import os import re import tempfile from pathlib import Path from typing import Optional import gradio as gr import pandas as pd import requests from smolagents import CodeAgent, DuckDuckGoSearchTool, VisitWebpageTool try: from smolagents import OpenAIServerModel except ImportError: # Older smolagents versions may not expose this class. OpenAIServerModel = None try: from smolagents import LiteLLMModel except ImportError: LiteLLMModel = None from smolagents import InferenceClientModel DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" class BasicAgent: def __init__(self): print("BasicAgent initialized.") self.model = self._build_model() self.agent = CodeAgent( tools=[ DuckDuckGoSearchTool(), VisitWebpageTool(), ], model=self.model, add_base_tools=True, additional_authorized_imports=[ "collections", "csv", "datetime", "fractions", "itertools", "json", "math", "mutagen", "numpy", "os", "pandas", "pathlib", "PIL", "PIL.Image", "pypdf", "re", "statistics", "string", "time", "unicodedata", "wave", "zipfile", ], max_steps=int(os.getenv("AGENT_MAX_STEPS", "10")), verbosity_level=1, ) def _build_model(self): """Prefer non-HF paid routes, then fall back to HF Inference Providers.""" if os.getenv("OPENAI_API_KEY") and OpenAIServerModel is not None: print("Using OpenAI-compatible model.") return OpenAIServerModel( model_id=os.getenv("OPENAI_MODEL", "gpt-4o-mini"), api_base=os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"), api_key=os.environ["OPENAI_API_KEY"], temperature=0, max_tokens=4096, ) if os.getenv("OPENAI_API_KEY") and LiteLLMModel is not None: print("Using OpenAI model through LiteLLM.") return LiteLLMModel( model_id=os.getenv("OPENAI_MODEL", "gpt-4o-mini"), api_key=os.environ["OPENAI_API_KEY"], temperature=0, max_tokens=4096, ) if os.getenv("GROQ_API_KEY") and OpenAIServerModel is not None: print("Using Groq OpenAI-compatible model.") return OpenAIServerModel( model_id=os.getenv("GROQ_MODEL", "llama-3.3-70b-versatile"), api_base="https://api.groq.com/openai/v1", api_key=os.environ["GROQ_API_KEY"], temperature=0, max_tokens=4096, flatten_messages_as_text=True, ) if os.getenv("GROQ_API_KEY") and LiteLLMModel is not None: print("Using Groq model through LiteLLM.") return LiteLLMModel( model_id=f"groq/{os.getenv('GROQ_MODEL', 'llama-3.3-70b-versatile')}", "Final answer:", "Final Answer:", "FINAL ANSWER:", "Answer:", "The answer is", "The final answer is", ] for prefix in prefixes: if answer.startswith(prefix): answer = answer[len(prefix):].strip() answer = answer.strip().strip('"').strip("'").strip() return answer def run_and_submit_all(profile: gr.OAuthProfile | None): space_id = os.getenv("SPACE_ID") username = profile.username if profile and profile.username else os.getenv("HF_USERNAME", "GionaZardini") print(f"Using username: {username}") 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" if space_id else "" 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 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 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: submitted_answer = agent.answer_question(question_text, task_id=task_id) 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}"} ) results_df = pd.DataFrame(results_log) if not answers_payload: print("Agent did not produce any answers to submit.") return "Agent did not produce any answers to submit.", results_df 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) 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, 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) return status_message, results_df except requests.exceptions.Timeout: status_message = "Submission Failed: The request timed out." print(status_message) return status_message, results_df except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" print(status_message) return status_message, results_df except Exception as e: status_message = f"An unexpected error occurred during submission: {e}" print(status_message) return status_message, results_df with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. Clone this space, then modify the code to define your agent's logic, tools, and packages. 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 the score. --- **Disclaimers:** Once clicking on the submit button, it can take quite some time. """ ) 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_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 should be: https://{space_host_startup}.hf.space") else: print("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("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)