Update app.py

app.py

@@ -1,217 +1,425 @@
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
 from langchain_core.messages import HumanMessage
 from agent import build_graph
 
+
+
+# (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 ------
+
+
 class BasicAgent:
-    """A langgraph agent using OpenAI."""
+    """A langgraph agent."""
     def __init__(self):
-        print("=== INITIALIZING OPENAI BASIC AGENT ===")
-        print(f"Current working directory: {os.getcwd()}")
-        print(f"Files in directory: {os.listdir('.')}")
-        
-        # Check environment variables
-        print("=== ENVIRONMENT VARIABLES ===")
-        for key in sorted(os.environ.keys()):
-            if any(term in key.upper() for term in ['OPENAI', 'API_KEY', 'TOKEN', 'TAVILY']):
-                value = os.environ[key]
-                print(f"{key}: {value[:10] if value else 'None'}...")
-        
-        # Check specifically for OpenAI API key
-        openai_key = os.getenv("OPENAI_API_KEY")
-        if openai_key:
-            print(f"✓ OpenAI API Key found: {openai_key[:15]}...")
-        else:
-            print("✗ OpenAI API Key not found!")
-            print("Please add OPENAI_API_KEY to your Hugging Face Space secrets")
-        
-        try:
-            self.graph = build_graph()
-            print("✓ Graph built successfully")
-        except Exception as e:
-            print(f"✗ Error building graph: {e}")
-            raise e
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
-        print(f"=== AGENT CALL ===")
-        print(f"Question: {question[:100]}...")
-        
-        try:
-            messages = [HumanMessage(content=question)]
-            print(f"Invoking graph with messages: {len(messages)}")
-            
-            result = self.graph.invoke({"messages": messages})
-            print(f"Graph result keys: {result.keys() if isinstance(result, dict) else 'Not a dict'}")
-            
-            if 'messages' in result and result['messages']:
-                answer = result['messages'][-1].content
-                print(f"Answer (first 100 chars): {answer[:100]}...")
-                return answer
-            else:
-                print("No messages in result")
-                return "I apologize, but I couldn't generate a response."
-                
-        except Exception as e:
-            print(f"Error in agent call: {e}")
-            return f"Error: {str(e)}"
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        messages = [HumanMessage(content=question)]
+        result = self.graph.invoke({"messages": messages})
+        answer = result['messages'][-1].content
+        return answer  # kein [14:] mehr nötig!
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    print("=== STARTING RUN AND SUBMIT ===")
-    space_id = os.getenv("SPACE_ID")
-    print(f"Space ID: {space_id}")
-    
-    if not profile:
+
+
+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
-    
-    username = profile.username
-    print(f"Username: {username}")
-    
+
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
-    
-    print("=== INITIALIZING AGENT ===")
+
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
-        print("✓ Agent initialized successfully")
     except Exception as e:
-        error_msg = f"Error initializing agent: {e}"
-        print(error_msg)
-        return error_msg, None
-
+        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(f"Agent code URL: {agent_code}")
+    print(agent_code)
 
-    print("=== FETCHING QUESTIONS ===")
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
     try:
-        resp_q = requests.get(questions_url, timeout=15)
-        resp_q.raise_for_status()
-        questions = resp_q.json()
-        print(f"✓ Fetched {len(questions)} questions")
+        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
+        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:
-        error_msg = f"Error fetching questions: {e}"
-        print(error_msg)
-        return error_msg, None
+        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 = []
-    
-    print("=== PROCESSING QUESTIONS ===")
-    for i, item in enumerate(questions):
+    answers_payload = []
+    print(f"Running agent on {len(questions_data)} questions...")
+    for item in questions_data:
         task_id = item.get("task_id")
-        q = item.get("question")
-        
-        print(f"\n--- Question {i+1}/{len(questions)} ---")
-        print(f"Task ID: {task_id}")
-        print(f"Question: {q[:100]}...")
-        
-        if not task_id or q is None:
-            print("Skipping - missing task_id or question")
+        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:
-            print("Calling agent...")
-            ans = agent(q)
-            print(f"Answer: {ans[:100]}...")
-            
-            answers.append({"task_id": task_id, "submitted_answer": ans})
-            results_log.append({"Task ID": task_id, "Question": q, "Submitted Answer": ans})
-            print("✓ Question processed successfully")
-            
+            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:
-            error_msg = f"ERROR: {e}"
-            print(f"✗ Error processing question: {error_msg}")
-            results_log.append({"Task ID": task_id, "Question": q, "Submitted Answer": error_msg})
+             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:
+    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)
 
