import os import gradio as gr import requests import pandas as pd # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" HF_TOKEN = os.getenv("HF_TOKEN") # Make sure your HF read token is set in environment variables # --- Gaia Agent using Qwen API --- class GaiaAgentQwen: def __init__(self, model="Qwen/Qwen2.5-Coder-32B-Instruct"): self.model = model self.api_url = f"https://api-inference.huggingface.co/models/{model}" self.headers = {"Authorization": f"Bearer {HF_TOKEN}"} print(f"GaiaAgentQwen initialized with model {model}") def __call__(self, question: str) -> str: prompt = f"Answer the following question concisely and correctly:\n{question}" payload = {"inputs": prompt, "options": {"wait_for_model": True}} try: response = requests.post(self.api_url, headers=self.headers, json=payload, timeout=60) response.raise_for_status() data = response.json() if isinstance(data, list) and "generated_text" in data[0]: return data[0]["generated_text"] else: return str(data) # fallback except Exception as e: print(f"Error calling HF Inference API: {e}") return f"API ERROR: {e}" # --- Main function --- def run_and_submit_all(profile: gr.OAuthProfile | None): api_url = DEFAULT_API_URL space_id = os.getenv("SPACE_ID") or "unknown-space" username = profile.username if profile else "anonymous" if profile: print(f"User logged in: {username}") else: print("User not logged in.") questions_url = f"{api_url}/questions" submit_url = f"{api_url}/submit" # Instantiate the Gaia agent try: agent = GaiaAgentQwen() except Exception as e: return f"Error initializing agent: {e}", None agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(f"Agent code repo: {agent_code}") # Fetch questions try: print(f"Fetching questions from: {questions_url}") response = requests.get(questions_url, timeout=10) 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 # Run agent on questions 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 not question_text: print(f"Skipping invalid question: {item}") continue try: answer = agent(question_text) answers_payload.append({"task_id": task_id, "submitted_answer": answer}) results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": 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) # Submit answers submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload} try: print(f"Submitting {len(answers_payload)} answers for user '{username}'...") response = requests.post(submit_url, json=submission_data, timeout=20) response.raise_for_status() submission_result = response.json() print(f"Submission result: {submission_result}") return "Submission completed successfully!", pd.DataFrame(results_log) except Exception as e: return f"Error submitting answers: {e}", pd.DataFrame(results_log) # --- Build Gradio Interface --- with gr.Blocks() as demo: gr.Markdown("# Gaia Agent Evaluation Runner") gr.Markdown(""" **Instructions:** 1. Clone this space, then modify the code to define your agent's logic. 2. Log in to your Hugging Face account using the button below. 3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see results. **Note:** Using the HF API can take a few seconds per question. """) login_btn = 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, inputs=[login_btn], outputs=[status_output, results_table] ) if __name__ == "__main__": print("\n" + "-"*30 + " App Starting " + "-"*30) print("Launching Gradio Interface for Gaia Agent Evaluation...") demo.launch(debug=True, share=False)