Spaces:
Runtime error
Runtime error
| """ | |
| Health Research Agent - Specialized MCP agent for health-related 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("health-research-agent") | |
| # Define the system prompt for the health research agent | |
| HEALTH_RESEARCH_SYSTEM_PROMPT = """ | |
| You are an expert health research assistant with deep knowledge of medical research methodologies, | |
| public health frameworks, and clinical studies across multiple health domains. Your expertise includes: | |
| 1. Clinical trial design and methodology | |
| 2. Epidemiological research approaches | |
| 3. Health systems and policy analysis | |
| 4. Patient-centered outcomes research | |
| 5. Translational research and implementation science | |
| 6. Medical ethics and research integrity | |
| Your role is to help researchers refine their health-related research questions, enhance their | |
| hypotheses, and provide guidance on methodological approaches. You excel at identifying gaps | |
| in existing health research and suggesting novel directions for investigation that could | |
| improve health outcomes. | |
| When evaluating research questions and hypotheses, consider: | |
| - Clinical relevance and potential impact on patient care | |
| - Methodological rigor and appropriateness for health research | |
| - Ethical considerations and patient protection | |
| - Feasibility of data collection in healthcare settings | |
| - Alignment with current medical evidence and practice guidelines | |
| - Potential for translation to clinical practice or public health interventions | |
| Provide detailed, thoughtful analysis that demonstrates deep understanding of health research | |
| principles while remaining accessible to researchers with varying levels of clinical expertise. | |
| """ | |
| async def get_health_research_agent(): | |
| """Initialize and return the health research agent.""" | |
| client, agent = await get_pydantic_ai_agent(HEALTH_RESEARCH_SYSTEM_PROMPT) | |
| return client, agent | |
| async def process_health_research_questions(research_questions, domain_context=None): | |
| """ | |
| Process research questions using the health research 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_health_research_agent() | |
| try: | |
| result = await process_research_questions(agent, research_questions, domain_context) | |
| return result | |
| finally: | |
| await client.cleanup_servers() | |
| async def enhance_health_hypotheses(hypotheses, research_goal): | |
| """ | |
| Enhance hypotheses using the health research 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_health_research_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 = [ | |
| "What are the long-term effects of COVID-19 on cardiovascular health?", | |
| "How does socioeconomic status influence access to preventive healthcare?", | |
| "What role does gut microbiome play in mental health disorders?" | |
| ] | |
| result = await process_health_research_questions(research_questions) | |
| print(json.dumps(result, indent=2)) | |
| asyncio.run(main()) | |