| import os |
| import io |
| import base64 |
| import subprocess |
| import tempfile |
| import requests |
| import gradio as gr |
| import pandas as pd |
|
|
| |
| 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 "\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" |
|
|
| |
| 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 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(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) |
|
|
| |
| 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.") |
| 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 |
|
|
|
|
| |
| 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) |
|
|
