import os import io import base64 import subprocess import tempfile import requests import gradio as gr import pandas as pd # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" OPENROUTER_API_URL = "https://openrouter.ai/api/v1/chat/completions" MAIN_MODEL = "anthropic/claude-sonnet-4-5" AUDIO_MODEL = "google/gemini-2.5-flash" SYSTEM_PROMPT = """You are a precise research assistant answering questions for a benchmark evaluation. CRITICAL RULES: - Return ONLY the final answer, nothing else - No explanations, no "the answer is", no "FINAL ANSWER:", no preamble - For numbers: give exact digits only (e.g. "42" not "42 items") - For names: exact spelling, exact capitalization - For lists: comma-separated on one line unless asked otherwise - For yes/no: just "yes" or "no" - Answer exactly what is asked, nothing more""" def _or_post(model, messages, tools=None, timeout=120): payload = { "model": model, "messages": messages, } if tools: payload["tools"] = tools resp = requests.post( OPENROUTER_API_URL, headers={ "Authorization": f"Bearer {os.environ.get('OPENROUTER_API_KEY', '')}", "Content-Type": "application/json", }, json=payload, timeout=timeout, ) resp.raise_for_status() return resp.json() class BasicAgent: def __init__(self): self.api_url = DEFAULT_API_URL print("BasicAgent initialized.") def _download_file(self, task_id): try: url = f"{self.api_url}/files/{task_id}" resp = requests.get(url, timeout=30) if resp.status_code == 200: content_type = resp.headers.get("Content-Type", "") disposition = resp.headers.get("Content-Disposition", "") filename = "" if "filename=" in disposition: filename = disposition.split("filename=")[-1].strip('" ') return resp.content, content_type, filename except Exception as e: print(f"File download error for {task_id}: {e}") return None, None, None def _transcribe_audio(self, audio_bytes): try: b64 = base64.standard_b64encode(audio_bytes).decode() data = _or_post( model=AUDIO_MODEL, messages=[{ "role": "user", "content": [ {"type": "text", "text": "Transcribe this audio exactly as spoken, word for word. Return only the transcript, nothing else."}, {"type": "input_audio", "input_audio": {"data": b64, "format": "mp3"}} ] }], timeout=60, ) return data["choices"][0]["message"]["content"] or "" except Exception as e: print(f"Audio transcription failed: {e}") return "[Audio transcription unavailable]" def _execute_python(self, code_bytes): with tempfile.NamedTemporaryFile(suffix=".py", delete=False, mode="wb") as f: f.write(code_bytes) tmp_path = f.name try: result = subprocess.run( ["python3", tmp_path], capture_output=True, text=True, timeout=30 ) os.unlink(tmp_path) return (result.stdout + result.stderr).strip()[:5000] except subprocess.TimeoutExpired: try: os.unlink(tmp_path) except Exception: pass return "[Execution timed out]" except Exception as e: return f"[Execution failed: {e}]" def _parse_xlsx(self, xlsx_bytes): try: df = pd.read_excel(io.BytesIO(xlsx_bytes)) return df.to_string(index=True)[:10000] except Exception as e: return f"[XLSX parsing failed: {e}]" def __call__(self, question: str, task_id: str = None) -> str: print(f"Agent received question: {question[:80]}...") user_content = [] extra_context = "" if task_id: file_bytes, content_type, filename = self._download_file(task_id) if file_bytes: ct = (content_type or "").lower() fn = (filename or "").lower() if "image" in ct or fn.endswith((".png", ".jpg", ".jpeg", ".gif", ".webp")): b64 = base64.standard_b64encode(file_bytes).decode() mime = "image/png" if ("png" in ct or fn.endswith(".png")) else "image/jpeg" user_content.append({ "type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"} }) elif "audio" in ct or "mpeg" in ct or fn.endswith((".mp3", ".wav", ".m4a")): transcript = self._transcribe_audio(file_bytes) extra_context = f"\n[Audio transcript:\n{transcript}]" elif fn.endswith(".py") or "python" in ct or "text/x-python" in ct: output = self._execute_python(file_bytes) extra_context = f"\n[Python script output:\n{output}]" elif ("spreadsheet" in ct or "excel" in ct or "openxmlformats" in ct or fn.endswith((".xlsx", ".xls"))): table = self._parse_xlsx(file_bytes) extra_context = f"\n[Spreadsheet data:\n{table}]" else: try: text = file_bytes.decode("utf-8") extra_context = f"\n[File content:\n{text[:3000]}]" except Exception: extra_context = f"\n[Binary file, {len(file_bytes)} bytes]" user_content.append({"type": "text", "text": question + extra_context}) try: data = _or_post( model=MAIN_MODEL, messages=[ {"role": "system", "content": SYSTEM_PROMPT}, {"role": "user", "content": user_content}, ], tools=[{ "type": "openrouter:web_search", "parameters": {"max_results": 8, "max_total_results": 24} }], ) raw = (data["choices"][0]["message"]["content"] or "").strip() # If response is multi-line reasoning, extract just the final answer if "\n" in raw: extract = _or_post( model=MAIN_MODEL, messages=[ {"role": "user", "content": ( f"Extract only the final answer from this text. " f"Return just the answer value, no explanation:\n\n{raw}" )} ], ) answer = (extract["choices"][0]["message"]["content"] or "").strip() else: answer = raw print(f"Agent answer: {answer[:120]}") return answer except Exception as e: print(f"Agent error: {e}") return f"Error: {e}" 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 if username != "polvallverdu": return "This space is restricted to its owner.", 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}") 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.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 # 3. Run your Agent 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(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}"}) 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} status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..." print(status_update) # 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.") results_df = pd.DataFrame(results_log) 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) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.Timeout: status_message = "Submission Failed: The request timed out." print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except requests.exceptions.RequestException as e: status_message = f"Submission Failed: Network error - {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df except Exception as e: status_message = f"An unexpected error occurred during submission: {e}" print(status_message) results_df = pd.DataFrame(results_log) return status_message, results_df # --- 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. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async. """ ) 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("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)