Update app.py

app.py

@@ -18,6 +18,73 @@ def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return
     """
     return "What magic will you build ?"
 
+@tool
+def simple_object_detection(image_path: str, confidence_threshold: float) -> str:
+    """
+    A tool that performs simple object detection on an image using MobileNet SSD with error handling.
+    
+    Args:
+        image_path: Path to the input image.
+        confidence_threshold: Minimum confidence (e.g., 0.2) to filter weak detections.
+    
+    Returns:
+        A string indicating the location of the saved processed image or an error message.
+    """
+    try:
+        # List of class labels MobileNet SSD was trained on
+        classes = ["background", "aeroplane", "bicycle", "bird", "boat",
+                   "bottle", "bus", "car", "cat", "chair", "cow",
+                   "diningtable", "dog", "horse", "motorbike", "person",
+                   "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+
+        # Paths to the pre-trained model files (ensure these files are downloaded)
+        prototxt_path = "MobileNetSSD_deploy.prototxt.txt"
+        model_path = "MobileNetSSD_deploy.caffemodel"
+        
+        # Load the pre-trained model from disk
+        net = cv2.dnn.readNetFromCaffe(prototxt_path, model_path)
+        
+        # Load the image and get its dimensions
+        image = cv2.imread(image_path)
+        if image is None:
+            return f"Error: Image at {image_path} could not be loaded."
+        (h, w) = image.shape[:2]
+        
+        # Prepare the image as a blob for the network
+        blob = cv2.dnn.blobFromImage(cv2.resize(image, (300, 300)), 
+                                     scalefactor=0.007843, size=(300, 300), 
+                                     mean=127.5)
+        
+        # Pass the blob through the network to obtain detections
+        net.setInput(blob)
+        detections = net.forward()
+        
+        # Loop over the detections and draw bounding boxes for those above the threshold
+        for i in range(0, detections.shape[2]):
+            confidence = detections[0, 0, i, 2]
+            if confidence > confidence_threshold:
+                idx = int(detections[0, 0, i, 1])
+                # Compute bounding box coordinates
+                box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
+                (startX, startY, endX, endY) = box.astype("int")
+                
+                # Draw the bounding box and label on the image
+                label = f"{classes[idx]}: {confidence * 100:.2f}%"
+                cv2.rectangle(image, (startX, startY), (endX, endY), (0, 255, 0), 2)
+                y = startY - 10 if startY - 10 > 10 else startY + 20
+                cv2.putText(image, label, (startX, y),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+        
+        # Save the output image
+        output_path = "output.jpg"
+        cv2.imwrite(output_path, image)
+        
+        return f"Processed image saved as {output_path}"
+    
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+
 @tool
 def get_current_time_in_timezone(timezone: str) -> str:
     """A tool that fetches the current local time in a specified timezone.
@@ -55,7 +122,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[DuckDuckGoSearchTool(), final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,