Update app.py

app.py

@@ -1,34 +1,98 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+import re
+from smolagents import CodeAgent, InferenceClientModel, DuckDuckGoSearchTool, VisitWebpageTool, tool
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Tools ---
+@tool
+def calculator(expression: str) -> str:
+    """Evaluates a mathematical expression and returns the result as a string.
+
+    Args:
+        expression: A valid Python math expression e.g. '847 * 293'.
+    """
+    try:
+        result = eval(expression, {"__builtins__": {}}, {})
+        return str(result)
+    except Exception as e:
+        return f"Error: {e}"
+
+
+@tool
+def fetch_task_file(task_id: str) -> str:
+    """Fetches the file associated with a GAIA task by its task ID.
+
+    Args:
+        task_id: The GAIA task ID string.
+    """
+    try:
+        url = f"{DEFAULT_API_URL}/files/{task_id}"
+        resp = requests.get(url, timeout=15)
+        resp.raise_for_status()
+        return resp.text
+    except Exception as e:
+        return f"FETCH_ERROR: {e}"
+
+
+# --- Agent ---
 class BasicAgent:
     def __init__(self):
+        model = InferenceClientModel(
+            model_id="meta-llama/Llama-3.3-70B-Instruct",
+            timeout=120,
+        )
+        self.agent = CodeAgent(
+            tools=[
+                DuckDuckGoSearchTool(),
+                VisitWebpageTool(),
+                calculator,
+                fetch_task_file,
+            ],
+            model=model,
+            max_steps=5,
+            additional_authorized_imports=["json", "re", "datetime", "math"],
+        )
         print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
+
+    def __call__(self, question: str, task_id: str = "") -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
 
-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
+        prompt = f"""
+Question: {question}
+{"Use fetch_task_file(task_id='" + task_id + "') to retrieve the associated file if needed." if task_id else ""}
+
+Rules:
+- Use tools to find the correct answer.
+- Return ONLY the final answer — no explanation, no preamble, no punctuation unless required by the question.
+- If the answer is a number, return only the number.
+- If the answer is a name, return only the name.
+- If the answer is a list, return items separated by commas.
+- Never include the words FINAL ANSWER in your response.
+"""
+        try:
+            result = self.agent.run(prompt)
+            # Strip common verbose prefixes the model might add
+            result = str(result).strip()
+            for prefix in ["The answer is ", "Answer: ", "Final answer: ", "Result: "]:
+                if result.lower().startswith(prefix.lower()):
+                    result = result[len(prefix):]
+            return result.strip()
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return f"AGENT ERROR: {e}"
+
+
+# --- Submission ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,41 +102,38 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     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("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
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        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
 
-    # 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")
@@ -80,23 +141,21 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, task_id)
             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:
-             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}"})
+            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)
 
-    # 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)
 
-    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -140,21 +199,19 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 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.
+        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution.
         """
     )
 
@@ -163,7 +220,6 @@ with gr.Blocks() as demo:
     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(
@@ -173,24 +229,20 @@ with gr.Blocks() as demo:
 
 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
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+        print(f"SPACE_HOST found: {space_host_startup}")
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        print("SPACE_HOST 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")
+    if space_id_startup:
+        print(f"SPACE_ID found: {space_id_startup}")
+        print(f"Repo URL: https://huggingface.co/spaces/{space_id_startup}")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        print("SPACE_ID not found (running locally?).")
 
     print("-"*(60 + len(" App Starting ")) + "\n")
-
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)