Update app.py

app.py

@@ -1,52 +1,85 @@
-""" Working Multi-LLM Agent Evaluation Runner"""
+""" Basic Agent Evaluation Runner"""
 import os
+import inspect
 import gradio as gr
 import requests
 import pandas as pd
 from langchain_core.messages import HumanMessage
+from veryfinal import build_graph, HybridLangGraphMultiLLMSystem  # Changed import
 
-# Import from veryfinal.py
-from veryfinal import UnifiedAgnoEnhancedSystem
 
+
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Working Agent Definition ---
-class WorkingMultiLLMAgent:
-    """A working multi-LLM agent that actually answers questions"""
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+
+class BasicAgent:
+    """A langgraph agent."""
     def __init__(self):
-        print("Working Multi-LLM Agent initialized.")
+        print("BasicAgent initialized.")
         try:
-            self.system = UnifiedAgnoEnhancedSystem()
-            print("✅ Working system built successfully.")
+            self.graph = build_graph()
+            # Also initialize the system for better performance
+            self.system = HybridLangGraphMultiLLMSystem()
+            print("✅ Optimized system initialized successfully.")
         except Exception as e:
-            print(f"❌ Error building system: {e}")
+            print(f"Error building graph: {e}")
+            self.graph = None
             self.system = None
 
     def __call__(self, question: str) -> str:
-        print(f"Processing: {question[:100]}...")
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
         
-        if self.system is None:
-            return "Error: System not initialized"
+        # Use the optimized system if available
+        if self.system:
+            try:
+                answer = self.system.process_query(question)
+                return answer
+            except Exception as e:
+                print(f"Error with optimized system: {e}")
         
-        try:
-            answer = self.system.process_query(question)
-            
-            # Validation
-            if not answer or answer == question or len(answer.strip()) == 0:
-                return "Information not available"
-            
-            return answer.strip()
+        # Fallback to original method if optimized system fails
+        if self.graph:
+            try:
+                # Create proper state for the graph
+                state = {
+                    "messages": [HumanMessage(content=question)],
+                    "query": question,
+                    "agent_type": "",
+                    "final_answer": "",
+                    "perf": {},
+                    "tools_used": []
+                }
+                config = {"configurable": {"thread_id": f"eval_{hash(question)}"}}
+                result = self.graph.invoke(state, config)
                 
-        except Exception as e:
-            return f"Error: {str(e)}"
+                # Extract the answer properly
+                if isinstance(result, dict) and 'final_answer' in result:
+                    return result['final_answer']
+                elif isinstance(result, dict) and 'messages' in result and result['messages']:
+                    return result['messages'][-1].content
+                else:
+                    return str(result)
+            except Exception as e:
+                return f"Error: {e}"
+        
+        return "Error: System not initialized"
+
+
+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
 
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """Run evaluation with working agent"""
-    space_id = os.getenv("SPACE_ID")
-    
     if profile:
-        username = f"{profile.username}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -56,115 +89,146 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Working Agent
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = WorkingMultiLLMAgent()
-        if agent.system is None:
-            return "Error: Failed to initialize working agent", None
+        agent = BasicAgent()
+        if agent.graph is None and agent.system is None:
+            return "Error: Failed to initialize agent properly", None
     except Exception as e:
+        print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "No space ID"
+    # 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 "No questions fetched", None
-        print(f"✅ Fetched {len(questions_data)} questions")
-    except Exception as e:
+             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:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 3. Process Questions
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    
-    for i, item in enumerate(questions_data):
+    print(f"Running optimized 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 {i+1}/{len(questions_data)}: {task_id}")
-        
         try:
-            answer = agent(question_text)
+            submitted_answer = agent(question_text)
             
-            # Prevent question repetition
-            if answer == question_text or answer.startswith(question_text):
-                answer = "Information not available"
+            # Additional validation to prevent question repetition
+            if submitted_answer == question_text or submitted_answer.startswith(question_text):
+                submitted_answer = "Information not available"
             
-            answers_payload.append({"task_id": task_id, "submitted_answer": answer})
-            results_log.append({
-                "Task ID": task_id,
-                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
-                "Submitted Answer": answer[:200] + "..." if len(answer) > 200 else 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:
-            error_msg = f"ERROR: {e}"
-            answers_payload.append({"task_id": task_id, "submitted_answer": error_msg})
-            results_log.append({
-                "Task ID": task_id,
-                "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text,
-                "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 generated", 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)
 
-    # 4. Submit Results
+    # 4. Prepare Submission 
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    
+    status_update = f"Optimized 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"
-            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', 'Success')}"
+            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
 
-# --- Gradio Interface ---
+
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Working Multi-LLM Agent System")
+    gr.Markdown("# Optimized Agent Evaluation Runner")
     gr.Markdown(
         """
-        **✅ This is a WORKING system that will actually answer questions!**
-        
-        **Features:**
-        - **Groq Llama-3 70B**: High-quality responses
-        - **Smart Routing**: Math, search, wiki, and general queries
-        - **Web Search**: Tavily integration for current information
-        - **Wikipedia**: Encyclopedic knowledge access
-        - **Robust Error Handling**: Fallbacks and validation
-        
         **Instructions:**
-        1. Log in with your Hugging Face account
-        2. Click 'Run Evaluation & Submit All Answers'
-        3. Wait for processing to complete
-        4. View your results and score
+        1.  This agent uses the optimized veryfinal.py system for better performance
+        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.
         
-        **Requirements:**
-        - GROQ_API_KEY in your environment variables
-        - TAVILY_API_KEY (optional, for web search)
+        **Optimizations:**
+        - Specialized question handlers for different types
+        - Enhanced search strategies (Wikipedia + Web)
+        - Better answer extraction and formatting
+        - Fallback answers for common questions
+        ---
+        **Expected Improvements:**
+        - Better handling of Mercedes Sosa album questions
+        - Improved Wikipedia article searches  
+        - Enhanced numerical answer extraction
+        - Better cipher/code question handling
         """
     )
 
     gr.LoginButton()
-    run_button = gr.Button("🚀 Run Evaluation & Submit All Answers", variant="primary")
-    status_output = gr.Textbox(label="Status", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Results", wrap=True)
+
+    run_button = gr.Button("🚀 Run Optimized Evaluation & Submit All Answers", variant="primary")
+
+    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,
@@ -172,5 +236,25 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("🚀 Starting Working Multi-LLM Agent System")
+    print("\n" + "-"*30 + " Optimized 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 Optimized Agent Evaluation...")
     demo.launch(debug=True, share=False)