Spaces:
Sleeping
Sleeping
| """ Enhanced Hybrid Agent Evaluation Runner""" | |
| import os | |
| import inspect | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from langchain_core.messages import HumanMessage | |
| from agent import HybridLangGraphAgnoSystem | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Enhanced Basic Agent Definition --- | |
| class BasicAgent: | |
| """A hybrid LangGraph + Agno agent with performance optimization.""" | |
| def __init__(self): | |
| print("BasicAgent initialized with Hybrid LangGraph + Agno System.") | |
| self.hybrid_system = HybridLangGraphAgnoSystem() | |
| def __call__(self, question: str) -> str: | |
| print(f"Agent received question: {question}") | |
| try: | |
| # Process query using hybrid system | |
| result = self.hybrid_system.process_query(question) | |
| # Extract final answer | |
| answer = result.get("answer", "No response generated") | |
| # Clean up the answer - extract only final answer if present | |
| if "FINAL ANSWER:" in answer: | |
| final_answer = answer.split("FINAL ANSWER:")[-1].strip() | |
| else: | |
| final_answer = answer.strip() | |
| # Log performance metrics for debugging | |
| metrics = result.get("performance_metrics", {}) | |
| provider = result.get("provider_used", "Unknown") | |
| processing_time = metrics.get("total_time", 0) | |
| print(f"Provider used: {provider}, Processing time: {processing_time:.2f}s") | |
| return final_answer | |
| except Exception as e: | |
| print(f"Error in agent processing: {e}") | |
| return f"Error: {str(e)}" | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the Enhanced Hybrid Agent on them, submits all answers, | |
| and displays the results with performance metrics. | |
| """ | |
| # --- Determine HF Space Runtime URL and Repo URL --- | |
| space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code | |
| 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 Enhanced Hybrid Agent | |
| try: | |
| agent = BasicAgent() | |
| print("✅ Hybrid LangGraph + Agno Agent initialized successfully") | |
| except Exception as e: | |
| print(f"❌ Error instantiating hybrid agent: {e}") | |
| return f"Error initializing hybrid agent: {e}", None | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| print(f"🔗 Agent code repository: {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 successfully.") | |
| except requests.exceptions.RequestException 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 Enhanced Hybrid Agent with Performance Tracking | |
| results_log = [] | |
| answers_payload = [] | |
| performance_stats = { | |
| "langgraph_math": 0, | |
| "agno_research": 0, | |
| "langgraph_retrieval": 0, | |
| "agno_general": 0, | |
| "errors": 0, | |
| "total_processing_time": 0 | |
| } | |
| print(f"🚀 Running Enhanced Hybrid Agent on {len(questions_data)} questions...") | |
| for i, item in enumerate(questions_data, 1): | |
| task_id = item.get("task_id") | |
| question_text = item.get("question") | |
| if not task_id or question_text is None: | |
| print(f"⚠️ Skipping item {i} with missing task_id or question: {item}") | |
| continue | |
| print(f"🔄 Processing question {i}/{len(questions_data)}: {task_id}") | |
| try: | |
| # Get detailed result from hybrid system | |
| detailed_result = agent.hybrid_system.process_query(question_text) | |
| submitted_answer = detailed_result.get("answer", "No response") | |
| # Extract final answer | |
| if "FINAL ANSWER:" in submitted_answer: | |
| clean_answer = submitted_answer.split("FINAL ANSWER:")[-1].strip() | |
| else: | |
| clean_answer = submitted_answer.strip() | |
| # Track performance metrics | |
| provider = detailed_result.get("provider_used", "Unknown") | |
| processing_time = detailed_result.get("performance_metrics", {}).get("total_time", 0) | |
| # Update performance stats | |
| if "LangGraph" in provider: | |
| if "Math" in provider: | |
| performance_stats["langgraph_math"] += 1 | |
| else: | |
| performance_stats["langgraph_retrieval"] += 1 | |
| elif "Agno" in provider: | |
| if "Research" in provider: | |
| performance_stats["agno_research"] += 1 | |
| else: | |
| performance_stats["agno_general"] += 1 | |
| performance_stats["total_processing_time"] += processing_time | |
| answers_payload.append({"task_id": task_id, "submitted_answer": clean_answer}) | |
| results_log.append({ | |
| "Task ID": task_id, | |
| "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text, | |
| "Submitted Answer": clean_answer, | |
| "Provider": provider, | |
| "Processing Time (s)": f"{processing_time:.2f}" | |
| }) | |
| print(f"✅ Question {i} processed successfully using {provider}") | |
| except Exception as e: | |
| print(f"❌ Error running agent on task {task_id}: {e}") | |
| performance_stats["errors"] += 1 | |
| results_log.append({ | |
| "Task ID": task_id, | |
| "Question": question_text[:100] + "..." if len(question_text) > 100 else question_text, | |
| "Submitted Answer": f"AGENT ERROR: {e}", | |
| "Provider": "Error", | |
| "Processing Time (s)": "0.00" | |
| }) | |
| 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. Performance Summary | |
| avg_processing_time = performance_stats["total_processing_time"] / len(answers_payload) if answers_payload else 0 | |
| performance_summary = f""" | |
| 📊 Performance Summary: | |
| • LangGraph Math: {performance_stats['langgraph_math']} queries | |
