Update app.py

app.py

@@ -27,32 +27,55 @@ vision_pipe = pipeline(
 print("📚 Loading Embedding Engine...")
 embed_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-# --- BOTTLE DETECTION (YOLO) ---
+# --- BOTTLE DETECTION (DEBUG MODE) ---
 def get_bottle_crops(image_path):
+    print(f"🔍 DEBUG: Starting YOLO on {image_path}")
+    found_crops = []
+    
     try:
-        yolo_model = YOLO("yolov8n.pt")
-        results = yolo_model(image_path, verbose=False)
-        found_crops = []
+        # Load original to verify path
         original_img = Image.open(image_path)
+        
+        # Initialize YOLO (weights download automatically)
+        yolo_model = YOLO("yolov8n.pt")
+        
+        # Lower confidence to 0.1 to catch even partial bottles
+        results = yolo_model(image_path, verbose=True, conf=0.1)
+        
         for r in results:
             for box in r.boxes:
-                if int(box.cls) == 39: # Bottle index
+                if int(box.cls) == 39: # Bottle
                     x1, y1, x2, y2 = box.xyxy[0].tolist()
                     w, h = original_img.size
-                    # Add margin for context
+                    
+                    # Pad the crop by 20px so we don't cut off text
                     x1, y1 = max(0, x1 - 20), max(0, y1 - 20)
                     x2, y2 = min(w, x2 + 20), min(h, y2 + 20)
-                    found_crops.append(original_img.crop((x1, y1, x2, y2)))
+                    
+                    crop = original_img.crop((x1, y1, x2, y2))
+                    found_crops.append(crop)
+
         del yolo_model
         gc.collect()
+
+        # FALLBACK: If YOLO misses, return the full image so the AI has SOMETHING to look at
+        if not found_crops:
+            print("⚠️ DEBUG: No bottles found. Returning full image.")
+            return [original_img]
+            
         return found_crops
+
     except Exception as e:
-        print(f"YOLO Error: {e}")
-        return []
+        print(f"❌ YOLO CRASH: {e}")
+        try:
+            return [Image.open(image_path)]
+        except:
+            return []
 
 # --- RECIPE INGESTION ---
 def ingest_recipes(files):
     if not files: return "❌ No files uploaded."
+    
     docs = []
     for f in files:
         try:
@@ -65,7 +88,8 @@ def ingest_recipes(files):
         except Exception as e:
             print(f"Error loading {f.name}: {e}")
             
-    if not docs: return "❌ Could not extract text."
+    if not docs:
+        return "❌ Could not extract text from files."
 
     vector_store = Chroma.from_documents(
         documents=docs, 
@@ -76,9 +100,14 @@ def ingest_recipes(files):
 
 # --- BARTENDER LOGIC ---
 def bartend(message, history, img_path, inventory):
+    debug_images = []
+    
     # 1. Vision Scanning
     if img_path:
         crops = get_bottle_crops(img_path)
+        debug_images = crops # Save crops to show in the gallery
+        
+        # Use the first crop (or full image if fallback triggered)
         target_img = crops[0] if crops else Image.open(img_path)
         
         prompt_text = "User: <image>\nWhat is the brand and type of alcohol in this image? Answer briefly.\nAssistant:"
@@ -92,6 +121,7 @@ def bartend(message, history, img_path, inventory):
             else:
                 inventory = raw_label.replace(prompt_text, "").strip()
             
+            # Clean up punctuation
             inventory = re.sub(r'<.*?>', '', inventory).strip().split('.')[0]
             
         except Exception as e:
@@ -100,6 +130,7 @@ def bartend(message, history, img_path, inventory):
 
     # 2. RAG (Recipe Search)
     recipe_context = ""
+    # Only search if we have a valid spirit name
     if inventory and inventory not in ["Empty Shelf", "Unknown Spirit", ""]:
         try:
             if os.path.exists(CHROMA_PATH):
@@ -110,19 +141,20 @@ def bartend(message, history, img_path, inventory):
         except Exception as e:
             print(f"Search error: {e}")
 
-    # 3. Create the Response
+    # 3. Create Response
     if inventory == "Unknown Spirit":
-        response = "I'm having trouble reading that label. Try taking a closer photo of just the brand name."
+        response = "I'm having trouble reading that label. Check the 'Vision Debug' gallery below—is the crop clear?"
     elif recipe_context:
-        response = f"I see you have **{inventory}**. Here is a recipe from your collection:\n\n{recipe_context}"
+        response = f"I see you have **{inventory}**. Here is a recipe I found in your collection:\n\n{recipe_context}"
     else:
-        response = f"I see you have **{inventory}**! I don't have a specific recipe for that in the library yet."
+        response = f"I see you have **{inventory}**! I don't have a specific recipe for that in the current library. Should I suggest a classic drink?"
 
-    # Standard Dictionary Format for Gradio 6.0
+    # Add to chat history (Dictionary format for Gradio 6.0)
     history.append({"role": "user", "content": message})
     history.append({"role": "assistant", "content": response})
 
-    return history, inventory
+    # Return 3 items: History, Inventory State, and the Debug Images
+    return history, inventory, debug_images
 
 # --- UI LAYOUT ---
 with gr.Blocks() as demo:
@@ -134,20 +166,25 @@ with gr.Blocks() as demo:
             file_up = gr.File(label="1. Upload Recipe PDFs/TXTs", file_count="multiple")
             ingest_btn = gr.Button("📥 Load Recipes into Memory")
             status = gr.Textbox(label="System Status", value="Ready")
+            
             gr.Markdown("---")
             img = gr.Image(type="filepath", label="2. Photo of your Bottle")
             
+            # VISION DEBUG (Restored)
+            with gr.Accordion("🔍 Vision Debug (See what the AI sees)", open=True):
+                debug_gallery = gr.Gallery(label="YOLO Crops", columns=2, height="auto")
+            
         with gr.Column(scale=2):
-            # FIXED LINE BELOW: Removed type="messages"
             chatbot = gr.Chatbot(height=500, label="Bartender Chat")
             msg = gr.Textbox(label="3. Your Message", placeholder="Ask for a drink suggestion...")
             send_btn = gr.Button("Mix It Up", variant="primary")
 
-    # Connect the buttons
+    # Event Wiring
     ingest_btn.click(ingest_recipes, file_up, status)
-    msg.submit(bartend, [msg, chatbot, img, inv_state], [chatbot, inv_state])
-    send_btn.click(bartend, [msg, chatbot, img, inv_state], [chatbot, inv_state])
+    
+    # Both inputs trigger the same function with 3 outputs
+    msg.submit(bartend, [msg, chatbot, img, inv_state], [chatbot, inv_state, debug_gallery])
+    send_btn.click(bartend, [msg, chatbot, img, inv_state], [chatbot, inv_state, debug_gallery])
 
 if __name__ == "__main__":
-    # Theme moved here for Gradio 6.0 compatibility
     demo.launch(theme=gr.themes.Soft())