update

app.py

@@ -1,10 +1,12 @@
 import inspect
 import json
 import os
+from io import BytesIO
 
 import gradio as gr
 import pandas as pd
 import requests
+from PIL import Image
 from smolagents import (
     CodeAgent,
     DuckDuckGoSearchTool,
@@ -23,6 +25,36 @@ from smolagents import (
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 
+@tool
+def get_image_content(file_name: str) -> Image.Image | None:
+    """
+    A tool that load the content of an image.
+    Args:
+        file_name: File name to load.
+    """
+    from io import BytesIO
+
+    import requests
+    from PIL import Image
+
+    try:
+        # Construct the API endpoint URL for file retrieval
+        file_url = f"{DEFAULT_API_URL}/files/{file_name}"
+
+        # Make GET request to retrieve file contents
+        response = requests.get(file_url, timeout=30)
+        response.raise_for_status()
+
+        image = Image.open(BytesIO(response.content)).convert("RGB")
+        # Return the file contents as text
+        return image
+
+    except requests.exceptions.RequestException as e:
+        print(f"Error retrieving file '{file_name}': {e}")
+    except Exception as e:
+        print(f"Unexpected error retrieving file '{file_name}': {e}")
+
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
@@ -44,14 +76,16 @@ class BasicAgent:
                 "markdownify",
                 "wikipedia",
                 "pandas",
+                "io",
+                "PIL",
             ],
         )
 
-    def __call__(self, question: str) -> str:
+    def __call__(self, question: str, file_name: str) -> str:
         print(f"Agent received question: {question}")
         prompt = f"""
             Answer the following question: 
-               "{question}"
+               "{question} {", with the following file: " if file_name else ""} {file_name}"
             
             Please follow hints below:
                 1. `wikipedia` Python package is provided to interact with Wikipedia.
@@ -127,11 +161,12 @@ def run_and_submit_all(questions_index: str, profile: gr.OAuthProfile | None):
         print(f"Question data: {json.dumps(item)}")
         task_id = item.get("task_id")
         question_text = item.get("question")
+        file_name = item.get("file_name")
         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)
+            submitted_answer = agent(question_text, file_name)
             answers_payload.append(
                 {"task_id": task_id, "submitted_answer": submitted_answer}
             )

requirements.txt

@@ -7,3 +7,4 @@ markdownify
 wikipedia
 pandas
 openai
+PIL