printing extracted text7

main.py

@@ -121,6 +121,30 @@ logging.basicConfig(
 )
 logger = logging.getLogger(__name__)
 
+def get_or_load_model(model_name):
+    """Get a model from cache or load it if not present"""
+    if model_name not in global_models:
+        try:
+            if model_name == 'fasttext':
+                from gensim.models import KeyedVectors
+                log_print(f"Loading {model_name} model...")
+                model_path = os.path.join(gensim_data_dir, 'fasttext-wiki-news-subwords-300', 'fasttext-wiki-news-subwords-300.gz')
+                if not os.path.exists(model_path):
+                    from gensim.downloader import load
+                    log_print("Downloading fasttext model...")
+                    global_models[model_name] = load('fasttext-wiki-news-subwords-300')
+                else:
+                    global_models[model_name] = KeyedVectors.load_word2vec_format(model_path)
+                log_print(f"Successfully loaded {model_name} model")
+            elif model_name == 'llm':
+                # Implement LLM model loading here
+                log_print("LLM model loading not implemented", "WARNING")
+                return None
+        except Exception as e:
+            log_print(f"Error loading {model_name} model: {e}", "ERROR")
+            raise
+    return global_models.get(model_name)
+
 def initialize_resources():
     """Initialize all required resources"""
     try:
@@ -766,30 +790,6 @@ def allowed_file(filename, allowed_extensions):
     return '.' in filename and \
            filename.rsplit('.', 1)[1].lower() in allowed_extensions
 
-def get_or_load_model(model_name):
-    """Get a model from cache or load it if not present"""
-    if model_name not in global_models:
-        try:
-            if model_name == 'fasttext':
-                from gensim.models import KeyedVectors
-                log_print(f"Loading {model_name} model...")
-                model_path = os.path.join(gensim_data_dir, 'fasttext-wiki-news-subwords-300', 'fasttext-wiki-news-subwords-300.gz')
-                if not os.path.exists(model_path):
-                    from gensim.downloader import load
-                    log_print("Downloading fasttext model...")
-                    global_models[model_name] = load('fasttext-wiki-news-subwords-300')
-                else:
-                    global_models[model_name] = KeyedVectors.load_word2vec_format(model_path)
-                log_print(f"Successfully loaded {model_name} model")
-            elif model_name == 'llm':
-                # Implement LLM model loading here
-                log_print("LLM model loading not implemented", "WARNING")
-                return None
-        except Exception as e:
-            log_print(f"Error loading {model_name} model: {e}", "ERROR")
-            raise
-    return global_models.get(model_name)
-
 def wait_for_initialization():
     """Wait for initialization to complete"""
     initialization_complete.wait()