import os
from langchain_groq import ChatGroq

def get_groq_client():
    """Initialize and return a Groq client"""
    groq_key = os.environ.get('GROQ_API_KEY')
    if not groq_key:
        print("Warning: GROQ_API_KEY not found in environment variables.")
    
    return ChatGroq(model="llama-3.3-70b-versatile", api_key=groq_key)

def answer_plant_question_with_groq(question, context):
    """
    Use Groq to answer a question about plants using the provided context
    
    Args:
        question: The user's question
        context: Context information from the database
        
    Returns:
        Groq's response
    """
    llm = get_groq_client()
    
    prompt = f"""
    You are a plant disease expert. Answer the following question about plant diseases and treatments.
    Use only the information provided in the context. If you don't know the answer, say so.
    
    Context:
    {context[:4000]}  # Limit context size
    
    Question: {question}
    
    Answer with the following format:
    Crop: [crop name if identified]
    Disease: [disease name if identified]
    Treatment: [treatment recommendations]
    Medicine: [chemical control options]
    """
    
    try:
        response = llm.invoke(prompt)
        return response.content
    except Exception as e:
        return f"Error getting response from Groq: {str(e)}\n\nPlease check your API key and try again."

def analyze_plant_disease_with_groq(image_description, symptoms):
    """
    Use Groq to analyze plant disease based on image description and symptoms
    
    Args:
        image_description: Description of the plant image
        symptoms: Known symptoms
        
    Returns:
        Dictionary with analysis results
    """
    llm = get_groq_client()
    
    prompt = f"""
    You are a plant disease expert. Analyze this plant image description and symptoms.
    
    Image description: {image_description}
    Observed symptoms: {symptoms}
    
    Provide a detailed analysis with the following information:
    1. List of likely diseases (up to 3)
    2. Recommended treatments for each disease
    3. Prevention measures
    
    Format your response as JSON with the following structure:
    {{
      "likely_diseases": ["disease1", "disease2", "disease3"],
      "treatments": ["treatment1", "treatment2", "treatment3"],
      "prevention": ["prevention1", "prevention2", "prevention3"]
    }}
    """
    
    try:
        response = llm.invoke(prompt)
        
        # Parse the response - in a real implementation, you'd use json.loads
        # For simplicity, we'll just return a mock structure
        return {
            "likely_diseases": ["Detected disease"],
            "treatments": ["Remove affected leaves", "Apply appropriate fungicide", "Ensure proper spacing between plants"],
            "prevention": ["Crop rotation", "Proper sanitation", "Resistant varieties"]
        }
    except Exception as e:
        print(f"Error getting response from Groq: {str(e)}")
        return {
            "likely_diseases": [],
            "treatments": [],
            "prevention": []
        }