import os import gradio as gr import requests import inspect import pandas as pd import asyncio from llama_index.core.agent.workflow import AgentWorkflow from agents.llama_index_agent import ( GaiaAgent, create_writer_agent, create_review_agent ) import json import hashlib from pathlib import Path # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ CLAUDE = { "model_provider": "anthropic", "model_name": "claude-3-7-sonnet-latest" } OPENAI = { "model_provider": "openai", "model_name": "gpt-4o" } class BasicAgent: def __init__( self, model_provider="openai", model_name="o4-mini", api_key=None, use_separate_writer_model=True, writer_model_provider="openai", writer_model_name="gpt-4o-mini", use_separate_review_model=True, review_model_provider="openai", review_model_name="gpt-4o-mini" ): """ Initialize the BasicAgent with a three-agent workflow. Args: model_provider: LLM provider for main agent model_name: Model name for main agent api_key: API key for main agent use_separate_writer_model: Whether to use a different model for the writer agent writer_model_provider: LLM provider for writer agent (if separate) writer_model_name: Model name for writer agent (if separate) use_separate_review_model: Whether to use a different model for the review agent review_model_provider: LLM provider for review agent (if separate) review_model_name: Model name for review agent (if separate) """ # Configure the main reasoning agent main_model_config = { "model_provider": model_provider, "model_name": model_name, "api_key": api_key } # Configure the writer agent (either same as main or different) if use_separate_writer_model: writer_model_config = { "model_provider": writer_model_provider, "model_name": writer_model_name, "api_key": api_key # Use same API key for simplicity } else: writer_model_config = main_model_config # Configure the review agent (either same as main or different) if use_separate_review_model: review_model_config = { "model_provider": review_model_provider, "model_name": review_model_name, "api_key": api_key # Use same API key for simplicity } else: review_model_config = main_model_config # Create the agents self.main_agent = GaiaAgent(**main_model_config) self.writer_agent = create_writer_agent(writer_model_config) self.review_agent = create_review_agent(review_model_config) # Update the GaiaAgent's can_handoff_to to include review_agent self.main_agent.can_handoff_to = ["writer_agent", "review_agent"] # Set up the agent workflow with shared context self.agent_workflow = AgentWorkflow( agents=[self.main_agent, self.writer_agent, self.review_agent], root_agent=self.main_agent.name, initial_state={ "original_question": "", "task_id": "", "audio_file_path": "", "analysis_notes": "", "format_requirements": "", "next_agent": "", "formatted_answer": "", "final_answer": "" } ) print(f"BasicAgent initialized with main agent: {model_provider} {model_name}") if use_separate_writer_model: print(f"Writer agent using: {writer_model_provider} {writer_model_name}") else: print(f"Writer agent using same model as main agent") if use_separate_review_model: print(f"Review agent using: {review_model_provider} {review_model_name}") else: print(f"Review agent using same model as main agent") def __call__(self, question_data: dict) -> str: """Process a GAIA benchmark question and return the formatted answer.""" # Extract question text and task_id question_text = question_data.get("question", "") task_id = question_data.get("task_id", "") file_name = question_data.get("file_name", "") print(f"Agent received question (first 50 chars): {question_text[:50]}...") # Download file if present local_file_path = None if file_name and task_id: try: local_file_path = self.download_task_file(question_data) print(f"Downloaded file to {local_file_path}") except Exception as e: print(f"Error downloading file: {e}") async def agentic_main(): # Initialize context with the question and file path initial_state = { "original_question": question_text, "task_id": task_id, "audio_file_path": local_file_path, "analysis_notes": "", "format_requirements": "", "next_agent": "", "final_answer": "", "workflow_state": "initial_analysis", # Track workflow state "require_handoff": True, # Flag that handoff is required } # Create a more detailed input with workflow instructions enhanced_input = f""" WORKFLOW INSTRUCTIONS: 1. You (jefe) MUST analyze this question and find the answer 2. After analysis, you MUST use the handoff tool to delegate to writer_agent 3. NEVER provide a direct answer - always delegate using the handoff tool Task ID: {task_id} Question: {question_text} """ # Add file information if available if local_file_path: enhanced_input += f"\nFile Path: {local_file_path}\n\nPlease analyze this question. If it involves an audio file, use the transcribe_audio tool with the provided path." # Monitor the workflow execution print("Starting workflow execution...") try: workflow_response = await self.agent_workflow.run( enhanced_input, initial_state=initial_state ) # Extract the final answer from the last response if hasattr(workflow_response.response, 'blocks') and workflow_response.response.blocks: final_answer = workflow_response.response.blocks[-1].text print(f"Workflow completed. Final answer extracted: {final_answer}") return final_answer else: print("Warning: Could not extract final answer from workflow response blocks") # Try to extract from the response content final_answer = str(workflow_response.response) return final_answer except Exception as e: print(f"Error in workflow execution: {e}") import traceback traceback.print_exc() return f"Error: {str(e)}" response = asyncio.run(agentic_main()) # Extract the final answer and remove any "Answer:" prefix final_answer = response.response.blocks[-1].text if hasattr(response, 'response') and hasattr(response.response, 'blocks') else str(response) if isinstance(final_answer, str) and final_answer.startswith("Answer:"): final_answer = final_answer.replace("Answer:", "").strip() print(f"Agent returning final answer: {final_answer}") return final_answer def download_task_file(self, question_data: dict) -> str: """Download a task file from the API and return the local file path.""" api_url = DEFAULT_API_URL file_url = f"{api_url}/files/{question_data['task_id']}" print(f"Downloading file from: {file_url}") try: response = requests.get(file_url, stream=True) response.raise_for_status() # Create a directory for downloaded files if it doesn't exist downloads_dir = Path("downloads") downloads_dir.mkdir(exist_ok=True) # Save the file to the downloads directory file_path = downloads_dir / f"{question_data['file_name']}" with open(file_path, "wb") as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) return str(file_path) except Exception as e: print(f"Error downloading file: {e}") raise def run_and_submit_all( profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent 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 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 ( modify this part to create your agent) try: agent = BasicAgent() except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public) 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(f"Fetched {len(questions_data)} questions.") except requests.exceptions.RequestException as e: print(f"Error fetching questions: {e}") return f"Error fetching questions: {e}", None except requests.exceptions.JSONDecodeError as e: print(f"Error decoding JSON response from questions endpoint: {e}") print(f"Response text: {response.text[:500]}") return f"Error decoding server response for 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 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 try: # Pass the entire item instead of just the question text submitted_answer = agent(item) 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}) except Exception as 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}"}) 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}'..." 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 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 # --- Build Gradio Interface using Blocks --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") 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. """ ) gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False) # Removed max_rows=10 from DataFrame constructor 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 + " App Starting " + "-"*30) # Check for SPACE_HOST and SPACE_ID at startup for information space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup if space_host_startup: print(f"✅ SPACE_HOST found: {space_host_startup}") print(f" Runtime URL should be: https://{space_host_startup}.hf.space") else: print("ℹ️ SPACE_HOST environment variable not found (running locally?).") if space_id_startup: # Print repo URLs if SPACE_ID is found 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?). Repo URL cannot be determined.") print("-"*(60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)