import os import requests import pandas as pd import gradio as gr from smolagents import ToolCallingAgent, OpenAIServerModel from audio_transcriber import AudioTranscriptionTool from image_analyzer import ImageAnalysisTool from wikipedia_searcher import WikipediaSearcher DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" class GaiaAgent: def __init__(self): tools = [ AudioTranscriptionTool(), ImageAnalysisTool(), WikipediaSearcher() ] model_id = os.getenv("OPENAI_MODEL_ID", "gpt-3.5-turbo") self.agent = ToolCallingAgent( model=OpenAIServerModel(model_id=model_id), tools=tools ) def __call__(self, query: str) -> str: result = self.agent.run(query) return result.get("output", "No output returned") def run_and_submit_all(profile: gr.OAuthProfile | None): space_id = os.getenv("SPACE_ID") if profile: username = profile.username if isinstance(username, list): username = username[0] username = username.strip() 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" try: agent = GaiaAgent() except Exception as e: print(f"Error initializing agent: {e}") return f"Error initializing agent: {e}", None agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(f"Agent code URL: {agent_code}") 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 results_log = [] answers_payload = [] for item in questions_data: task_id = item.get("task_id") if not task_id: continue question_text = item.get("question", "") file_url = item.get("file_url") local_file_path = None if file_url: try: ext = file_url.split(".")[-1].lower() if ext in ["mp3", "wav", "jpeg", "jpg", "png"]: local_file_path = f"./temp_{task_id}.{ext}" with requests.get(file_url, stream=True) as r: r.raise_for_status() with open(local_file_path, "wb") as f: for chunk in r.iter_content(chunk_size=8192): f.write(chunk) print(f"Downloaded file for task {task_id} to {local_file_path}") question_text += f"\n\nFile path: {local_file_path}" except Exception as e: print(f"Failed to download file for task {task_id}: {e}") 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 }) except Exception as e: error_msg = f"AGENT ERROR: {e}" results_log.append({ "Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg }) if local_file_path: try: os.remove(local_file_path) except Exception: pass if not answers_payload: return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) submission_data = { "username": username, "agent_code": agent_code, "answers": answers_payload } 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.')}" ) results_df = pd.DataFrame(results_log) return final_status, results_df except requests.exceptions.HTTPError as e: try: detail = e.response.json().get("detail", e.response.text) except Exception: detail = e.response.text[:500] return f"Submission Failed: {detail}", pd.DataFrame(results_log) except requests.exceptions.Timeout: return "Submission Failed: The request timed out.", pd.DataFrame(results_log) except Exception as e: return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log) # Gradio UI with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown(""" **Instructions:** 1. Clone this space and define your agent and tools. 2. Log in to your Hugging Face account using the button below. 3. Click 'Run Evaluation & Submit All Answers' to test your agent and submit results. """) gr.LoginButton() run_button = gr.Button("Run Evaluation & Submit All Answers") 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 + " App Starting " + "-"*30) space_host = os.getenv("SPACE_HOST") space_id = os.getenv("SPACE_ID") if space_host: print(f"✅ SPACE_HOST found: {space_host}") print(f" Runtime URL should be: https://{space_host}.hf.space") else: print("ℹ️ SPACE_HOST not found.") if space_id: print(f"✅ SPACE_ID found: {space_id}") print(f" Repo URL: https://huggingface.co/spaces/{space_id}") else: print("ℹ️ SPACE_ID not found.") print("-"*(60 + len(" App Starting ")) + "\n") demo.launch(debug=True, share=False)