Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from smolagents import CodeAgent, DuckDuckGoSearchTool | |
| import gradio as gr | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| # --- Enhanced Agent Definition --- | |
| class GAIAAgent: | |
| def __init__(self): | |
| print("GAIAAgent initialized.") | |
| self.model = gr.load("models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", provider="novita") | |
| self.search_tool = DuckDuckGoSearchTool() # optional if you still want to use search manually | |
| def format_prompt(self, question: str, file_content: str = None) -> str: | |
| prompt = ( | |
| "You are a helpful AI agent solving a question from the GAIA benchmark. " | |
| "Respond only with the final answer." | |
| ) | |
| if file_content: | |
| prompt += f"\nAttached File Content:\n{file_content}\n" | |
| prompt += f"\nQuestion: {question}\nAnswer:" | |
| return prompt | |
| def read_file(self, filename: str) -> str: | |
| filepath = os.path.join("./", filename) | |
| if filename.endswith(".txt") and os.path.exists(filepath): | |
| with open(filepath, "r") as file: | |
| return file.read()[:1000] # limit to 1000 chars | |
| return "" | |
| def __call__(self, question: str, file_name: str = None) -> str: | |
| file_content = self.read_file(file_name) if file_name else None | |
| prompt = self.format_prompt(question, file_content) | |
| result = self.model(prompt) # directly call the Gradio-loaded model | |
| return result.strip() | |
| # class GAIAAgent: | |
| # def __init__(self): | |
| # print("GAIAAgent initialized.") | |
| # self.model = gr.load("models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", provider="novita") | |
| # search_tool = DuckDuckGoSearchTool() | |
| # self.agent = CodeAgent(model=model, tools=[search_tool]) | |
| # def format_prompt(self, question: str, file_content: str = None) -> str: | |
| # prompt = ( | |
| # "You are a helpful AI agent solving a question from the GAIA benchmark. " | |
| # "Respond only with the final answer." | |
| # ) | |
| # if file_content: | |
| # prompt += f"\nAttached File Content:\n{file_content}\n" | |
| # prompt += f"\nQuestion: {question}\nAnswer:" | |
| # return prompt | |
| # def read_file(self, filename: str) -> str: | |
| # filepath = os.path.join("./", filename) | |
| # if filename.endswith(".txt") and os.path.exists(filepath): | |
| # with open(filepath, "r") as file: | |
| # return file.read()[:1000] # limit to 1000 chars | |
| # return "" | |
| # def __call__(self, question: str, file_name: str = None) -> str: | |
| # file_content = self.read_file(file_name) if file_name else None | |
| # prompt = self.format_prompt(question, file_content) | |
| # result = self.agent.run(prompt) | |
| # return result.strip() | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| 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 | |
| api_url = DEFAULT_API_URL | |
| questions_url = f"{api_url}/questions" | |
| submit_url = f"{api_url}/submit" | |
| try: | |
| agent = GAIAAgent() | |
| except Exception as e: | |
| return f"Error initializing agent: {e}", None | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| try: | |
| response = requests.get(questions_url, timeout=15) | |
| response.raise_for_status() | |
| questions_data = response.json() | |
| except Exception as e: | |
| return f"Error fetching questions: {e}", None | |
| results_log = [] | |
| answers_payload = [] | |
| for item in questions_data: | |
| task_id = item.get("task_id") | |
| question_text = item.get("question") | |
| file_name = item.get("file_name") | |
| if not task_id or question_text is None: | |
| continue | |
| try: | |
| submitted_answer = agent(question_text, file_name) | |
| 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: | |
| results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"}) | |
| 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} | |
| 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.')}" | |
| ) | |
| return final_status, pd.DataFrame(results_log) | |
| except Exception as e: | |
| return f"Submission Failed: {e}", pd.DataFrame(results_log) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# GAIA Agent Evaluation Runner") | |
| gr.Markdown(""" | |
| **Instructions:** | |
| 1. Log in to your Hugging Face account. | |
| 2. Click the button to run the agent and submit answers. | |
| 3. Your score will be printed below. | |
| """) | |
| 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("Launching GAIA agent app...") | |
| demo.launch(debug=True, share=False) | |