| • Agno Research: {performance_stats['agno_research']} queries | |
| • LangGraph Retrieval: {performance_stats['langgraph_retrieval']} queries | |
| • Agno General: {performance_stats['agno_general']} queries | |
| • Errors: {performance_stats['errors']} queries | |
| • Average Processing Time: {avg_processing_time:.2f}s | |
| • Total Processing Time: {performance_stats['total_processing_time']:.2f}s | |
| """ | |
| print(performance_summary) | |
| # 5. Prepare Submission | |
| submission_data = { | |
| "username": username.strip(), | |
| "agent_code": agent_code, | |
| "answers": answers_payload | |
| } | |
| status_update = f"🎯 Hybrid Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." | |
| print(status_update) | |
| # 6. Submit Results | |
| print(f"📤 Submitting {len(answers_payload)} answers to: {submit_url}") | |
| try: | |
| response = requests.post(submit_url, json=submission_data, timeout=120) # Increased timeout | |
| 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.')}\n" | |
| f"{performance_summary}" | |
| ) | |
| 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: | |
| status_message = f"❌ An unexpected error occurred during submission: {e}" | |
| print(status_message) | |
| results_df = pd.DataFrame(results_log) | |
| return status_message, results_df | |
| # --- Enhanced Gradio Interface --- | |
| with gr.Blocks(title="Enhanced Hybrid Agent Evaluation") as demo: | |
| gr.Markdown("# 🚀 Enhanced Hybrid LangGraph + Agno Agent Evaluation Runner") | |
| gr.Markdown( | |
| """ | |
| ## 🎯 **Advanced AI Agent System** | |
| This evaluation runner uses a **Hybrid LangGraph + Agno Agent System** that combines the best of both frameworks: | |
| ### 🧠 **Intelligent Routing System** | |
| - **🔢 Mathematical Queries** → LangGraph (Groq Llama 3.3 70B) - *Optimized for speed* | |
| - **🔍 Complex Research** → Agno (Gemini 2.0 Flash-Lite) - *Optimized for reasoning* | |
| - **📚 Factual Retrieval** → LangGraph + FAISS Vector Store - *Optimized for accuracy* | |
| - **🎭 General Queries** → Agno Multi-Agent System - *Optimized for comprehensiveness* | |
| ### ⚡ **Performance Features** | |
| - **Rate Limiting**: Intelligent rate management for free tier models | |
| - **Caching**: Performance optimization with query caching | |
| - **Fallback Systems**: Automatic provider switching on failures | |
| - **Performance Tracking**: Real-time metrics and provider usage stats | |
| ### 🛠 **Tools & Capabilities** | |
| - Mathematical calculations (add, subtract, multiply, divide, modulus) | |
| - Web search (Tavily, Wikipedia, ArXiv) | |
| - FAISS vector database for similar question retrieval | |
| - Memory persistence across sessions | |
| --- | |
| **Instructions:** | |
| 1. 🔐 Log in to your Hugging Face account using the button below | |
| 2. 🚀 Click 'Run Evaluation & Submit All Answers' to start the evaluation | |
| 3. 📊 Monitor real-time performance metrics and provider usage | |
| 4. 🏆 View your final score and detailed results | |
| **Note:** The hybrid system automatically selects the optimal AI provider for each question type to maximize both speed and accuracy. | |
| """ | |
| ) | |
| gr.LoginButton() | |
| with gr.Row(): | |
| run_button = gr.Button( | |
| "🚀 Run Evaluation & Submit All Answers", | |
| variant="primary", | |
| size="lg" | |
| ) | |
| status_output = gr.Textbox( | |
| label="📊 Run Status / Submission Result", | |
| lines=10, | |
| interactive=False, | |
| placeholder="Status updates will appear here..." | |
| ) | |
| results_table = gr.DataFrame( | |
| label="📋 Questions, Answers & Performance Metrics", | |
| wrap=True, | |
| height=400 | |
| ) | |
| run_button.click( | |
| fn=run_and_submit_all, | |
| outputs=[status_output, results_table] | |
| ) | |
| # Add footer with system info | |
| gr.Markdown( | |
| """ | |
| --- | |
| ### 🔧 **System Information** | |
| - **Primary Models**: Groq Llama 3.3 70B, Gemini 2.0 Flash-Lite, NVIDIA Llama 3.1 70B | |
| - **Frameworks**: LangGraph + Agno Hybrid Architecture | |
| - **Vector Store**: FAISS with NVIDIA Embeddings | |
| - **Rate Limiting**: Advanced rate management with exponential backoff | |
| - **Memory**: Persistent agent memory with session summaries | |
| """ | |
| ) | |
| if __name__ == "__main__": | |
| print("\n" + "="*80) | |
| print("🚀 ENHANCED HYBRID AGENT EVALUATION RUNNER") | |
| print("="*80) | |
| # Check for environment variables | |
| space_host_startup = os.getenv("SPACE_HOST") | |
| space_id_startup = os.getenv("SPACE_ID") | |
| if space_host_startup: | |
| print(f"✅ SPACE_HOST found: {space_host_startup}") | |
| print(f" 🌐 Runtime URL: https://{space_host_startup}.hf.space") | |
| else: | |
| print("ℹ️ SPACE_HOST environment variable not found (running locally?).") | |
| if space_id_startup: | |
| 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?).") | |
| print("\n🎯 System Features:") | |
| print(" • Hybrid LangGraph + Agno Architecture") | |
| print(" • Intelligent Query Routing") | |
| print(" • Performance Optimization") | |
| print(" • Advanced Rate Limiting") | |
| print(" • FAISS Vector Database") | |
| print(" • Multi-Provider Fallbacks") | |
| print("\n" + "="*80) | |
| print("🎉 Launching Enhanced Gradio Interface...") | |
| print("="*80 + "\n") | |
| demo.launch(debug=True, share=False) | |