import os import gradio as gr import requests import inspect import pandas as pd import time from smolagents import CodeAgent, WikipediaSearchTool, DuckDuckGoSearchTool, OpenAIServerModel from PIL import Image from io import BytesIO # (Keep Constants as is) # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY") # --- Basic Agent Definition --- # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ # class BasicAgent: # def __init__(self): # print("BasicAgent initialized.") # def __call__(self, question: str) -> str: # print(f"Agent received question (first 50 chars): {question[:50]}...") # fixed_answer = "This is a default answer." # print(f"Agent returning fixed answer: {fixed_answer}") # return fixed_answer def is_valid_image_pillow(file_name): try: with Image.open(file_name) as img: img.verify() # Verify the image file return True except (IOError, SyntaxError): return False class myAgent: def __init__(self): print("myAgent initialized.") self.agent = CodeAgent( model = OpenAIServerModel( model_id="gemini-2.0-flash-lite", api_base="https://generativelanguage.googleapis.com/v1beta/openai/", api_key=GEMINI_API_KEY, ), tools=[DuckDuckGoSearchTool(), WikipediaSearchTool()], add_base_tools=True, # additional_authorized_imports=['pandas','numpy','csv'] ) def __call__(self, question: str, file_data=None) -> str: # Renamed img to file_data print(f"Agent received question (first 50 chars): {question[:50]}...") images_for_agent = [] # List to hold image objects text_from_file = "" # String to hold text content from files if file_data: print(f"Agent received file data of size: {len(file_data)} bytes") # Attempt to open as an image try: img_obj = Image.open(BytesIO(file_data)) img_obj.verify() # Verify if it's a valid image images_for_agent.append(img_obj) print("File identified as an image.") except (IOError, SyntaxError): print("File is not an image, attempting to decode as text.") # If not an image, try to decode as text try: text_from_file = file_data.decode('utf-8') # You might want to add more sophisticated parsing here for CSV/JSON/etc. # For example, if it's a CSV: # df = pd.read_csv(StringIO(text_from_file)) # text_from_file = df.to_string() # Convert DataFrame to string for agent print(f"File decoded as text (first 200 chars): {text_from_file[:200]}...") except UnicodeDecodeError: text_from_file = f"Could not decode file as UTF-8 text. Raw bytes size: {len(file_data)}" print("File could not be decoded as UTF-8 text.") except Exception as e: print(f"Unexpected error processing file data: {e}") text_from_file = f"Error processing file: {e}" # Combine question with file content if available if text_from_file: # You might want to prepend or append, or format this more intelligently question_with_file_context = f"{question}\n\n[FILE CONTENT START]\n{text_from_file}\n[FILE CONTENT END]" else: question_with_file_context = question # Pass images and the possibly augmented question to the CodeAgent answer = self.agent.run(question_with_file_context, images=images_for_agent if images_for_agent else None) time.sleep(5) print(f"Agent returning answer: {answer}") return 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" files_url = f"{api_url}/files" submit_url = f"{api_url}/submit" # 1. Instantiate Agent ( modify this part to create your agent) try: agent = myAgent() 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") file_name = item.get("file_name") file_content_to_pass = None # Initialize to None if file_name: # Fetch files print(f"Fetching file '{file_name}' for task_id: {task_id}") try: response = requests.get(f'{files_url}/{task_id}', timeout=15, allow_redirects=True) print("Response status code:", response.status_code) if response.status_code == 404: print(f"File not found for task_id {task_id}. Skipping file processing for this task.") # Continue without a file, agent will still receive the question else: response.raise_for_status() file_content_to_pass = response.content # Store the raw content print(f"Fetched file for task_id {task_id}: {file_name} (size: {len(file_content_to_pass)} bytes)") # Optional: Add specific handling for image files if your agent needs them # The `img` parameter in `myAgent.__call__` suggests it's designed for images. # If you want to pass image objects for image files, and raw content for others, # you'll need to adapt how `myAgent` uses the `img` parameter. # For now, we'll just pass the raw content. except requests.exceptions.RequestException as e: print(f"Error fetching file for task {task_id}: {e}. Agent will run without file.") # Do not return here, allow agent to run with just the question if file fetch fails except Exception as e: print(f"An unexpected error occurred fetching file for task {task_id}: {e}. Agent will run without file.") # Do not return here, allow agent to run with just the question if file fetch fails if not task_id or question_text is None: print(f"Skipping item with missing task_id or question: {item}") continue try: # Pass file_content_to_pass to the agent. # Your agent's __call__ method needs to be ready to handle # raw byte content for the 'img' parameter, or you might # rename it to something more generic like 'file_data'. submitted_answer = agent(question_text, file_content_to_pass) 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, "File Name": file_name if file_name else "N/A"}) 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}", "File Name": file_name if file_name else "N/A"}) # 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)