your precomputed embeddings
+# with open('song_embeddings.npy', 'rb') as f:
+#     song_embeddings = np.load(f)
+
+# For demo: compute embeddings on the fly (replace with your pre-computed ones)
+print("Computing embeddings for demo songs...")
+demo_lyrics = [song['lyrics'] for song in songs_metadata]
+song_embeddings = model.encode(demo_lyrics, convert_to_numpy=True)
+song_embeddings = song_embeddings / np.linalg.norm(song_embeddings, axis=1, keepdims=True)
+
+# ============= SEARCH FUNCTION =============
+def search_songs(query: str) -> list:
+    """
+    Perform semantic search on song lyrics
+    
+    Args:
+        query: Text description of desired song characteristics
+        
+    Returns:
+        List of matching songs with similarity scores
+    """
+    if not query or not query.strip():
+        return []
+    
+    try:
+        # Encode the query
+        query_embedding = model.encode([query], convert_to_numpy=True)
+        query_embedding = query_embedding / np.linalg.norm(query_embedding, axis=1, keepdims=True)
+        
+        # Compute similarities (cosine similarity since embeddings are normalized)
+        similarities = np.dot(song_embeddings, query_embedding.T).flatten()
+        
+        # Get top K indices sorted by similarity
+        top_indices = np.argsort(similarities)[::-1][:TOP_K_RESULTS]
+        
+        # Format results and filter by threshold
+        results = []
+        for idx in top_indices:
+            similarity = float(similarities[idx])
+            
+            # Only include results above threshold
+            if similarity >= MIN_SIMILARITY_THRESHOLD:
+                song = songs_metadata[idx]
+                results.append({
+                    "title": song['title'],
+                    "artist": song['artist'],
+                    "similarity": similarity,
+                    "spotifyUrl": song.get('spotify_url', '')
+                })
+        
+        return results
+        
+    except Exception as e:
+        print(f"Error during search: {str(e)}")
+        return []
+
+# ============= GRADIO INTERFACE =============
+def gradio_search(query: str) -> str:
+    """Wrapper function for Gradio that returns JSON string"""
+    results = search_songs(query)
+    return json.dumps(results, indent=2)
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=gradio_search,
+    inputs=gr.Textbox(
+        label="Search Query",
+        placeholder="Describe the song you're looking for...",
+        lines=3
+    ),
+    outputs=gr.JSON(label="Search Results"),
+    title="🎵 HarmoniFind Backend",
+    description=f"""
+    Semantic music search powered by {MODEL_NAME} embeddings.
+    
+    **Current Settings:**
+    - Minimum Similarity: {MIN_SIMILARITY_THRESHOLD * 100}%
+    - Top Results: {TOP_K_RESULTS}
+    - Dataset: {len(songs_metadata)} songs
+    
+    Enter a description of lyrical themes, emotions, or narratives to find matching songs.
+    """,
+    examples=[
+        ["Uplifting song about overcoming personal challenges"],
+        ["Melancholic love song with introspective narrative"],
+        ["Energetic anthem about friendship and loyalty"],
+        ["Reflective song about life transitions and growth"],
+    ],
+    api_name="predict"  # This creates the /api/predict endpoint
+)
+
+# ============= LAUNCH =============
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=False  # Set to True for temporary public link
+    )