Spaces:
Sleeping
Sleeping
| """ Enhanced Multi-LLM Agent Evaluation Runner with Vector Database Integration""" | |
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from langchain_core.messages import HumanMessage | |
| from veryfinal import build_graph, HybridLangGraphMultiLLMSystem | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Enhanced Agent Definition --- | |
| class EnhancedMultiLLMAgent: | |
| """A multi-provider LangGraph agent with vector database integration.""" | |
| def __init__(self): | |
| print("Enhanced Multi-LLM Agent with Vector Database initialized.") | |
| try: | |
| self.system = HybridLangGraphMultiLLMSystem(provider="groq") | |
| self.graph = self.system.graph | |
| # Load metadata if available | |
| if os.path.exists("metadata.jsonl"): | |
| print("Loading question metadata...") | |
| count = self.system.load_metadata_from_jsonl("metadata.jsonl") | |
| print(f"Loaded {count} questions into vector database") | |
| print("Enhanced Multi-LLM Graph built successfully.") | |
| except Exception as e: | |
| print(f"Error building graph: {e}") | |
| self.graph = None | |
| self.system = None | |
| def __call__(self, question: str) -> str: | |
| print(f"Agent received question: {question[:100]}...") | |
| if self.graph is None or self.system is None: | |
| return "Error: Agent not properly initialized" | |
| try: | |
| # Use the enhanced system's process_query method | |
| answer = self.system.process_query(question) | |
| # Additional validation | |
| if not answer or answer == question or len(answer.strip()) == 0: | |
| return "Information not available" | |
| 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): | |
| """Fetch questions, run enhanced 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 = 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" 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) | |
| 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(f"Fetched {len(questions_data)} questions.") | |
| except Exception as e: | |
| print(f"Error fetching questions: {e}") | |
| return f"Error fetching questions: {e}", None | |
| # 3. Run Enhanced Agent | |
| results_log = [] | |
| answers_payload = [] | |
| print(f"Running Enhanced Multi-LLM agent with vector database 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) | |
| # 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": 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}") | |
| 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"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) | |
| 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.')}" | |
| ) | |
| print("Submission successful.") | |
| results_df = pd.DataFrame(results_log) | |
| return final_status, results_df | |
| except Exception as e: | |
| status_message = f"Submission Failed: {e}" | |
| print(status_message) | |
| results_df = pd.DataFrame(results_log) | |
| return status_message, results_df | |
| # --- Build Gradio Interface --- | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Enhanced Multi-LLM Agent with Vector Database Integration") | |
| 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 (Llama-3 8B/70B, DeepSeek) | |
| - **Vector Database Integration**: FAISS + Supabase for similar question retrieval | |
| - **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 | |
| - **Similar Questions Context**: Uses vector similarity to provide relevant context | |
| - **Error Handling**: Robust fallback mechanisms and comprehensive logging | |
| **Routing Examples:** | |
| - Math: "What is 25 multiplied by 17?" → Llama-3 70B | |
| - Search: "Find information about Mercedes Sosa" → Search-Enhanced | |
| - Complex: "Analyze quantum computing principles" → DeepSeek | |
| - Simple: "What is the capital of France?" → Llama-3 8B | |
| **Vector Database Features:** | |
| - Automatic loading of metadata.jsonl if present | |
| - Similar question retrieval for enhanced context | |
| - Supabase integration for persistent storage | |
| - FAISS for fast vector similarity search | |
| """ | |
| ) | |
| 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 Multi-LLM Agent with Vector DB Starting " + "-"*30) | |
| demo.launch(debug=True, share=False) | |