# RAG Support Assistant Core Logic
from azure.search.documents import SearchClient
from azure.core.credentials import AzureKeyCredential
from openai import AzureOpenAI

class SupportRAGAssistant:
    def __init__(self, search_endpoint, search_key, openai_endpoint, openai_key):
        self.search_client = SearchClient(
            endpoint=search_endpoint,
            index_name="support-knowledge",
            credential=AzureKeyCredential(search_key)
        )
        self.openai_client = AzureOpenAI(
            azure_endpoint=openai_endpoint,
            api_key=openai_key,
            api_version="2024-02-15-preview"
        )
    
    def get_support_response(self, query: str, customer_context: dict):
        # Retrieve relevant knowledge
        search_results = self.search_client.search(
            query, 
            top=5,
            select=["content", "source", "category"]
        )
        
        context = []
        for result in search_results:
            context.append({
                "content": result["content"],
                "source": result["source"],
                "category": result["category"]
            })
        
        # Generate contextual response
        system_prompt = """You are a helpful support assistant. Use the provided 
        context to answer customer questions accurately and professionally. 
        Always cite your sources and suggest next steps when appropriate."""
        
        user_prompt = f"""
        Customer Question: {query}
        Customer Context: {customer_context}
        
        Relevant Knowledge:
        {self._format_context(context)}
        
        Please provide a helpful response:
        """
        
        response = self.openai_client.chat.completions.create(
            model="gpt-5",
            messages=[
                {"role": "system", "content": system_prompt},
                {"role": "user", "content": user_prompt}
            ],
            temperature=0.3
        )
        
        return {
            "response": response.choices[0].message.content,
            "sources": [c["source"] for c in context],
            "confidence": self._calculate_confidence(search_results)
        }
    
    def _format_context(self, context):
        formatted = []
        for item in context:
            formatted.append(f"Source: {item['source']}\nContent: {item['content']}")
        return "\n\n".join(formatted)