Spaces:
Runtime error
Runtime error
| """ | |
| Problem Solving Agent - Specialized MCP agent for problem-solving research. | |
| """ | |
| import asyncio | |
| import json | |
| import logging | |
| from common import get_pydantic_ai_agent, process_research_questions, enhance_hypotheses | |
| # Configure logging | |
| logging.basicConfig( | |
| level=logging.INFO, | |
| format="%(asctime)s - %(name)s - %(levelname)s - %(message)s" | |
| ) | |
| logger = logging.getLogger("problem-solving-agent") | |
| # Define the system prompt for the problem solving agent | |
| PROBLEM_SOLVING_SYSTEM_PROMPT = """ | |
| You are an expert problem-solving research assistant with deep knowledge of analytical | |
| frameworks, decision-making methodologies, and innovative solution development across | |
| multiple domains. Your expertise includes: | |
| 1. Systems thinking and complex problem analysis | |
| 2. Root cause identification and causal mapping | |
| 3. Creative ideation and solution generation | |
| 4. Decision analysis and optimization | |
| 5. Implementation planning and risk assessment | |
| 6. Interdisciplinary approaches to wicked problems | |
| Your role is to help researchers refine their problem statements, enhance their solution | |
| hypotheses, and provide guidance on methodological approaches to problem-solving research. | |
| You excel at identifying underlying patterns in complex problems and suggesting novel | |
| approaches for investigation and resolution. | |
| When evaluating research questions and hypotheses, consider: | |
| - Problem framing and boundary definition | |
| - Stakeholder perspectives and needs | |
| - Feasibility, scalability, and sustainability of potential solutions | |
| - Metrics for success and impact measurement | |
| - Potential unintended consequences | |
| - Implementation challenges and strategies | |
| Provide detailed, practical analysis that demonstrates deep understanding of problem-solving | |
| methodologies while remaining actionable and solution-oriented. | |
| """ | |
| async def get_problem_solving_agent(): | |
| """Initialize and return the problem solving agent.""" | |
| client, agent = await get_pydantic_ai_agent(PROBLEM_SOLVING_SYSTEM_PROMPT) | |
| return client, agent | |
| async def process_problem_solving_questions(research_questions, domain_context=None): | |
| """ | |
| Process research questions using the problem solving agent. | |
| Args: | |
| research_questions (list): List of research questions to process. | |
| domain_context (str, optional): Additional domain context to provide. | |
| Returns: | |
| dict: Enhanced research questions with explanations and context. | |
| """ | |
| client, agent = await get_problem_solving_agent() | |
| try: | |
| result = await process_research_questions(agent, research_questions, domain_context) | |
| return result | |
| finally: | |
| await client.cleanup_servers() | |
| async def enhance_problem_solving_hypotheses(hypotheses, research_goal): | |
| """ | |
| Enhance hypotheses using the problem solving agent. | |
| Args: | |
| hypotheses (list): List of hypotheses to enhance. | |
| research_goal (str): The research goal. | |
| Returns: | |
| dict: Enhanced hypotheses with explanations and context. | |
| """ | |
| client, agent = await get_problem_solving_agent() | |
| try: | |
| result = await enhance_hypotheses(agent, hypotheses, research_goal) | |
| return result | |
| finally: | |
| await client.cleanup_servers() | |
| if __name__ == "__main__": | |
| # Example usage | |
| async def main(): | |
| research_questions = [ | |
| "How can urban transportation systems be redesigned to reduce congestion?", | |
| "What strategies can effectively address food waste in the supply chain?", | |
| "How can organizations better prepare for and respond to cybersecurity threats?" | |
| ] | |
| result = await process_problem_solving_questions(research_questions) | |
| print(json.dumps(result, indent=2)) | |
| asyncio.run(main()) | |