Update app.py

app.py

@@ -1,87 +1,304 @@
-import gradio as gr
-import json
+import os
 import pandas as pd
-from smolagents import CodeAgent
-from smolagents.models import InferenceClientModel
-from smolagents.tools import (
-    DuckDuckGoSearchTool,
-    WikipediaSearchTool,
-    PythonInterpreterTool,
-    UserInputTool,
+import requests
+import smolagents
+print("SmolAgents version:", smolagents.__version__)
+from smolagents import Tool, CodeAgent, InferenceClientModel, load_tool
+from smolagents import DuckDuckGoSearchTool, WikipediaSearchTool, PythonInterpreterTool, UserInputTool
+import gradio as gr
+from PIL import Image
+from io import BytesIO
+import base64
+
+
+
+model = InferenceClientModel("qwen/Qwen2.5-0.5B-Instruct",
+                            max_tokens=512,
+                            system_message="""
+You are a highly capable AI assistant designed to solve real-world, multi-step reasoning tasks in the GAIA benchmark.
+Your job is to:
+- Search the web or Wikipedia if needed
+- Perform Python calculations or date arithmetic
+Instructions:
+1. Think step-by-step and use tools wisely.
+2. Always return a short, direct answer — no explanation or formatting.
+Examples:
+- Q: What is the capital of France?
+- A: Paris
+Your output must be: a single clean answer string only.
+"""
 )
 
-# Define the model
-model = InferenceClientModel(
-    model_id="Qwen/Qwen1.5-1.8B-Chat",  # Ensure this is a model that supports system_message
-    system_message="You are a helpful academic assistant tasked with solving student questions accurately.",
-    max_tokens=512,
-)
 
-# Define tools
-tools = [
-    DuckDuckGoSearchTool(),
-    WikipediaSearchTool(),
+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": "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."
+
+
+# ---------------------- TOOL CONFIGURATION ---------------------- #
+tools=[
+    DuckDuckGoSearchTool(max_results=5, rate_limit=2.0),
+    WikipediaSearchTool(user_agent="my-agent", language="en"),
     PythonInterpreterTool(),
     UserInputTool(),
+    ImageCaptioningTool(),
 ]
 
-# Initialize agent
-agent = CodeAgent(model=model, tools=tools)
 
-# Run agent on uploaded question set
-def run_agent(file):
-    results_log = []
-    answers_payload = []
+# # ---------------------- AGENT SETUP ---------------------- #
+# agent = CodeAgent(
+#     model = model,
+#     tools = tools,
+# )
+
+# ---------------------- MAIN LOGIC ---------------------- #
+
+class BasicAgent:
+    def __init__(self):
+        model = InferenceClientModel(
+            "qwen/Qwen2.5-0.5B-Instruct",
+            max_tokens=512
 
+        )
+        self.agent = CodeAgent(
+            tools = tools,
+            model=model
+        
+        )
+        print("BasicAgent initialized.")
+        # print("Available tools:", [tool.name for tool in self.agent.tools])
+    def __call__(self, question):
+        if isinstance(question, dict):
+            text = question.get("question", "")
+            # ignoring image context for now since agent.run doesn't support it
+        else:
+            text = question
+    
+        print(f"Agent received question (first 50 chars): {text[:50]}...")
+        answer = self.agent.run(text)
+        return answer.strip()
+
+
+
+    
+def run_agent_on_image(image):
     try:
-        with open(file.name, "r", encoding="utf-8") as f:
-            questions_data = json.load(f)
+        # Wrap image as expected by the agent tool
+        response = agent("Describe this image", inputs={"image": image})
+        return response
     except Exception as e:
-        return f"Error reading JSON file: {e}", pd.DataFrame()
+        return f"Error: {e}"
+
+# iface = gr.Interface(fn=run_agent_on_image, inputs=gr.Image(type="pil"), outputs="text")
+# iface.launch()
 
-    print(f"Running agent on {len(questions_data)} questions...")
 
+           
+def run_and_submit_all( profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+
+    if profile:
+        username= f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # 1. Instantiate Agent ( modify this part to create your agent)
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+             print("Fetched questions list is empty.")
+             return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        return f"Error fetching questions: {e}", None
+    except requests.exceptions.JSONDecodeError as e:
+         print(f"Error decoding JSON response from questions endpoint: {e}")
+         print(f"Response text: {response.text[:500]}")
+         return f"Error decoding server response for questions: {e}", None
+    except Exception as e:
+        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 = item.get("question")
-
-        if not task_id or question is None:
-            results_log.append({
-                "Task ID": task_id if task_id else "MISSING",
-                "Question": question if question else "MISSING",
-                "Submitted Answer": "Invalid entry",
-            })
+        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:
-            answer = agent(question)
-            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
-            results_log.append({"Task ID": task_id, "Question": question, "Submitted Answer": answer})
+            question_input = {"question": question_text}
+            if image:
+                try:
+                    image_bytes = base64.b64decode(image)
+                    pil_image = Image.open(BytesIO(image_bytes))
+                    question_input["image"] = pil_image
+                except Exception as e:
+                    print(f"Failed to decode image for task {task_id}: {e}")
+
+            submitted_answer = agent(question_input)
+    
+            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})
+    
         except Exception as e:
-            error_msg = f"AGENT ERROR: {e}"
-            print(error_msg)
-            results_log.append({"Task ID": task_id, "Question": question, "Submitted Answer": error_msg})
+            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}"})
 
     if not answers_payload:
+        print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    return "Success! Answers submitted.", pd.DataFrame(results_log)
-
-# Create Gradio UI
-demo = gr.Interface(
-    fn=run_agent,
-    inputs=gr.File(label="Upload your questions.json"),
-    outputs=[
-        gr.Textbox(label="Status"),
-        gr.Dataframe(label="Submitted Answers")
-    ],
-    title="Academic Assistant Agent",
-    description="Upload a .json file with questions and task_ids to run the agent.",
-)
+    # 4. Prepare Submission 
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    print(status_update)
 
-if __name__ == "__main__":
-    demo.launch()
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    try:
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        final_status = (
+            f"Submission Successful!\n"
+            f"User: {result_data.get('username')}\n"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Message: {result_data.get('message', 'No message received.')}"
+        )
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+        except requests.exceptions.JSONDecodeError:
+            error_detail += f" Response: {e.response.text[:500]}"
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.Timeout:
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.RequestException as e:
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except Exception as e:
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        ---
+        **Disclaimers:**
+        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
+        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    # Removed max_rows=10 from DataFrame constructor
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
 
+if __name__ == "__main__":
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    # Check for SPACE_HOST and SPACE_ID at startup for information
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    if space_id_startup: # Print repo URLs if SPACE_ID is found
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)
 # import os
 # import pandas as pd
 # import requests