from app.core.llm import get_llm
from app.memory.qdrant_memory import search_memory

async def generate_response(
    user_id,
    user_query
):

    memories = search_memory(
        user_id,
        user_query
    )

    memory_context = "\n".join(memories)

    SYSTEM_PROMPT = f"""
    You are NeuroFlora,
    an intelligent plant disease assistant.

    Previous user memories:
    {memory_context}

    Help users with:
    - plant diseases
    - crop health
    - farming guidance
    - pesticide awareness
    - plant care
    """

    client = get_llm()

    response = await client.chat.completions.create(
        model="meta-llama/Llama-3.1-70B-Instruct:scaleway",
        messages=[
            {
                "role": "system",
                "content": SYSTEM_PROMPT
            },
            {
                "role": "user",
                "content": user_query
            }
        ],
        stream=True
    )

    return response