| import os | |
| from openai import OpenAI | |
| class GaiaAgent: | |
| def __init__(self): | |
| self.client = OpenAI(api_key=os.getenv("OPENAI_API_KEY")) | |
| self.instructions = ( | |
| "You are a research assistant solving GAIA benchmark questions using 2022 English Wikipedia knowledge.\n" | |
| "For each question, reason step-by-step and only return the final answer in exact format." | |
| ) | |
| self.task_templates = { | |
| "8e867cd7-cff9-4e6c-867a-ff5ddc2550be": self.q_mercedes_sosa_albums | |
| } | |
| def __call__(self, question: str, task_id: str = None) -> str: | |
| if task_id in self.task_templates: | |
| return self.task_templates[task_id](question) | |
| else: | |
| return "[SKIPPED: Task not yet implemented in Agent V9]" | |
| def q_mercedes_sosa_albums(self, question: str) -> str: | |
| prompt = ( | |
| "You are a research assistant using 2022 English Wikipedia knowledge.\n" | |
| "\nQUESTION:\n" | |
| "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)?\n" | |
| "\nFollow this step-by-step reasoning chain:\n" | |
| "Step 1: Identify all studio albums by Mercedes Sosa.\n" | |
| "Step 2: Filter the albums published between 2000 and 2009 inclusive.\n" | |
| "Step 3: Count them.\n" | |
| "Step 4: Return only the count as a number (no text, no explanation).\n" | |
| "\nANSWER:" | |
| ) | |
| try: | |
| response = self.client.chat.completions.create( | |
| model="gpt-4-turbo", | |
| messages=[ | |
| {"role": "system", "content": self.instructions}, | |
| {"role": "user", "content": prompt} | |
| ], | |
| temperature=0.0 | |
| ) | |
| return response.choices[0].message.content.strip() | |
| except Exception as e: | |
| return f"[AGENT ERROR: {e}]" | |