-    print(f"=== SUBMITTING {len(answers)} ANSWERS ===")
-    payload = {"username": username.strip(), "agent_code": agent_code, "answers": answers}
-    
+    # 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:
-        resp_s = requests.post(submit_url, json=payload, timeout=60)
-        resp_s.raise_for_status()
-        data = resp_s.json()
-        
-        status = (
+        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"User: {data.get('username')}\n"
-            f"Score: {data.get('score', 'N/A')}% "
-            f"({data.get('correct_count', '?')}/{data.get('total_attempted', '?')})\n"
-            f"{data.get('message', '')}"
+            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.')}"
         )
-        print("✓ Submission successful")
-        print(status)
-        return 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:
-        error_msg = f"Submission Failed: {e}"
-        print(error_msg)
-        return error_msg, pd.DataFrame(results_log)
-
-# Simple test function for debugging
-def test_agent():
-    """Test function to verify agent works"""
-    print("=== TESTING AGENT ===")
-    try:
-        agent = BasicAgent()
-        test_questions = [
-            "What is 2 + 3?",
-            "What is 10 * 5?",
-            "Search for information about Python programming"
-        ]
+        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)
+
+
+# import os
+# import gradio as gr
+# import requests
+# import pandas as pd
+# from langchain_core.messages import HumanMessage
+# from agent import build_graph
+
+# # --- Constants ---
+# DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# class BasicAgent:
+#     """A langgraph agent using OpenAI."""
+#     def __init__(self):
+#         print("=== INITIALIZING OPENAI BASIC AGENT ===")
+#         print(f"Current working directory: {os.getcwd()}")
+#         print(f"Files in directory: {os.listdir('.')}")
+        
+#         # Check environment variables
+#         print("=== ENVIRONMENT VARIABLES ===")
+#         for key in sorted(os.environ.keys()):
+#             if any(term in key.upper() for term in ['OPENAI', 'API_KEY', 'TOKEN', 'TAVILY']):
+#                 value = os.environ[key]
+#                 print(f"{key}: {value[:10] if value else 'None'}...")
+        
+#         # Check specifically for OpenAI API key
+#         openai_key = os.getenv("OPENAI_API_KEY")
+#         if openai_key:
+#             print(f"✓ OpenAI API Key found: {openai_key[:15]}...")
+#         else:
+#             print("✗ OpenAI API Key not found!")
+#             print("Please add OPENAI_API_KEY to your Hugging Face Space secrets")
         
-        for q in test_questions:
-            print(f"\nTesting: {q}")
-            answer = agent(q)
-            print(f"Answer: {answer}")
+#         try:
+#             self.graph = build_graph()
+#             print("✓ Graph built successfully")
+#         except Exception as e:
+#             print(f"✗ Error building graph: {e}")
+#             raise e
+
+#     def __call__(self, question: str) -> str:
+#         print(f"=== AGENT CALL ===")
+#         print(f"Question: {question[:100]}...")
+        
+#         try:
+#             messages = [HumanMessage(content=question)]
+#             print(f"Invoking graph with messages: {len(messages)}")
             
