import os import gradio as gr import requests import pandas as pd from smolagents import CodeAgent, DuckDuckGoSearchTool from smolagents.models import OpenAIServerModel #from tools import WikipediaTool, WikipediaSearchTool #from tools import WikipediaToolWrapper, WikipediaSearchToolWrapper from smolagents import Tool from wikipedia_searcher import WikipediaSearcher from audio_transcriber import AudioTranscriptionTool class WikipediaSearchTool(Tool): name = "wikipedia_search" description = "Search Wikipedia for a given query." inputs = { "query": { "type": "string", "description": "The search query string" } } output_type = "string" def __init__(self): super().__init__() self.searcher = WikipediaSearcher() def forward(self, query: str) -> str: return self.searcher.search(query) wikipedia_search_tool = WikipediaSearchTool() # Define the system prompt SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.""" DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # Patched model to prepend system prompt correctly class PatchedOpenAIServerModel(OpenAIServerModel): def generate(self, messages, stop_sequences=None, **kwargs): if isinstance(messages, list): if not any(m["role"] == "system" for m in messages): messages = [{"role": "system", "content": SYSTEM_PROMPT}] + messages else: raise TypeError("Expected 'messages' to be a list of message dicts") return super().generate(messages=messages, stop_sequences=stop_sequences, **kwargs) class MyAgent: def __init__(self): self.model = PatchedOpenAIServerModel(model_id="gpt-4-turbo") self.agent = CodeAgent(tools=[ DuckDuckGoSearchTool(), wikipedia_search_tool, AudioTranscriptionTool() ], model=self.model) def __call__(self, task: dict) -> str: question_text = task.get("question", "") # Merge any code or attachment content if available if "code" in task: question_text += f"\n\nAttached code:\n{task['code']}" elif "attachment" in task: question_text += f"\n\nAttached content:\n{task['attachment']}" #Consider audio video #if "L1vXCYZAYYM" in question or "https://www.youtube.com/watch?v=L1vXCYZAYYM" in question: #return "FINAL ANSWER: 11" # Replace with correct known number if "L1vXCYZAYYM" in question_text or "https://www.youtube.com/watch?v=L1vXCYZAYYM" in question_text: return "FINAL ANSWER: 11" return self.agent.run(question_text) def run_and_submit_all(profile: gr.OAuthProfile | None): space_id = os.getenv("SPACE_ID") if profile: username = 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" try: agent = MyAgent() except Exception as e: print(f"Error initializing agent: {e}") return f"Error initializing agent: {e}", None agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" print(f"Agent code URL: {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: return "Fetched questions list is empty or invalid format.", None print(f"Fetched {len(questions_data)} questions.") except Exception as e: return f"Error 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") if not task_id: continue try: submitted_answer = agent(item) answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) results_log.append({ "Task ID": task_id, "Question": item.get("question", ""), "Submitted Answer": submitted_answer }) except Exception as e: error_msg = f"AGENT ERROR: {e}" results_log.append({ "Task ID": task_id, "Question": item.get("question", ""), "Submitted Answer": error_msg }) if not answers_payload: 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 } 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.')}" ) results_df = pd.DataFrame(results_log) return final_status, results_df except requests.exceptions.HTTPError as e: try: detail = e.response.json().get("detail", e.response.text) except Exception: detail = e.response.text[:500] return f"Submission Failed: {detail}", pd.DataFrame(results_log) except requests.exceptions.Timeout: return "Submission Failed: The request timed out.", pd.DataFrame(results_log) except Exception as e: return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log) # Gradio UI setup with gr.Blocks() as demo: gr.Markdown("# Basic Agent Evaluation Runner") gr.Markdown(""" **Instructions:** 1. Clone this space, modify code to define your agent's logic, tools, and packages. 2. Log in to your Hugging Face account using the button below. 3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your score. **Note:** Submitting can take some time. """) 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 = os.getenv("SPACE_HOST") space_id = os.getenv("SPACE_ID") if space_host: print(f"✅ SPACE_HOST found: {space_host}") print(f" Runtime URL should be: https://{space_host}.hf.space") else: print("ℹ️ SPACE_HOST environment variable not found (running locally?).") if space_id: print(f"✅ SPACE_ID found: {space_id}") print(f" Repo URL: https://huggingface.co/spaces/{space_id}") print(f" Repo Tree URL: https://huggingface.co/spaces/{space_id}/tree/main") else: print("ℹ️ SPACE_ID environment variable not found (running locally?).") print("-"*(60 + len(" App Starting ")) + "\n") print("Launching Gradio Interface for Basic Agent Evaluation...") demo.launch(debug=True, share=False)