Update app.py

app.py

@@ -1,65 +1,105 @@
-""" Basic Agent Evaluation Runner"""
+"""Simple Agent Evaluation Runner"""
 import os
-import inspect
+import re
 import gradio as gr
 import requests
 import pandas as pd
-from langchain_core.messages import HumanMessage
-from agent import build_graph
+import google.generativeai as genai
+from dotenv import load_dotenv
 
+# Load environment variables
+load_dotenv()
 
+# Configure Gemini
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
-# (Keep Constants as is)
-# --- Constants ---
+# Constants
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-
-
-class BasicAgent:
-    """A langgraph agent."""
+class SimpleAgent:
+    """A simple agent using Google Gemini."""
+    
     def __init__(self):
-        print("BasicAgent initialized.")
-        self.graph = build_graph()
-
+        print("SimpleAgent initialized.")
+        self.model = genai.GenerativeModel('gemini-1.5-flash')
+        
     def __call__(self, question: str) -> str:
+        """Process a question and return an answer."""
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        # Wrap the question in a HumanMessage from langchain_core
-        messages = [HumanMessage(content=question)]
-        messages = self.graph.invoke({"messages": messages})
-        answer = messages['messages'][-1].content
-        return answer[14:]
-
+        
+        # Simple system prompt
+        system_prompt = """You are a helpful assistant. Answer questions as accurately as possible.
+
+IMPORTANT: Your final answer should be:
+- A number (without commas, $ signs, or % signs unless specifically requested)
+- A few words as possible 
+- A comma-separated list if multiple items are requested
+
+Always end your response with: FINAL ANSWER: [your answer]
+
+Examples:
+- For "How many albums did X release?" → FINAL ANSWER: 5
+- For "What city is the capital?" → FINAL ANSWER: Paris
+- For "List the top 3 countries" → FINAL ANSWER: USA, China, Japan
+"""
+        
+        # Combine system prompt with question
+        full_prompt = f"{system_prompt}\n\nQuestion: {question}"
+        
+        try:
+            # Generate response using Gemini
+            response = self.model.generate_content(full_prompt)
+            answer = response.text
+            
+            # Extract final answer if it exists
+            final_answer_match = re.search(r'FINAL ANSWER:\s*(.+?)(?:\n|$)', answer, re.IGNORECASE)
+            if final_answer_match:
+                final_answer = final_answer_match.group(1).strip()
+                return final_answer
+            else:
+                # If no "FINAL ANSWER:" format, try to extract a simple answer
+                # Look for numbers, short phrases, or lists
+                lines = answer.strip().split('\n')
+                for line in reversed(lines):  # Start from the end
+                    line = line.strip()
+                    if line and not line.startswith('FINAL'):
+                        # Simple heuristic: if it's short, likely an answer
+                        if len(line) < 100:
+                            return line
+                
+                return answer.strip()[:100]  # Fallback to first 100 chars
+                
+        except Exception as e:
+            print(f"Error calling Gemini API: {e}")
+            return f"Error: {str(e)}"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+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 SimpleAgent 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
-
+    # Check if user is logged in
     if profile:
-        username= f"{profile.username}"
+        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
 
+    # Get space info
+    space_id = os.getenv("SPACE_ID")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Unknown"
+    
     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. Initialize Agent
     try:
-        agent = BasicAgent()
+        agent = SimpleAgent()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
+        print(f"Error initializing 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}")
@@ -67,115 +107,120 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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
+            return "No questions received from server.", None
+            
         print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
+        
+    except Exception 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
+    # 3. Process Questions
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    
+    print(f"Processing {len(questions_data)} questions...")
+    
+    for i, item in enumerate(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}")
+            print(f"Skipping invalid item: {item}")
             continue
+            
+        print(f"Processing question {i+1}/{len(questions_data)}: {task_id}")
+        
         try:
+            # Get answer from agent
             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})
+            
+            # Store results
+            answers_payload.append({
+                "task_id": task_id, 
+                "submitted_answer": submitted_answer
+            })
+            
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else 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}"})
+            error_msg = f"ERROR: {str(e)}"
+            print(f"Error processing task {task_id}: {e}")
+            
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
+                "Submitted Answer": error_msg
+            })
 
     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}")
+    # 4. Submit Results
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+    
+    print(f"Submitting {len(answers_payload)} answers...")
+    
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
+        
+        # Format success message
         final_status = (
-            f"Submission Successful!\n"
+            f"✅ Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"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"Message: {result_data.get('message', 'No additional message.')}"
         )
-        print("Submission successful.")
+        
+        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)
+        error_msg = f"❌ Submission Failed: {str(e)}"
+        print(error_msg)
         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.
-        """
-    )
+        return error_msg, results_df
+
+# Build Gradio Interface
+with gr.Blocks(title="Simple Agent Evaluation") as demo:
+    gr.Markdown("# Simple Agent Evaluation Runner")
+    gr.Markdown("""
+    **Instructions:**
+    1. Make sure you have set up your `GOOGLE_API_KEY` in the environment variables
+    2. Log in to your Hugging Face account using the button below
+    3. Click 'Run Evaluation & Submit All Answers' to start the evaluation
+    
+    **Note:** This is a simplified agent that uses Google Gemini to answer questions.
+    """)
 
     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 = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
+    
+    status_output = gr.Textbox(
+        label="Status / Results", 
+        lines=6, 
+        interactive=False
+    )
+    
+    results_table = gr.DataFrame(
+        label="Questions and Answers",
+        wrap=True
+    )
 
     run_button.click(
         fn=run_and_submit_all,
@@ -183,26 +228,28 @@ 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
-
-    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")
+    print("=" * 50)
+    print("🚀 Starting Simple Agent Evaluation Runner")
+    print("=" * 50)
+    
+    # Check environment variables
+    if not os.getenv("GOOGLE_API_KEY"):
+        print("⚠️  WARNING: GOOGLE_API_KEY not found in environment variables!")
+        print("   Please set your Google API key to use Gemini.")
     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...")
+        print("✅ GOOGLE_API_KEY found")
+    
+    space_host = os.getenv("SPACE_HOST")
+    space_id = os.getenv("SPACE_ID")
+    
+    if space_host:
+        print(f"✅ Running on Hugging Face Space")
+        print(f"   URL: https://{space_host}.hf.space")
+    
+    if space_id:
+        print(f"✅ Space ID: {space_id}")
+    
+    print("=" * 50)
+    
     demo.launch(debug=True, share=False)