fixes

app.py

@@ -1,139 +1,73 @@
 import os
-import gradio as gr
 import requests
-import pandas as pd
-
-from agent import create_agent, fetch_random_question
-
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+from smolagents import CodeAgent, tool, OpenAIServerModel
+
+# ------------------------
+# Constants
+# ------------------------
+API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# ------------------------
+# Tool definitions
+# ------------------------
+@tool
+def fetch_questions() -> list:
     """
-    Fetch all questions, run the SmolAgent on them, submit all answers,
-    and display the results.
+    Fetch the full list of GAIA evaluation questions.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID")
-
-    if profile:
-        username = 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 SmolAgent
-    try:
-        agent = create_agent()
-        print("SmolAgent initialized.")
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-
-    # Code link for verification
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch all 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 Exception as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-
-    # 3. Run agent on each question
-    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 invalid item: {item}")
-            continue
-        try:
-            answer = agent.run(question=question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Answer": answer})
-        except Exception as e:
-            print(f"Error on task {task_id}: {e}")
-            results_log.append({"Task ID": task_id, "Question": question_text, "Answer": f"ERROR: {e}"})
-
-    if not answers_payload:
-        return "Agent produced no answers.", pd.DataFrame(results_log)
-
-    # 4. Submit answers
-    payload = {"username": username, "agent_code": agent_code, "answers": answers_payload}
-    print(f"Submitting {len(answers_payload)} answers...")
-    try:
-        resp = requests.post(submit_url, json=payload, timeout=60)
-        resp.raise_for_status()
-        data = resp.json()
-        status = (
-            f"Submission Successful!\n"
-            f"User: {data.get('username')}\n"
-            f"Score: {data.get('score')}% ({data.get('correct_count')}/{data.get('total_attempted')})\n"
-            f"Message: {data.get('message')}"
-        )
-        return status, pd.DataFrame(results_log)
-    except Exception as e:
-        print(f"Submission error: {e}")
-        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+    response = requests.get(f"{API_URL}/questions", timeout=15)
+    response.raise_for_status()
+    return response.json()
 
-
-def test_random_question(profile: gr.OAuthProfile | None):
+@tool
+def fetch_random_question() -> dict:
     """
-    Fetch a random GAIA question and get the agent's answer for testing.
+    Fetch a single random GAIA question.
     """
-    if not profile:
-        return "Please login to test.", ""
-
-    try:
-        q = fetch_random_question()
-        agent = create_agent()
-        ans = agent.run(question=q.get('question', ''))
-        return q.get('question', ''), ans
-    except Exception as e:
-        print(f"Test error: {e}")
-        return f"Error: {e}", ""
+    response = requests.get(f"{API_URL}/random-question", timeout=15)
+    response.raise_for_status()
+    return response.json()
 
+@tool
+def fetch_file(task_id: str) -> bytes:
+    """
+    Download a file associated with a given task_id.
+    """
+    response = requests.get(f"{API_URL}/files/{task_id}", timeout=15)
+    response.raise_for_status()
+    return response.content
 
-# --- Build Gradio Interface ---
-with gr.Blocks() as demo:
-    gr.Markdown("# SmolAgent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Clone this space and define your agent logic in agent.py.
-        2. Log in with your Hugging Face account.
-        3. Use 'Run Evaluation & Submit All Answers' or 'Test Random Question'.
-        """
+@tool
+def submit_answers(username: str, agent_code: str, answers: list) -> dict:
+    """
+    Submit the agent's answers to GAIA and return the scoring.
+    """
+    payload = {
+        "username": username,
+        "agent_code": agent_code,
+        "answers": answers
+    }
+    response = requests.post(f"{API_URL}/submit", json=payload, timeout=60)
+    response.raise_for_status()
+    return response.json()
+
+# ------------------------
+# Agent factory
+# ------------------------
+def create_agent() -> CodeAgent:
+    """
+    Factory that returns a configured CodeAgent instance.
+    Requires OPENAI_API_KEY in environment.
+    """
+    # Initialize the LLM with OpenAI API
+    llm = OpenAIServerModel(
+        model_id=os.getenv("OPENAI_MODEL_ID", "gpt-3.5-turbo"),
+        api_key=os.getenv("OPENAI_API_KEY")
     )
+    # Create agent with defined tools
+    agent = CodeAgent(
+        tools=[fetch_questions, fetch_random_question, fetch_file, submit_answers],
+        model=llm
+    )
+    return agent
 
-    login = gr.LoginButton()
-    run_all_btn = gr.Button("Run Evaluation & Submit All Answers")
-    test_btn = gr.Button("Test Random Question")
-
-    status_box = gr.Textbox(label="Status / Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Full Results Table", wrap=True)
-    question_box = gr.Textbox(label="Random Question", lines=3, interactive=False)
-    answer_box = gr.Textbox(label="Agent Answer", lines=3, interactive=False)
-
-    run_all_btn.click(fn=run_and_submit_all, inputs=[login], outputs=[status_box, results_table])
-    test_btn.click(fn=test_random_question, inputs=[login], outputs=[question_box, answer_box])
-
-if __name__ == "__main__":
-    demo.launch(debug=True, share=False)