-    except Exception as e:
-        print(f"Test failed: {e}")
+#             result = self.graph.invoke({"messages": messages})
+#             print(f"Graph result keys: {result.keys() if isinstance(result, dict) else 'Not a dict'}")
+            
+#             if 'messages' in result and result['messages']:
+#                 answer = result['messages'][-1].content
+#                 print(f"Answer (first 100 chars): {answer[:100]}...")
+#                 return answer
+#             else:
+#                 print("No messages in result")
+#                 return "I apologize, but I couldn't generate a response."
+                
+#         except Exception as e:
+#             print(f"Error in agent call: {e}")
+#             return f"Error: {str(e)}"
 
-with gr.Blocks() as demo:
-    gr.Markdown("# OpenAI-Powered Agent Evaluation Runner")
-    gr.Markdown("""
-    This agent uses OpenAI's GPT models instead of Hugging Face.
+# def run_and_submit_all(profile: gr.OAuthProfile | None):
+#     print("=== STARTING RUN AND SUBMIT ===")
+#     space_id = os.getenv("SPACE_ID")
+#     print(f"Space ID: {space_id}")
     
-    ## Setup Instructions:
-    1. Get an OpenAI API key from https://platform.openai.com/api-keys
-    2. Add it as `OPENAI_API_KEY` in your Hugging Face Space secrets
-    3. (Optional) Add `TAVILY_API_KEY` for web search functionality
-    4. Log in with the button below
-    5. Click **Run Evaluation & Submit All Answers**
+#     if not profile:
+#         return "Please Login to Hugging Face with the button.", None
     
-    ## Current Configuration:
-    - Model: GPT-3.5-turbo (change to GPT-4 in agent.py if you have access)
-    - Tools: Math operations, Wikipedia search, Arxiv search, Web search (if Tavily configured)
-    """)
+#     username = profile.username
+#     print(f"Username: {username}")
     
-    with gr.Row():
-        gr.LoginButton()
-        test_btn = gr.Button("Test Agent", variant="secondary")
+#     api_url = DEFAULT_API_URL
+#     questions_url = f"{api_url}/questions"
+#     submit_url = f"{api_url}/submit"
     
-    run_btn = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
-    status_out = gr.Textbox(label="Run Status / Submission Result", lines=5)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+#     print("=== INITIALIZING AGENT ===")
+#     try:
+#         agent = BasicAgent()
+#         print("✓ Agent initialized successfully")
+#     except Exception as e:
+#         error_msg = f"Error initializing agent: {e}"
+#         print(error_msg)
+#         return error_msg, None
+
+#     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+#     print(f"Agent code URL: {agent_code}")
+
+#     print("=== FETCHING QUESTIONS ===")
+#     try:
+#         resp_q = requests.get(questions_url, timeout=15)
+#         resp_q.raise_for_status()
+#         questions = resp_q.json()
+#         print(f"✓ Fetched {len(questions)} questions")
+#     except Exception as e:
+#         error_msg = f"Error fetching questions: {e}"
+#         print(error_msg)
+#         return error_msg, None
+
+#     results_log = []
+#     answers = []
     
-    # Button actions
-    run_btn.click(fn=run_and_submit_all, outputs=[status_out, results_table])
-    test_btn.click(fn=test_agent, outputs=[])
+#     print("=== PROCESSING QUESTIONS ===")
+#     for i, item in enumerate(questions):
+#         task_id = item.get("task_id")
+#         q = item.get("question")
+        
+#         print(f"\n--- Question {i+1}/{len(questions)} ---")
+#         print(f"Task ID: {task_id}")
+#         print(f"Question: {q[:100]}...")
+        
+#         if not task_id or q is None:
+#             print("Skipping - missing task_id or question")
+#             continue
+            
+#         try:
+#             print("Calling agent...")
+#             ans = agent(q)
+#             print(f"Answer: {ans[:100]}...")
+            
+#             answers.append({"task_id": task_id, "submitted_answer": ans})
+#             results_log.append({"Task ID": task_id, "Question": q, "Submitted Answer": ans})
+#             print("✓ Question processed successfully")
+            
+#         except Exception as e:
+#             error_msg = f"ERROR: {e}"
+#             print(f"✗ Error processing question: {error_msg}")
+#             results_log.append({"Task ID": task_id, "Question": q, "Submitted Answer": error_msg})
 
