> ## Documentation Index > Fetch the complete documentation index at: https://docs.getbindu.com/llms.txt > Use this file to discover all available pages before exploring further. # 2.10 Medical Research Agent > A Bindu agent that provides medical information and health guidance using web search A Bindu agent that provides medical information and health guidance using web search. ## Code Create `medical_agent.py` with the code below, or save it directly from your editor. ```python theme={null} """Medical Research Agent with Web Search A Bindu agent that provides medical information and health guidance using DuckDuckGo web search. Provides general health information, symptom analysis, and wellness recommendations. Features: - Web search via DuckDuckGo for real-time medical information - Medical research and symptom analysis capabilities - OpenRouter integration with google/gemini-2.0-flash-001 - Clean, synthesized responses with medical disclaimers - Health and wellness guidance Usage: python medical_agent.py Environment: Requires OPENROUTER_API_KEY in .env file """ import os from dotenv import load_dotenv # Load environment variables from .env file load_dotenv() from bindu.penguin.bindufy import bindufy from agno.agent import Agent from agno.tools.duckduckgo import DuckDuckGoTools from agno.models.openrouter import OpenRouter # Initialize the medical research agent agent = Agent( instructions="""You are a medical research assistant. When asked about health or medical topics, provide clear, accurate information with appropriate disclaimers. Key guidelines: - Always include a medical disclaimer stating this is not professional medical advice - Provide general health information and educational content - For specific medical concerns, recommend consulting healthcare professionals - Use web search to find current, reliable medical information - Present information in an organized, easy-to-read format - Avoid making definitive diagnoses or treatment recommendations - Focus on evidence-based information from reputable sources Response format: - Start with relevant medical information - Include supporting details and context - End with a clear medical disclaimer - Avoid showing multiple search results - synthesize information coherently""", model=OpenRouter( id="google/gemini-2.0-flash-001", api_key=os.getenv("OPENROUTER_API_KEY") ), tools=[DuckDuckGoTools()], markdown=True ) # Agent configuration for Bindu config = { "author": "bindu.builder@getbindu.com", "name": "medical_agent", "description": "Medical research agent that provides health information, symptom analysis, and wellness guidance", "deployment": { "url": "http://localhost:3773", "expose": True, "cors_origins": ["http://localhost:5173"] }, "skills": ["skills/medical-research-skill"], } # Message handler function def handler(messages: list[dict[str, str]]): """ Process incoming messages and return agent response. Args: messages: List of message dictionaries containing conversation history Returns: Agent response with medical information and appropriate disclaimers """ # Extract the latest user message if messages: latest_message = messages[-1].get('content', '') if isinstance(messages[-1], dict) else str(messages[-1]) # Run the agent with the latest message result = agent.run(input=latest_message) # Format the response to be cleaner if hasattr(result, 'content'): return result.content elif hasattr(result, 'response'): return result.response else: return str(result) return "Please provide a health or medical question. Remember, I provide general information for educational purposes only." # Bindu-fy the agent - converts it to a discoverable, interoperable Bindu agent bindufy(config, handler) ``` ## Skill Configuration Create `skills/medical-research-skill/skill.yaml`: ```yaml theme={null} id: medical-research-skill name: medical-research-skill version: 1.0.0 author: bindu.builder@getbindu.com description: | Advanced medical research skill that provides comprehensive health information, symptom analysis, and wellness guidance for educational purposes. Features: - Real-time medical information via web search - Symptom analysis and preliminary assessment - Drug information and interaction details - Health and wellness recommendations - Medical research and study summaries - Preventive care guidance - Lifestyle and nutrition advice Uses DuckDuckGo search to find current medical information and provides detailed analysis with appropriate medical disclaimers. tags: - medical - health - symptoms - wellness - research - healthcare - medicine input_modes: - application/json output_modes: - application/json examples: - "What are the symptoms of flu?" - "Provide information about ibuprofen side effects" - "How to prevent common cold?" - "What are the benefits of regular exercise?" - "Explain the symptoms of diabetes" - "Give tips for better sleep hygiene" capabilities_detail: medical_research: supported: true description: "Comprehensive medical research and health information retrieval" symptom_analysis: supported: true description: "Preliminary symptom analysis and assessment guidance" drug_information: supported: true description: "Medication details, side effects, and interaction information" wellness_guidance: supported: true description: "Health and wellness recommendations and lifestyle advice" search_integration: supported: true description: "Real-time medical information search via DuckDuckGo" preventive_care: supported: true description: "Preventive health measures and screening recommendations" ``` ## How It Works **Medical Research** * Uses Google Gemini 2.0 Flash for fast, accurate medical information * DuckDuckGo web search for current medical research and health guidelines * Synthesizes information from multiple sources **Safety Features** * Always includes medical disclaimers * Never provides definitive diagnoses * Recommends professional consultation for specific concerns * Focuses on evidence-based information **Response Format** * Clear, organized medical information * Supporting details and context * Consistent medical disclaimer * Educational content only ## Dependencies ```bash theme={null} uv init uv add bindu agno python-dotenv ``` ## Environment Setup Create `.env` file: ```bash theme={null} OPENROUTER_API_KEY=your_openrouter_api_key_here ``` ## Run ```bash theme={null} uv run medical_agent.py ``` **Examples:** * "What are the symptoms of flu?" * "Provide information about ibuprofen side effects" * "How to prevent common cold?" * "What are the benefits of regular exercise?" ## Example API Calls ```json theme={null} { "jsonrpc": "2.0", "method": "message/send", "params": { "message": { "role": "user", "kind": "message", "messageId": "9f11c870-5616-49ad-b187-d93cbb100001", "contextId": "9f11c870-5616-49ad-b187-d93cbb100002", "taskId": "9f11c870-5616-49ad-b187-d93cbb100003", "parts": [ { "kind": "text", "text": "What are the symptoms of flu?" } ] }, "skillId": "medical-research-skill", "configuration": { "acceptedOutputModes": ["application/json"] } }, "id": "9f11c870-5616-49ad-b187-d93cbb100003" } ``` ```json theme={null} { "jsonrpc": "2.0", "method": "tasks/get", "params": { "taskId": "9f11c870-5616-49ad-b187-d93cbb100003" }, "id": "9f11c870-5616-49ad-b187-d93cbb100004" } ``` ## Frontend Setup ```bash theme={null} # Clone the Bindu repository git clone https://github.com/GetBindu/Bindu # Navigate to frontend directory cd frontend # Install dependencies npm install # Start frontend development server npm run dev ``` Open [http://localhost:5173](http://localhost:5173) and try to chat with the medical research agent