from typing import List

from llama_index.core import Document, Settings, VectorStoreIndex
from llama_index.core.embeddings import BaseEmbedding


class KeywordEmbedding(BaseEmbedding):
    @classmethod
    def class_name(cls) -> str:
        return "KeywordEmbedding"

    def _vector(self, text: str) -> List[float]:
        lowered = text.lower()
        refund_signal = 1.0 if any(
            term in lowered for term in ("refund", "support", "handbook")
        ) else 0.0
        release_signal = 1.0 if any(
            term in lowered for term in ("release", "deployment", "calendar")
        ) else 0.0
        return [refund_signal, release_signal, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]

    def _get_text_embedding(self, text: str) -> List[float]:
        return self._vector(text)

    def _get_query_embedding(self, query: str) -> List[float]:
        return self._vector(query)

    async def _aget_query_embedding(self, query: str) -> List[float]:
        return self._get_query_embedding(query)