-if __name__ == "__main__":
-    print("=== STARTING OPENAI GRADIO APP ===")
+#     if not answers:
+#         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+
+#     print(f"=== SUBMITTING {len(answers)} ANSWERS ===")
+#     payload = {"username": username.strip(), "agent_code": agent_code, "answers": answers}
     
-    # Quick environment check
-    openai_key = os.getenv("OPENAI_API_KEY")
-    if openai_key:
-        print(f"✓ OpenAI API Key configured: {openai_key[:15]}...")
-    else:
-        print("⚠️  OpenAI API Key not found - please add OPENAI_API_KEY to your Space secrets")
+#     try:
+#         resp_s = requests.post(submit_url, json=payload, timeout=60)
+#         resp_s.raise_for_status()
+#         data = resp_s.json()
+        
+#         status = (
+#             f"Submission Successful!\n"
+#             f"User: {data.get('username')}\n"
+#             f"Score: {data.get('score', 'N/A')}% "
+#             f"({data.get('correct_count', '?')}/{data.get('total_attempted', '?')})\n"
+#             f"{data.get('message', '')}"
+#         )
+#         print("✓ Submission successful")
+#         print(status)
+#         return status, pd.DataFrame(results_log)
+        
+#     except Exception as e:
+#         error_msg = f"Submission Failed: {e}"
+#         print(error_msg)
+#         return error_msg, pd.DataFrame(results_log)
+
+# # Simple test function for debugging
+# def test_agent():
+#     """Test function to verify agent works"""
+#     print("=== TESTING AGENT ===")
+#     try:
+#         agent = BasicAgent()
+#         test_questions = [
+#             "What is 2 + 3?",
+#             "What is 10 * 5?",
+#             "Search for information about Python programming"
+#         ]
+        
+#         for q in test_questions:
+#             print(f"\nTesting: {q}")
+#             answer = agent(q)
+#             print(f"Answer: {answer}")
+            
+#     except Exception as e:
+#         print(f"Test failed: {e}")
+
+# with gr.Blocks() as demo:
+#     gr.Markdown("# OpenAI-Powered Agent Evaluation Runner")
+#     gr.Markdown("""
+#     This agent uses OpenAI's GPT models instead of Hugging Face.
     
-    demo.launch(debug=True, share=False)
+#     ## Setup Instructions:
+#     1. Get an OpenAI API key from https://platform.openai.com/api-keys
+#     2. Add it as `OPENAI_API_KEY` in your Hugging Face Space secrets
+#     3. (Optional) Add `TAVILY_API_KEY` for web search functionality
+#     4. Log in with the button below
+#     5. Click **Run Evaluation & Submit All Answers**
+    
+#     ## Current Configuration:
+#     - Model: GPT-3.5-turbo (change to GPT-4 in agent.py if you have access)
+#     - Tools: Math operations, Wikipedia search, Arxiv search, Web search (if Tavily configured)
+#     """)
+    
+#     with gr.Row():
+#         gr.LoginButton()
+#         test_btn = gr.Button("Test Agent", variant="secondary")
+    
+#     run_btn = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
+#     status_out = gr.Textbox(label="Run Status / Submission Result", lines=5)
+#     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    
+#     # Button actions
+#     run_btn.click(fn=run_and_submit_all, outputs=[status_out, results_table])
+#     test_btn.click(fn=test_agent, outputs=[])
+
+# if __name__ == "__main__":
+#     print("=== STARTING OPENAI GRADIO APP ===")
+    
+#     # Quick environment check
+#     openai_key = os.getenv("OPENAI_API_KEY")
+#     if openai_key:
+#         print(f"✓ OpenAI API Key configured: {openai_key[:15]}...")
+#     else:
+#         print("⚠️  OpenAI API Key not found - please add OPENAI_API_KEY to your Space secrets")
+    
+#     demo.launch(debug=True, share=False)