Update app.py

app.py

@@ -32,18 +32,18 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 #     def forward(self, image: Image.Image) -> str:
 #         return "This is a placeholder caption for the uploaded image."
 
-# class ImageCaptioningTool(Tool):
-#     name = "image_captioner"
-#     description = "Generate a caption for an image."
-#     inputs = {"image": "image"}
-#     output_type = "text"
+class ImageCaptioningTool(Tool):
+    name = "image_captioner"
+    description = "Generate a caption for an image."
+    inputs = {"image": "image"}
+    output_type = "text"
     
-#     def run(self, inputs: dict) -> str:
-#         image = inputs.get("image")
-#         if not image:
-#             return "No image provided."
-#         # You could run your model here instead
-#         return "This is a placeholder caption for the uploaded image."
+    def run(self, inputs: dict) -> str:
+        image = inputs.get("image")
+        if not image:
+            return "No image provided."
+        # You could run your model here instead
+        return "This is a placeholder caption for the uploaded image."
         
 class BasicAgent:
     def __init__(self):
@@ -54,7 +54,7 @@ class BasicAgent:
                 WikipediaSearchTool(user_agent="my-agent", language="en"),
                 PythonInterpreterTool(),
                 UserInputTool(),
-                # ImageCaptioningTool(),
+                ImageCaptioningTool(),
             ],
         model=model,
         system_prompt="""
@@ -148,20 +148,37 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
+
+#     question_text = item.get("question")
+# question_input = {"question": question_text}
+# if "image" in item:
+#     question_input["image"] = item["image"]
+# submitted_answer = agent(question_input)
     # 3. Run your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
     for item in questions_data:
         task_id = item.get("task_id")
+        # question_text = item.get("question")
+        # if not task_id or question_text is None:
+        #     print(f"Skipping item with missing task_id or question: {item}")
+        #     continue
+        # try:
+        #     submitted_answer = agent(question_text)
+        #     answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+        #     results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         question_text = item.get("question")
+        image = item.get("image", None)
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            question_input = {"question": question_text}
+            if image:
+                question_input["image"] = image
+            submitted_answer = agent(question_input)
+            
         except Exception as e:
              print(f"Error running agent on task {task_id}: {e}")
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})