Update app.py

app.py

@@ -6,21 +6,28 @@ import json
 from sentence_transformers import SentenceTransformer
 
 def load_data():
-    with h5py.File('path_to_your_embeddings_file.h5', 'r') as f:
-        embeddings = f['embeddings'][:]
-        patent_numbers = f['patent_numbers'][:]
-    
-    metadata = {}
-    with open('path_to_your_metadata_file.jsonl', 'r') as f:
-        for line in f:
-            data = json.loads(line)
-            metadata[data['patent_number']] = data
-    
-    print(f"Embedding shape: {embeddings.shape}")
-    print(f"Number of patent numbers: {len(patent_numbers)}")
-    print(f"Number of metadata entries: {len(metadata)}")
-    
-    return embeddings, patent_numbers, metadata
+    try:
+        with h5py.File('patent_embeddings.h5', 'r') as f:
+            embeddings = f['embeddings'][:]
+            patent_numbers = f['patent_numbers'][:]
+        
+        metadata = {}
+        with open('patent_metadata.jsonl', 'r') as f:
+            for line in f:
+                data = json.loads(line)
+                metadata[data['patent_number']] = data
+        
+        print(f"Embedding shape: {embeddings.shape}")
+        print(f"Number of patent numbers: {len(patent_numbers)}")
+        print(f"Number of metadata entries: {len(metadata)}")
+        
+        return embeddings, patent_numbers, metadata
+    except FileNotFoundError as e:
+        print(f"Error: Could not find file. {e}")
+        raise
+    except Exception as e:
+        print(f"An unexpected error occurred while loading data: {e}")
+        raise
 
 embeddings, patent_numbers, metadata = load_data()