import os import time import traceback import gradio as gr import requests import pandas as pd import spaces @spaces.GPU def _keep_alive(): return None # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # TEK KAYNAK: model sirasi sadece burada. Sirasiyla denenir. # Not: 2.x modeller listede gorunse bile yeni API key'lere kapali (404 verir), # o yuzden buraya hic koymuyoruz. MODEL_CANDIDATES = [ "gemini-3.1-flash-lite", "gemini-3-flash-preview", "gemini-3.5-flash-lite", "gemini-flash-latest", "gemini-3.5-flash", "gemini-3.6-flash", ] # 503 / asiri yuk hatalarini yakalamak icin anahtar kelimeler OVERLOAD_KEYS = ("503", "UNAVAILABLE", "ServiceUnavailable", "overloaded", "high demand") def log_available_models(api_key: str) -> None: """Sadece bilgi amacli: key'in gordugu modelleri loglar.""" try: r = requests.get( "https://generativelanguage.googleapis.com/v1beta/models", headers={"x-goog-api-key": api_key}, timeout=20, ) r.raise_for_status() available = [ m["name"].replace("models/", "") for m in r.json().get("models", []) if "generateContent" in m.get("supportedGenerationMethods", []) ] print("=" * 70) print("AVAILABLE MODELS FOR THIS KEY:") for m in available: print(" -", m) print("=" * 70) except Exception as e: print(f"[MODEL LIST ERROR] {type(e).__name__}: {e}") # --- Basic Agent Definition --- class BasicAgent: def __init__(self): self.api_key = os.environ["GEMINI_API_KEY"] log_available_models(self.api_key) self.model_idx = 0 self._build_agent() def _build_agent(self) -> None: from smolagents import CodeAgent, LiteLLMModel, PythonInterpreterTool name = MODEL_CANDIDATES[self.model_idx] print(f"[MODEL] agent kuruluyor -> gemini/{name}") model = LiteLLMModel( model_id=f"gemini/{name}", api_key=self.api_key, num_retries=5, ) try: from smolagents import WebSearchTool search_tool = WebSearchTool() print("[TOOL] WebSearchTool") except ImportError: from smolagents import DuckDuckGoSearchTool search_tool = DuckDuckGoSearchTool() print("[TOOL] DuckDuckGoSearchTool") self.agent = CodeAgent( tools=[search_tool, PythonInterpreterTool()], model=model, max_steps=6, ) def _switch_model(self) -> bool: if self.model_idx + 1 < len(MODEL_CANDIDATES): self.model_idx += 1 print(f"[FALLBACK] siradaki modele geciliyor: {MODEL_CANDIDATES[self.model_idx]}") self._build_agent() return True print("[FALLBACK] denenecek baska model kalmadi") return False def _clean(self, text: str) -> str: text = str(text).strip() for prefix in ["FINAL ANSWER:", "Final answer:", "Answer:", "The answer is"]: if text.startswith(prefix): text = text[len(prefix):].strip() return text.strip().strip('"').rstrip(".") def __call__(self, question: str) -> str: prompt = ( "You are answering a benchmark question. Your response is graded by EXACT string match.\n" "Output ONLY the answer itself: no explanation, no sentence, no units unless the question asks for them, " "no trailing period, no quotes.\n" "If the answer is a number, write just the number. If it is a name, write just the name.\n\n" f"Question: {question}" ) for attempt in range(3): try: answer = self.agent.run(prompt) cleaned = self._clean(answer) if cleaned: return cleaned except Exception as e: err = f"{type(e).__name__}: {e}" print(f"[AGENT ERROR] attempt {attempt+1} | {err}") traceback.print_exc() if any(k in err for k in OVERLOAD_KEYS): self._switch_model() time.sleep(5) return "unknown" def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ 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" # 1. Instantiate Agent try: agent = BasicAgent() except Exception as e: print(f"Error instantiating agent: {e}") traceback.print_exc() return f"Error initializing agent: {e}", None 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.JSONDecodeError as e: print(f"Error decoding JSON response from questions endpoint: {e}") return f"Error decoding server response for questions: {e}", None except requests.exceptions.RequestException as e: print(f"Error fetching questions: {e}") return f"Error fetching 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 = [] total = len(questions_data) print(f"Running agent on {total} questions...") for idx, item in enumerate(questions_data, start=1): 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 print(f"\n>>> [{idx}/{total}] task_id={task_id}") 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}) print(f"<<< [{idx}/{total}] answer = {submitted_answer!r}") except Exception as e: print(f"Error running agent on task {task_id}: {e}") answers_payload.append({"task_id": task_id, "submitted_answer": "unknown"}) results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}) # Free tier RPM limitini asmamak icin nefes payi time.sleep(4) 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} print(f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'...") # 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.") return final_status, pd.DataFrame(results_log) 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, pd.DataFrame(results_log) except requests.exceptions.Timeout: status_message = "Submission Failed: The request timed out." print(status_message) return status_message, pd.DataFrame(results_log) except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" print(status_message) return status_message, pd.DataFrame(results_log) except Exception as e: status_message = f"An unexpected error occurred during submission: {e}" print(status_message) return status_message, pd.DataFrame(results_log) # --- 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. """ ) 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}") else: print("ℹ️ 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("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)