import os import requests import pandas as pd import gradio as gr import tempfile import json from pathlib import Path from typing import Union, Optional from smolagents import LiteLLMModel, DuckDuckGoSearchTool, CodeAgent, WikipediaSearchTool from smolagents.tools import Tool # --- Function to Configure Google Credentials (ESSENTIAL) --- def setup_google_credentials(): """ Reads Google Cloud credential JSON content from an environment variable, writes it to a temporary file, and sets the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of that file. This function should be called before any Google Cloud client library (like the one used by LiteLLM for Vertex AI) is initialized. Requires the service account key JSON content to be stored in an environment variable named 'GOOGLE_APPLICATION_CREDENTIALS_JSON'. Set this in your Hugging Face Space secrets. """ credentials_json_str = os.environ.get("GOOGLE_APPLICATION_CREDENTIALS_JSON") if not credentials_json_str: print("ERROR: 'GOOGLE_APPLICATION_CREDENTIALS_JSON' secret not found in environment variables.") print(" Please ensure you have set this secret in your Hugging Face Space settings.") # Depending on requirements, you might want to raise an error here # raise ValueError("Secret 'GOOGLE_APPLICATION_CREDENTIALS_JSON' not set.") return False # Indicate failure try: # Create a secure temporary file to store the credentials # delete=False ensures the file persists until the process exits or it's manually cleaned up. # We need the file path to set the environment variable. with tempfile.NamedTemporaryFile(mode='w', suffix=".json", delete=False, encoding='utf-8') as temp_f: temp_f.write(credentials_json_str) credentials_path = temp_f.name # Get the path to the temporary file # Set the environment variable that Google client libraries expect os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = credentials_path print(f"Google Application Credentials successfully set to temporary file: {credentials_path}") return True # Indicate success except json.JSONDecodeError: print("ERROR: Failed to parse the content of 'GOOGLE_APPLICATION_CREDENTIALS_JSON'. Ensure it's valid JSON.") return False except OSError as e: print(f"ERROR: Failed to write credentials to temporary file: {e}") return False except Exception as e: print(f"ERROR: An unexpected error occurred during Google credential setup: {e}") # You might want to re-raise the exception depending on your error handling strategy # raise e return False # --- Call Credential Setup EARLY --- # This needs to run before any code (like BasicAgent initialization) tries to use Google Cloud services. print("Attempting to configure Google Cloud credentials...") CREDENTIALS_CONFIGURED = setup_google_credentials() if not CREDENTIALS_CONFIGURED: print("WARNING: Google Cloud credentials setup failed. Agent initialization might fail.") # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" ### Defining tools ### class ExcelToTextTool(Tool): """Render an Excel worksheet as Markdown text.""" name = "excel_to_text" description = ( "Read an Excel file and return a Markdown table of the requested sheet. " "Accepts either the sheet name or the zero-based index." ) inputs = { "excel_path": { "type": "string", "description": "Path to the Excel file (.xlsx / .xls).", }, "sheet_name": { "type": "string", "description": ( "Worksheet name or zero‑based index *as a string* (optional; default first sheet)." ), "nullable": True, }, } output_type = "string" def forward( self, excel_path: str, sheet_name: Optional[str] = None, ) -> str: """Load *excel_path* and return the sheet as a Markdown table.""" path = Path(excel_path).expanduser().resolve() if not path.exists(): return f"Error: Excel file not found at {path}" try: # Interpret sheet identifier sheet: Union[str, int] if sheet_name is None or sheet_name == "": sheet = 0 # first sheet else: # If the user passed a numeric string (e.g. "1"), cast to int sheet = int(sheet_name) if sheet_name.isdigit() else sheet_name # Load worksheet df = pd.read_excel(path, sheet_name=sheet) # Render to Markdown, fallback to tabulate if needed if hasattr(pd.DataFrame, "to_markdown"): return df.to_markdown(index=False) from tabulate import tabulate return tabulate(df, headers="keys", tablefmt="github", showindex=False) except Exception as exc: # broad catch keeps the agent chat‑friendly return f"Error reading Excel file: {exc}" # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ class BasicAgent: def __init__(self): # Assuming you've set GOOGLE_API_KEY in secrets google_api_key = os.environ.get("GOOGLE_API_KEY") if not google_api_key: raise ValueError("GOOGLE_API_KEY environment variable not set.") # Check if the global credential setup was successful if not CREDENTIALS_CONFIGURED: raise ValueError("Google Cloud credentials could not be configured. Check startup logs and HF Secrets (ensure 'GOOGLE_APPLICATION_CREDENTIALS_JSON' is set correctly).") self.agent = CodeAgent( model=LiteLLMModel(model_id="gemini-2.0-flash"), tools=[DuckDuckGoSearchTool(), WikipediaSearchTool(), ExcelToTextTool()], add_base_tools=True, additional_authorized_imports=['pandas','numpy','csv','subprocess'] ) print("BasicAgent initialized.") def __call__(self, question: str) -> str: print(f"Agent received question (first 50 chars): {question[:50]}...") fixed_answer = self.agent.run(question) print(f"Agent returning answer: {fixed_answer}") return fixed_answer def run_and_submit_all( profile: gr.OAuthProfile | None): """ Fetches all questions, runs the BasicAgent on them, submits all answers, and displays the results. """ # --- Determine HF Space Runtime URL and Repo URL --- space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code 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 ( modify this part to create your agent) try: agent = BasicAgent() except Exception as e: print(f"Error instantiating agent: {e}") return f"Error initializing agent: {e}", None # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public) 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) 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) # Removed max_rows=10 from DataFrame constructor 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) # Check for SPACE_HOST and SPACE_ID at startup for information space_host_startup = os.getenv("SPACE_HOST") space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup 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 repo URLs if SPACE_ID is found 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)