import os import gradio as gr import requests import inspect import pandas as pd from openai import OpenAI client = OpenAI(api_key="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") # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # --- Basic Agent Definition --- class BasicAgent: def __init__(self): self.api_key = os.getenv("OPENAI_API_KEY") if not self.api_key: raise ValueError("OpenAI API key not found. Please set OPENAI_API_KEY as environment variable.") # Optional: Log OpenAI constructor arguments print("🔍 OpenAI init params:", list(inspect.signature(OpenAI.__init__).parameters.keys())) # ✅ Ensure only valid args passed self.client = OpenAI(api_key=self.api_key) print("✅ OpenAI Agent initialized (v1+ syntax).") def __call__(self, question: str) -> str: print(f"❓ Question received: {question[:50]}...") try: response = self.client.chat.completions.create( model="gpt-3.5-turbo", messages=[ {"role": "system", "content": "You are a helpful assistant that answers GAIA benchmark questions."}, {"role": "user", "content": question} ], max_tokens=300, temperature=0.7 ) answer = response.choices[0].message.content.strip() print(f"✅ Answer: {answer}") return answer except Exception as e: print(f"❌ Error calling OpenAI API: {e}") return f"ERROR: {e}" def run_and_submit_all(profile: gr.OAuthProfile | None): 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" try: agent = BasicAgent() 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" print(agent_code) 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: {e}") return f"Error decoding server response for questions: {e}", None except Exception as e: print(f"Unexpected error fetching questions: {e}") return f"Unexpected error fetching questions: {e}", None 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 invalid item: {item}") continue 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: 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: return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) submission_data = { "username": username.strip(), "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.')}" ) print("Submission successful.") return final_status, pd.DataFrame(results_log) except requests.exceptions.HTTPError as e: try: error_detail = f"{e.response.status_code} - {e.response.json().get('detail', e.response.text)}" except Exception: error_detail = f"{e.response.status_code} - {e.response.text}" return f"Submission Failed: {error_detail}", pd.DataFrame(results_log) except requests.exceptions.Timeout: return "Submission Failed: The request timed out.", pd.DataFrame(results_log) except requests.exceptions.RequestException as e: return f"Submission Failed: Network error - {e}", pd.DataFrame(results_log) except Exception as e: return f"Unexpected error during submission: {e}", pd.DataFrame(results_log) # --- Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown(""" **Instructions:** 1. Clone this space and modify the code to define your own agent. 2. Log in with your Hugging Face account. 3. Click 'Run Evaluation & Submit All Answers' to start. """) 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: {space_host}") print(f"Runtime URL: https://{space_host}.hf.space") else: print("ℹī¸ SPACE_HOST not found.") if space_id: print(f"✅ SPACE_ID: {space_id}") print(f"Repo: https://huggingface.co/spaces/{space_id}/tree/main") else: print("ℹī¸ SPACE_ID not found.") print("-" * 70) print("Launching Gradio Interface...") demo.launch(debug=True, share=False)