Update app.py

app.py

@@ -1,79 +1,36 @@
-""" Multi-LLM 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
 
-# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Enhanced Agent Definition ---
-class EnhancedMultiLLMAgent:
-    """A multi-provider LangGraph agent supporting Groq, DeepSeek, and Baidu."""
+class BasicAgent:
+    """A langgraph agent."""
     def __init__(self):
-        print("Enhanced Multi-LLM Agent initialized.")
-        try:
-            self.graph = build_graph(provider="groq")  # Using Groq as default
-            print("Multi-LLM Graph built successfully.")
-        except Exception as e:
-            print(f"Error building graph: {e}")
-            self.graph = None
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
-        print(f"Agent received question: {question}")
-        
-        if self.graph is None:
-            return "Error: Agent not properly initialized"
-        
-        # Create complete state structure that matches EnhancedAgentState
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # Always pass the full state expected by the graph
         state = {
             "messages": [HumanMessage(content=question)],
-            "query": question,  # This was the critical missing field
+            "query": question,
             "agent_type": "",
             "final_answer": "",
             "perf": {},
             "agno_resp": ""
         }
-        config = {"configurable": {"thread_id": f"eval_{hash(question)}"}}
-        
-        try:
-            result = self.graph.invoke(state, config)
-            
-            # Handle different response formats
-            if isinstance(result, dict):
-                if 'messages' in result and result['messages']:
-                    answer = result['messages'][-1].content
-                elif 'final_answer' in result:
-                    answer = result['final_answer']
-                else:
-                    answer = str(result)
-            else:
-                answer = str(result)
-            
-            # Extract final answer if present
-            if "FINAL ANSWER:" in answer:
-                return answer.split("FINAL ANSWER:")[-1].strip()
-            else:
-                return answer.strip()
-                
-        except Exception as e:
-            error_msg = f"Error: {str(e)}"
-            print(error_msg)
-            return error_msg
+        result = self.graph.invoke(state)
+        return result.get("final_answer", "")
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the Enhanced Multi-LLM Agent 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
-
+    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.")
@@ -83,78 +40,52 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
     try:
-        agent = EnhancedMultiLLMAgent()
-        if agent.graph is None:
-            return "Error: Failed to initialize agent properly", None
+        agent = BasicAgent()
     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 available"
-    print(f"Agent code URL: {agent_code}")
+    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:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", 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 requests.exceptions.RequestException as e:
+    except Exception as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching 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
     results_log = []
     answers_payload = []
-    print(f"Running Enhanced Multi-LLM agent on {len(questions_data)} questions...")
-    
-    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}")
-        
         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[:100] + "..." if len(question_text) > 100 else question_text, 
-                "Submitted Answer": submitted_answer[:200] + "..." if len(submitted_answer) > 200 else submitted_answer
-            })
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-             error_msg = f"AGENT ERROR: {e}"
-             print(f"Error running agent on task {task_id}: {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:
         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"Enhanced Multi-LLM Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    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)
@@ -176,33 +107,24 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Enhanced Multi-LLM Agent Evaluation Runner")
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1. Log in to your Hugging Face account using the button below.
-        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-        
-        **Enhanced Agent Features:**
-        - **Multi-LLM Support**: Groq, DeepSeek, and Baidu ERNIE
-        - **Intelligent Routing**: Automatically selects best provider based on query
-        - **Mathematical Tools**: Add, subtract, multiply, divide, modulus operations
-        - **Web Search**: Tavily and Wikipedia integration
-        - **Error Handling**: Robust fallback mechanisms
-        - **Rate Limiting**: Optimized for free tier usage
-        
-        **Supported Models:**
-        - **Groq**: Llama 3.1 70B Versatile (fast inference)
-        - **DeepSeek**: DeepSeek Chat (reasoning-focused)
-        - **Baidu**: ERNIE (Chinese language optimized)
+        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", variant="primary")
+    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)
@@ -213,5 +135,5 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " Enhanced Multi-LLM Agent Starting " + "-"*30)
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
     demo.launch(debug=True, share=False)