Update app.py

app.py

@@ -3,101 +3,121 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
-
-# (Keep Constants as is)
-# --- Constants ---
+import asyncio
+from smolagents import ToolCallingAgent, InferenceClientModel, HfApiModel
+from smolagents import DuckDuckGoSearchTool, Tool, CodeAgent
+from huggingface_hub import login
+#h
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    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
-
-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)
+login(token=os.environ["HUGGINGFACEHUB_API_TOKEN"])
+
+search_tool = DuckDuckGoSearchTool()
+
+async def run_and_submit_all(profile: gr.OAuthProfile | None):
+    log_output = ""
+
     try:
-        agent = BasicAgent()
+        agent = CodeAgent(
+            tools=[search_tool],
+            model=HfApiModel(model="MiniMaxAI/MiniMax-M1-80k"),
+            max_steps=5,
+            verbosity_level=2        
+        )
     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)
+        yield f"Error initializing agent: {e}", None, log_output
+        return
+
+    space_id = os.getenv("SPACE_ID")
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
 
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    questions_url = f"{DEFAULT_API_URL}/questions"
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
-        questions_data = response.json()
+        questions_data = response.json()[:5]
         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
+            yield "Fetched questions list is empty or invalid format.", None, log_output
+            return
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        yield f"Error fetching questions: {e}", None, log_output
+        return
 
-    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+    loop = asyncio.get_event_loop()
+
     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
+
+        log_output += f"🔍 Solving Task ID: {task_id}...\n"
+        yield None, None, log_output
+
         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})
+            system_prompt = (
+                "You are a general AI assistant. I will ask you a question. "
+                "Report your thoughts, and finish your answer with the following template: "
+                "FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. "
+                "If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. "
+                "If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. "
+                "If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.\n\n"
+            )
+            full_prompt = system_prompt + f"Question: {question_text.strip()}"
+
+            agent_result = await loop.run_in_executor(None, agent, full_prompt)
+
+            # Extract final answer cleanly
+            if isinstance(agent_result, dict) and "final_answer" in agent_result:
+                final_answer = str(agent_result["final_answer"]).strip()
+            elif isinstance(agent_result, str):
+                response_text = agent_result.strip()
+
+                # Remove known boilerplate
+                if "Here is the final answer from your managed agent" in response_text:
+                    response_text = response_text.split(":", 1)[-1].strip()
+
+                if "FINAL ANSWER:" in response_text:
+                    _, final_answer = response_text.rsplit("FINAL ANSWER:", 1)
+                    final_answer = final_answer.strip()
+                else:
+                    final_answer = response_text
+            else:
+                final_answer = str(agent_result).strip()
+
+            answers_payload.append({
+                "task_id": task_id,
+                "submitted_answer": final_answer
+            })
+
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": final_answer
+            })
+
+            log_output += f"✅ Done: {task_id} — Answer: {final_answer[:60]}\n"
+            yield None, None, log_output
+
         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}"
+            })
+            log_output += f"⛔️ Error: {task_id} — {e}\n"
+            yield None, None, log_output
 
     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)
+        yield "Agent did not produce any answers to submit.", pd.DataFrame(results_log), log_output
+        return
 
-    # 4. Prepare Submission 
+    username = profile.username if profile else "unknown"
+    submit_url = f"{DEFAULT_API_URL}/submit"
     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)
         response.raise_for_status()
@@ -109,88 +129,43 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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
+        yield final_status, results_df, log_output
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
+        status_message = f"Submission Failed: {e}"
         results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        yield status_message, results_df, log_output
 
-
-# --- 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.Markdown("""
+    **Instructions:**
+    1. Clone this space and define your agent logic.
+    2. Log in to your Hugging Face account.
+    3. Click 'Run Evaluation & Submit All Answers'.
+    ---
+    **Note:**
+    The run may take time. Async is now used to improve responsiveness.
+    """)
 
     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)
+    progress_log = gr.Textbox(label="Progress Log", lines=10, interactive=False)
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table, progress_log])
 
 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")
-    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)
+        print(f"✅ SPACE_HOST: https://{space_host_startup}.hf.space")
+    if space_id_startup:
+        print(f"✅ SPACE_ID: https://huggingface.co/spaces/{space_id_startup}")
+
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, share=False)