""" Enhanced LangGraph Agent Evaluation Runner - Final Version""" import os 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 EnhancedLangGraphAgent: """Enhanced LangGraph agent with proper response handling.""" def __init__(self): print("Enhanced LangGraph Agent initialized.") try: self.graph = build_graph(provider="groq") print("LangGraph built successfully.") except Exception as e: print(f"Error building graph: {e}") self.graph = None def __call__(self, question: str) -> str: print(f"Processing: {question[:100]}...") if self.graph is None: return "Error: Agent not properly initialized" try: # Create messages and config messages = [HumanMessage(content=question)] config = {"configurable": {"thread_id": f"eval_{hash(question)}"}} # Invoke the graph result = self.graph.invoke({"messages": messages}, config) # Extract the final answer if result and "messages" in result and result["messages"]: final_message = result["messages"][-1] if hasattr(final_message, 'content'): answer = final_message.content else: answer = str(final_message) # Clean up the answer if "FINAL ANSWER:" in answer: answer = answer.split("FINAL ANSWER:")[-1].strip() # Validate the answer if not answer or answer == question or len(answer.strip()) == 0: return "Information not available" return answer.strip() else: return "Information not available" except Exception as e: print(f"Error processing question: {e}") return f"Error: {str(e)}" def run_and_submit_all(profile: gr.OAuthProfile | None): """Fetch questions, run agent, and submit answers.""" space_id = os.getenv("SPACE_ID") 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 api_url = DEFAULT_API_URL questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" # 1. Instantiate Agent try: agent = EnhancedLangGraphAgent() 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" if space_id else "No space ID available" # 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 "Fetched questions list is empty or invalid format.", None print(f"Fetched {len(questions_data)} questions.") except Exception as e: return f"Error fetching questions: {e}", None # 3. Run Agent results_log = [] answers_payload = [] print(f"Running Enhanced LangGraph agent 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: 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 }) except Exception as e: error_msg = 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: return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) # 4. Submit submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} print(f"Submitting {len(answers_payload)} answers...") 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"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.')}" ) return final_status, pd.DataFrame(results_log) except Exception as e: return f"Submission Failed: {e}", pd.DataFrame(results_log) # --- Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Enhanced LangGraph Agent - Final Version") gr.Markdown( """ **Features:** - ✅ Proper LangGraph structure with tool integration - ✅ Multi-LLM support (Groq, Google, HuggingFace) - ✅ Enhanced search capabilities (Wikipedia, Tavily, ArXiv) - ✅ Mathematical tools for calculations - ✅ Vector store integration for similar questions - ✅ Proper response formatting and validation - ✅ Error handling and fallback mechanisms **Tools Available:** - Mathematical operations (add, subtract, multiply, divide, modulus) - Wikipedia search for encyclopedic information - Web search via Tavily for current information - ArXiv search for academic papers - Vector similarity search for related questions """ ) gr.LoginButton() 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) run_button.click( fn=run_and_submit_all, outputs=[status_output, results_table] ) if __name__ == "__main__": print("\n" + "-"*30 + " Enhanced LangGraph Agent Starting " + "-"*30) demo.launch(debug=True, share=False)