Upload app.py

app.py

@@ -143,26 +143,42 @@ def load_embeddings(embeddings_path):
     print(f"Loaded {len(ingredients_embeddings)} ingredient embeddings")
     return ingredients_embeddings
 
-def categorize_products_from_text(product_text, embeddings, progress=gr.Progress(), top_n=5, confidence_threshold=0.5):
+# Define a safe progress tracker that handles None
+class SafeProgress:
+    def __init__(self, progress_obj=None):
+        self.progress = progress_obj
+    
+    def __call__(self, value, desc=""):
+        if self.progress is not None:
+            try:
+                self.progress(value, desc=desc)
+            except:
+                print(f"Progress {value}: {desc}")
+        else:
+            print(f"Progress {value}: {desc}")
+
+def categorize_products_from_text(product_text, top_n=5, confidence_threshold=0.5, progress=None):
     """Categorize products from text input (one product per line)"""
+    # Create a safe progress tracker
+    progress_tracker = SafeProgress(progress)
+    progress_tracker(0, desc="Starting...")
+    
     # Parse input text to get product names
     product_names = [line.strip() for line in product_text.split("\n") if line.strip()]
     
     if not product_names:
         return "No product names provided."
     
-    progress(0, desc="Starting...")
-    
     # Create product embeddings
-    progress(0.1, desc="Generating product embeddings...")
+    progress_tracker(0.1, desc="Generating product embeddings...")
     products_embeddings = create_product_embeddings_voyageai(product_names)
     
     # Compute similarities
-    progress(0.6, desc="Computing similarities...")
+    progress_tracker(0.6, desc="Computing similarities...")
     all_similarities = compute_similarities(embeddings, products_embeddings)
     
     # Format results
-    progress(0.9, desc="Formatting results...")
+    progress_tracker(0.9, desc="Formatting results...")
     results = {}
     for product, similarities in all_similarities.items():
         # Filter by confidence threshold and take top N
@@ -183,12 +199,14 @@ def categorize_products_from_text(product_text, embeddings, progress=gr.Progress
             output_text += "  No matching categories found.\n"
         output_text += "\n"
     
-    progress(1.0, desc="Done!")
+    progress_tracker(1.0, desc="Done!")
     return output_text
 
-def categorize_products_from_file(file, embeddings, progress=gr.Progress(), top_n=5, confidence_threshold=0.5):
+def categorize_products_from_file(file, top_n=5, confidence_threshold=0.5, progress=None):
     """Categorize products from a JSON file"""
-    progress(0.1, desc="Reading file...")
+    # Create a safe progress tracker
+    progress_tracker = SafeProgress(progress)
+    progress_tracker(0.1, desc="Reading file...")
     
     try:
         with open(file.name, 'r') as f:
@@ -215,15 +233,15 @@ def categorize_products_from_file(file, embeddings, progress=gr.Progress(), top_
         return "No product names found in the file."
     
     # Create product embeddings
-    progress(0.2, desc="Generating product embeddings...")
+    progress_tracker(0.2, desc="Generating product embeddings...")
     products_embeddings = create_product_embeddings_voyageai(product_names)
     
     # Compute similarities
-    progress(0.7, desc="Computing similarities...")
+    progress_tracker(0.7, desc="Computing similarities...")
     all_similarities = compute_similarities(embeddings, products_embeddings)
     
     # Format results
-    progress(0.9, desc="Formatting results...")
+    progress_tracker(0.9, desc="Formatting results...")
     output_text = f"Found {len(product_names)} products in file.\n\n"
     
     for product, similarities in all_similarities.items():
@@ -240,13 +258,28 @@ def categorize_products_from_file(file, embeddings, progress=gr.Progress(), top_
             output_text += "  No matching categories found.\n"
         output_text += "\n"
     
-    progress(1.0, desc="Done!")
+    progress_tracker(1.0, desc="Done!")
     return output_text
 
+# Load embeddings at the module level for easier access
+try:
+    embeddings_path = "ingredient_embeddings_voyageai.pkl"
+    embeddings = load_embeddings(embeddings_path)
+except Exception as e:
+    print(f"Warning: Could not load embeddings at startup: {e}")
+    print("Will attempt to load them when the app runs")
+    embeddings = {}
+
 # ===== Gradio Interface Setup =====
 def create_interface(embeddings_path="ingredient_embeddings_voyageai.pkl"):
-    # Load embeddings once at startup
-    embeddings = load_embeddings(embeddings_path)
+    # Ensure embeddings are loaded
+    global embeddings
+    if not embeddings:
+        try:
+            embeddings = load_embeddings(embeddings_path)
+        except Exception as e:
+            print(f"Error loading embeddings: {e}")
+            gr.Error(f"Failed to load embeddings file: {e}")
     
     # Text input interface
     with gr.Blocks() as demo:
@@ -282,9 +315,7 @@ def create_interface(embeddings_path="ingredient_embeddings_voyageai.pkl"):
                         text_output = gr.Textbox(label="Categorization Results", lines=20)
                 
                 submit_button.click(
-                    fn=lambda text, top_n, conf, prog: categorize_products_from_text(
-                        text, embeddings, prog, top_n, conf
-                    ),
+                    fn=categorize_products_from_text,
                     inputs=[text_input, top_n, confidence],
                     outputs=text_output
                 )
@@ -313,9 +344,7 @@ def create_interface(embeddings_path="ingredient_embeddings_voyageai.pkl"):
                         file_output = gr.Textbox(label="Categorization Results", lines=20)
                 
                 file_button.click(
-                    fn=lambda file, top_n, conf, prog: categorize_products_from_file(
-                        file, embeddings, prog, top_n, conf
-                    ),
+                    fn=categorize_products_from_file,
                     inputs=[file_input, file_top_n, file_confidence],
                     outputs=file_output
                 )