Update evaluation_app.py

evaluation_app.py

@@ -1,6 +1,7 @@
-"""GAIA Agent Evaluation Runner - Fixed Version"""
+""" Basic Agent Evaluation Runner"""
 
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
@@ -8,143 +9,113 @@ import time
 from langchain_core.messages import HumanMessage
 from agent import build_graph
 
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class GAIAAgent:
-    """A GAIA evaluation agent with proper answer extraction."""
-    
+# --- Basic Agent Definition ---
+# ----- THIS IS WHERE YOU CAN BUILD WHAT YOU WANT ------
+
+class BasicAgent:
+    """A langgraph agent."""
+
     def __init__(self):
-        print("GAIAAgent initialized.")
+        print("BasicAgent initialized.")
         self.graph = build_graph()
-    
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question: {question[:50]}...")
-        
-        # Create a focused prompt
-        focused_prompt = f"""Answer this question directly and concisely. 
 
-Question: {question}
+    def __call__(self, question: str) -> str:
+        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:]
 
-Instructions:
-- Read the question carefully
-- Provide only the specific answer requested  
-- End with: FINAL ANSWER: [your answer]
-- Keep the final answer brief and exact
+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
 
-Answer:"""
-        
-        try:
-            # Wrap the question in a HumanMessage
-            messages = [HumanMessage(content=focused_prompt)]
-            result = self.graph.invoke({"messages": messages}, {"recursion_limit": 5})
-            
-            answer = result['messages'][-1].content
-            print(f"Raw agent response: {answer[:100]}...")
-            
-            # Extract final answer properly
-            if "FINAL ANSWER:" in answer:
-                final_part = answer.split("FINAL ANSWER:")[-1].strip()
-                # Clean up the final answer
-                final_part = final_part.replace("</function>", "").replace("<function>", "").strip()
-                if final_part:
-                    return final_part
-            
-            # If no FINAL ANSWER found, extract the last meaningful line
-            lines = answer.strip().split('\n')
-            for line in reversed(lines):
-                line = line.strip()
-                if line and not line.startswith('<') and not line.startswith('Error'):
-                    return line
-            
-            return answer.strip()[:100]  # Fallback
-            
-        except Exception as e:
-            print(f"Error in agent call: {e}")
-            return f"Error: {str(e)[:50]}"
-
-def run_evaluation(username: str):
-    """Runs the GAIA evaluation with proper error handling."""
-    
-    if not username or username.strip() == "":
-        return "Please enter your Hugging Face username.", None
-    
-    # Get space info automatically
-    space_id = os.getenv("SPACE_ID")
-    if not space_id:
-        return "Error: SPACE_ID not found.", None
-    
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
-    
-    # Initialize agent
+
+    # 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
-    
-    # Fetch questions
+
+    # Link to code repository on Hugging Face Spaces
+    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 "No questions fetched.", 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
     
-    # Run agent on questions with better error handling
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    
-    for i, item in enumerate(questions_data):
+
+    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
-        
-        print(f"Processing question {i+1}/{len(questions_data)}: {task_id}")
-        
-        # Shorter delay to speed up
-        time.sleep(5)
-        
+        time.sleep(30)  # Delay to avoid API rate limit or syncing issues
         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[:80] + "...", 
-                "Submitted Answer": submitted_answer
-            })
-            print(f"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: {str(e)[:50]}"
-            results_log.append({
-                "Task ID": task_id, 
-                "Question": question_text[:80] + "...", 
-                "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_payload:
-        return "No answers produced.", pd.DataFrame(results_log)
-    
-    # Submit answers
-    submission_data = {
-        "username": username.strip(), 
-        "agent_code": agent_code, 
-        "answers": 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}")
     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"User: {result_data.get('username')}\n"
@@ -152,42 +123,93 @@ def run_evaluation(username: str):
             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: {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 ---
 
-# Gradio Interface
 with gr.Blocks() as demo:
-    gr.Markdown("# GAIA Agent Evaluation Runner - Fixed Version")
-    gr.Markdown("""
-    **Instructions:**
-    1. Enter your Hugging Face username below.
-    2. Click 'Run Evaluation & Submit All Answers'.
-    
-    **Fixed Issues:**
-    - Proper answer extraction with FINAL ANSWER format
-    - Reduced tool calling loops 
-    - Better error handling
-    """)
-    
-    username_input = gr.Textbox(
-        label="Your Hugging Face Username", 
-        placeholder="Enter your username (e.g., Supan23)",
-        value=""
+    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 separate action or even to answer the questions in async.
+
+        """
     )
-    
-    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
-    
+
+    gr.LoginButton()
+
+    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_evaluation,
-        inputs=[username_input],
+        fn=run_and_submit_all,
         outputs=[status_output, results_table]
     )
 
 if __name__ == "__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 Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)