Update app.py

app.py

@@ -1,196 +1,177 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from smolagents import CodeAgent, HfApiModel, tool
+import inspect
 
-# (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 ------
+# ====================== CUSTOM TOOLS ======================
+# Add any tools you want here. The more useful ones you add, the better your score.
+
+@tool
+def web_search(query: str) -> str:
+    """Perform a web search and return results. Very useful for GAIA questions."""
+    # You can implement with DuckDuckGo, Tavily, or even requests to a search API
+    # For simplicity, here's a placeholder using a free search (replace with better if you want)
+    try:
+        from duckduckgo_search import DDGS
+        with DDGS() as ddgs:
+            results = list(ddgs.text(query, max_results=5))
+            return "\n\n".join([f"{r['title']}: {r['body']}" for r in results])
+    except Exception as e:
+        return f"Search failed: {str(e)}"
+
+
+@tool
+def calculate(expression: str) -> str:
+    """Evaluate a mathematical expression safely."""
+    try:
+        # You can use sympy for more complex math if you install it
+        import math
+        return str(eval(expression, {"__builtins__": {}}, {"math": math}))
+    except Exception as e:
+        return f"Calculation error: {str(e)}"
+
+
+# Add more tools as needed (file handling, image description, code execution, etc.)
+# GAIA often requires: search, math, file reading, reasoning over tables/images, etc.
+
+# ====================== AGENT DEFINITION ======================
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("🚀 Initializing Smolagents Agent for GAIA benchmark...")
+        
+        # Choose your model
+        # Option 1: Free HF Inference (good enough for many questions)
+        self.model = HfApiModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct")
+        
+        # Option 2: Stronger (if you have API key) → uncomment and set env var
+        # self.model = HfApiModel(
+        #     model_id="gpt-4o-mini",  # or "Qwen/Qwen2.5-72B-Instruct"
+        #     provider="openai" if "OPENAI_API_KEY" in os.environ else "hf"
+        # )
+
+        # Define tools for the agent
+        tools = [web_search, calculate]   # ← Add your custom tools here
+
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=tools,
+            add_base_tools=True,          # includes Python interpreter, final_answer, etc.
+            verbosity_level=1,
+            max_steps=12,                 # GAIA questions can need several steps
+            planning_interval=4           # helps with complex multi-step reasoning
+        )
+        
+        print("✅ Agent initialized successfully.")
+
     def __call__(self, question: 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
+        print(f"🤖 Agent processing question (first 80 chars): {question[:80]}...")
+        
+        try:
+            # Run the agent
+            result = self.agent.run(question)
+            
+            # Smolagents usually returns the final answer nicely
+            final_answer = str(result).strip()
+            
+            print(f"✅ Agent returned: {final_answer[:200]}{'...' if len(final_answer) > 200 else ''}")
+            return final_answer
+            
+        except Exception as e:
+            error_msg = f"Agent error: {str(e)}"
+            print(f"❌ {error_msg}")
+            return error_msg
+
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+# ====================== THE REST OF THE CODE (unchanged) ======================
+# Keep everything from run_and_submit_all() onward exactly as you had it
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the agent 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.")
+    if not profile:
         return "Please Login to Hugging Face with the button.", None
 
+    username = profile.username.strip()
+    print(f"👤 User logged in: {username}")
+
     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)
+    # 1. Instantiate 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)
+
+    space_id = os.getenv("SPACE_ID")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE/tree/main"
 
     # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(questions_url, timeout=20)
         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
+            return "Fetched questions list is empty.", None
+        print(f"📥 Fetched {len(questions_data)} questions.")
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run Agent on all questions
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+
+    print(f"🚀 Running agent on {len(questions_data)} questions... (this may take a while)")
+
     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 item with missing task_id or question: {item}")
             continue
+
         try:
             submitted_answer = agent(question_text)
             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})
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text[:150] + ("..." if len(question_text) > 150 else ""),
+                "Submitted Answer": str(submitted_answer)[:300] + ("..." if len(str(submitted_answer)) > 300 else "")
+            })
         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}"})
+            error_ans = f"AGENT ERROR: {str(e)}"
+            answers_payload.append({"task_id": task_id, "submitted_answer": error_ans})
+            results_log.append({"Task ID": task_id, "Question": question_text[:150]+"...", "Submitted Answer": error_ans})
 
     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 "No answers were generated.", 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)
+    # 4. Submit
+    submission_data = {
+        "username": username,
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response = requests.post(submit_url, json=submission_data, timeout=90)
         response.raise_for_status()
         result_data = response.json()
+
         final_status = (
-            f"Submission Successful!\n"
+            f"✅ Submission Successful!\n\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.')}"
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n\n"
+            f"Message: {result_data.get('message', 'No message')}"
         )
-        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)
+
+        return final