Update app.py

app.py

@@ -1,3 +1,4 @@
+""" Enhanced Multi-LLM Agent Evaluation Runner with Agno Integration"""
 import os
 import gradio as gr
 import requests
@@ -5,30 +6,74 @@ 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"
 
-class BasicAgent:
-    """A langgraph agent."""
+# --- Enhanced Agent Definition ---
+class EnhancedMultiLLMAgent:
+    """A multi-provider LangGraph agent with Agno-style reasoning capabilities."""
     def __init__(self):
-        print("BasicAgent initialized.")
-        self.graph = build_graph()
+        print("Enhanced Multi-LLM Agent with Agno Integration initialized.")
+        try:
+            self.graph = build_graph(provider="groq")
+            print("Enhanced Multi-LLM Graph built successfully.")
+        except Exception as e:
+            print(f"Error building graph: {e}")
+            self.graph = None
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        # Always pass the full state expected by the graph
+        
+        if self.graph is None:
+            return "Error: Agent not properly initialized"
+        
+        # CRITICAL FIX: Always pass the complete state expected by the graph
         state = {
-        "messages": [HumanMessage(content=question)],
-        "query": question,
-        "agent_type": "",
-        "final_answer": "",
-        "perf": {},
-        "agno_resp": ""}
+            "messages": [HumanMessage(content=question)],
+            "query": question,  # This was the critical missing field
+            "agent_type": "",
+            "final_answer": "",
+            "perf": {},
+            "agno_resp": "",
+            "tools_used": [],
+            "reasoning": "",
+            "confidence": ""
+        }
+        # CRITICAL FIX: Always provide the required config with thread_id
         config = {"configurable": {"thread_id": f"eval_{hash(question)}"}}
-        result = self.graph.invoke(state, config)
-        return result.get("final_answer", "")
+        
+        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
 
 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.
+    """
     space_id = os.getenv("SPACE_ID")
+    
     if profile:
         username = f"{profile.username}"
         print(f"User logged in: {username}")
@@ -40,14 +85,19 @@ 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 = BasicAgent()
+        agent = EnhancedMultiLLMAgent()
+        if agent.graph 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"
-    print(agent_code)
+    
+    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}")
 
+    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -61,31 +111,49 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
 
+    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    print(f"Running Enhanced Multi-LLM agent with Agno integration on {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}")
             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, "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
+            })
         except Exception as e:
+            error_msg = f"AGENT ERROR: {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}"})
+            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
+            })
 
     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}'..."
+    status_update = f"Enhanced Multi-LLM 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)
@@ -107,24 +175,35 @@ 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("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Enhanced Multi-LLM Agent with Agno Integration")
     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.
+        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 (Llama-3 8B/70B, DeepSeek), Google Gemini, NVIDIA NIM
+        - **Agno Integration**: Systematic reasoning with step-by-step analysis
+        - **Intelligent Routing**: Automatically selects best provider based on query complexity
+        - **Enhanced Tools**: Mathematical operations, web search, Wikipedia integration
+        - **Question-Answering**: Optimized for evaluation tasks with proper formatting
+        - **Error Handling**: Robust fallback mechanisms and comprehensive logging
+        
+        **Routing Examples:**
+        - Standard: "What is the capital of France?" → Llama-3 8B
+        - Complex: "Analyze quantum computing principles" → Llama-3 70B
+        - Search: "Find information about Mercedes Sosa" → Search-Enhanced
+        - Agno: "agno llama-70: Systematic analysis of AI ethics" → Agno Llama-3 70B
+        - Provider-specific: "google: Explain machine learning" → Google Gemini
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
@@ -135,5 +214,5 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    print("\n" + "-"*30 + " Enhanced Multi-LLM Agent with Agno Starting " + "-"*30)
     demo.launch(debug=True, share=False)