Update app.py

app.py

@@ -10,7 +10,7 @@ from PIL import Image
 from io import BytesIO
 import base64
 from smolagents import load_tool
-from typing import Dict
+from typing import Any
 
 model = InferenceClientModel("qwen/Qwen2.5-0.5B-Instruct",
                             max_tokens=512,
@@ -40,7 +40,7 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 class ImageCaptioningTool(Tool):
     name = "image_captioner"
     description = "Generate a caption for an image."
-    inputs = {"image": Dict, "question": "str"} 
+    inputs = {"image": Any, "question": "str"} 
     output_type = "text"
     
     def run(self, inputs: dict) -> str:
@@ -75,12 +75,7 @@ tools = [
 # ---------------------- MAIN LOGIC ---------------------- #
 
 class BasicAgent:
-    def __init__(self):
-        model = InferenceClientModel(
-            "qwen/Qwen2.5-0.5B-Instruct",
-            max_tokens=512
-
-        )
+    def __init__(self, model, tools):
         self.agent = CodeAgent(
             tools = tools,
             model=model
@@ -91,7 +86,9 @@ class BasicAgent:
     def __call__(self, question):
         if isinstance(question, dict):
             text = question.get("question", "")
-            # ignoring image context for now since agent.run doesn't support it
+            image = question.get("image", None)
+            if image:
+                question["image"] = {"type": "pil", "data": image}
         else:
             text = question