Update app.py

app.py

@@ -3,42 +3,35 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
-from openai import OpenAI  # openai>=1.0.0
+
+# Try to import Google GenAI SDK
+try:
+    from google import genai
+except ImportError:
+    raise ImportError("Please install the 'google-genai' package: pip install google-genai")
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- GPT-4 Based Agent ---
-class BasicAgent:
+# --- Gemini Agent Definition ---
+class GeminiAgent:
     def __init__(self):
-        openai_api_key = os.getenv("OPENAI_API_KEY")
-        if not openai_api_key:
-            raise ValueError("Missing OPENAI_API_KEY in environment.")
-        self.client = OpenAI(api_key=openai_api_key)
-        print("✅ BasicAgent initialized using OpenAI GPT-4.")
+        print("GeminiAgent initialized.")
+        api_key = os.getenv("GEMINI_API_KEY")
+        if not api_key:
+            raise ValueError("GEMINI_API_KEY environment variable not set.")
+        self.client = genai.Client(api_key=api_key)
 
     def __call__(self, question: str) -> str:
-        print(f"Agent received question: {question[:50]}...")
-        try:
-            response = self.client.chat.completions.create(
-                model="gpt-4",
-                messages=[
-                    {
-                        "role": "system",
-                        "content": "You are a helpful AI agent answering science and reasoning questions. Return only the exact final answer. No explanations."
-                    },
-                    {"role": "user", "content": question}
-                ],
-                temperature=0.0
-            )
-            answer = response.choices[0].message.content.strip()
-            print(f"Answer: {answer}")
-            return answer
-        except Exception as e:
-            print(f"❌ Error in GPT response: {e}")
-            return "ERROR: GPT call failed"
+        print(f"GeminiAgent received question (first 50 chars): {question[:50]}...")
+        prompt = f"Answer concisely without explanation: {question}"
+        response = self.client.models.generate_content(
+            model="gemini-2.0-flash", contents=prompt
+        )
+        answer = response.text.strip().rstrip(".!?")
+        print(f"GeminiAgent returning answer: {answer}")
+        return answer
 
-# --- Run + Submit Function ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
 
@@ -46,99 +39,160 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
-        return "⚠️ Please login to Hugging Face with the button above.", None
+        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"
 
     try:
-        agent = BasicAgent()
+        agent = GeminiAgent()
     except Exception as e:
-        return f"Agent init error: {e}", None
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
 
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Agent code: {agent_code}")
+    print(agent_code)
 
-    # 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()
-        print(f"✅ Fetched {len(questions_data)} questions.")
+        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
     except Exception as e:
-        return f"❌ Failed to fetch questions: {e}", None
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
 
     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 not question_text:
+        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
-            })
+            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 on task {task_id}: {e}")
-            results_log.append({
-                "Task ID": task_id,
-                "Question": question_text,
-                "Submitted Answer": f"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 "❌ No answers to submit.", 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)
 
-    # Submit results
     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)
 
+    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"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
-            f"Score: {result_data.get('score', 'N/A')}% "
+            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)
+        return status_message, pd.DataFrame(results_log)
+    except requests.exceptions.Timeout:
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
+        return status_message, pd.DataFrame(results_log)
+    except requests.exceptions.RequestException as e:
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
+        return status_message, pd.DataFrame(results_log)
     except Exception as e:
-        return f"❌ Submission failed: {e}", pd.DataFrame(results_log)
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        return status_message, pd.DataFrame(results_log)
 
-# --- Gradio Interface ---
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# 🤖 GAIA Agent Submission Portal")
-    gr.Markdown("""
-    1. Log in with your Hugging Face account.
-    2. Click the button to run your agent on 20 questions and submit the results.
-    """)
-
+    gr.Markdown("# Gemini 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 separate action or even to answer the questions asynchronously.
+        """
+    )
     gr.LoginButton()
-    run_button = gr.Button("🚀 Run Evaluation & Submit All Answers")
-    status_output = gr.Textbox(label="📢 Run Status", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="📊 Questions and Submitted Answers")
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
-    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]
+    )
 
 if __name__ == "__main__":
-    print("\n========== Starting App ==========")
-    space_id = os.getenv("SPACE_ID")
-    if space_id:
-        print(f"🧠 Repo: https://huggingface.co/spaces/{space_id}/tree/main")
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    space_host_startup = os.getenv("SPACE_HOST")
+    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(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 Gemini Agent Evaluation...")
     demo.launch(debug=True, share=False)