Update app.py

app.py

@@ -1,91 +1,49 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-import re
-from openai import OpenAI
-from duckduckgo_search import DDGS
+from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel
 
+# (Keep Constants and BasicAgent class as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-GAIA_SYSTEM_PROMPT = """
-You are an expert at solving GAIA benchmark questions. Follow these rules:
-1. Think step-by-step before answering
-2. Format answers EXACTLY as required
-3. Use web search when needed
-4. ALWAYS end with: FINAL ANSWER: [Your Answer]
-"""
-
-class GaiaAgent:
-    def __init__(self):
-        print("Initializing GAIA Agent")
-        self.client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
-        self.answer_patterns = [
-            r"FINAL ANSWER:\s*(.+)",
-            r"Final Answer:\s*(.+)",
-            r"Answer:\s*(.+)"
-        ]
-
-    def web_search(self, query: str) -> str:
-        """Simple web search implementation"""
-        try:
-            with DDGS() as ddgs:
-                results = [r for r in ddgs.text(query, max_results=3)]
-            return "\n".join([f"{i+1}. {res['title']}: {res['body']}" for i, res in enumerate(results)])
-        except Exception as e:
-            print(f"Search error: {str(e)}")
-            return ""
 
-    def __call__(self, question: str) -> str:
-        """Handle question answering"""
-        print(f"Processing: {question[:60]}...")
-        
-        # Determine if we need web search
-        needs_search = any(word in question.lower() for word in 
-                         ["current", "recent", "today", "latest", "who is", "what is"])
-        
-        context = self.web_search(question) if needs_search else ""
-        
-        messages = [
-            {"role": "system", "content": GAIA_SYSTEM_PROMPT},
-            {"role": "user", "content": question}
-        ]
-        
-        if context:
-            messages.insert(1, {"role": "system", "content": f"Search Results:\n{context}"})
-        
-        try:
-            response = self.client.chat.completions.create(
-                model="gpt-4-turbo",
-                messages=messages,
-                temperature=0.1,
-                max_tokens=500
-            )
-            return self.extract_final_answer(response.choices[0].message.content)
-        except Exception as e:
-            print(f"GPT error: {str(e)}")
-            return "Error: Could not generate answer"
-
-    def extract_final_answer(self, response: str) -> str:
-        """Extract the final answer from the response"""
-        for pattern in self.answer_patterns:
-            match = re.search(pattern, response, re.IGNORECASE)
-            if match:
-                answer = match.group(1).strip()
-                # Clean up the answer
-                answer = re.sub(r"[^a-zA-Z0-9,. ]", "", answer)
-                return answer[:200]  # Limit length
+# --- Basic Agent Definition ---
+class BasicAgent:
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=HfApiModel())
+
+        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.
+        """
+        self.agent.prompt_templates["system_prompt"] = self.agent.prompt_templates["system_prompt"] + SYSTEM_PROMPT
         
-        # Fallback: return the last line
-        lines = response.strip().split('\n')
-        return lines[-1].strip() if lines else "No answer found"
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """Handle the full submission process"""
-    space_id = os.getenv("SPACE_ID")
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        final_answer = self.agent.run(question)
+        print(f"Agent returning final answer: {final_answer}")
+        return final_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}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -95,74 +53,150 @@ 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 = GaiaAgent()
+        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:
-            return "Fetched questions list is empty.", 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 Exception as e:
+    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
 
+    # 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")
         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})
         except Exception as 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:
-        return "Agent did not produce any answers.", pd.DataFrame(results_log)
+        print("Agent did not produce any answers to submit.")
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    submission_data = {
-        "username": username.strip(),
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
+    # 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)
         response.raise_for_status()
         result_data = response.json()
         final_status = (
             f"Submission Successful!\n"
-            f"Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)"
+            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.')}"
         )
-        return final_status, pd.DataFrame(results_log)
+        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:
-        return f"Submission Failed: {str(e)}", pd.DataFrame(results_log)
+        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("# GAIA Benchmark Agent")
-    gr.Markdown("Run the agent to answer GAIA benchmark questions")
-    
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown(
+        "Please clone this space, then modify the code to define your agent's logic within the BasicAgent class. "
+        "Log in to your Hugging Face account using the button below. This uses your HF username for submission. "
+        "Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score."
+    )
+
     gr.LoginButton()
-    run_button = gr.Button("Run Evaluation")
-    status_output = gr.Textbox(label="Status", lines=3)
-    results_table = gr.DataFrame(label="Results")
-    
+
+    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("Starting GAIA Agent...")
-    demo.launch()
+    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)