from __future__ import annotations

import hashlib
import math


class EmbeddingService:
    """Deterministic local embeddings so Chroma can persist vectors without a remote embedding API."""

    def __init__(self, dimensions: int = 256) -> None:
        self.dimensions = dimensions

    def embed_documents(self, texts: list[str]) -> list[list[float]]:
        return [self.embed_query(text) for text in texts]

    def embed_query(self, text: str) -> list[float]:
        vector = [0.0] * self.dimensions
        tokens = self._tokenize(text)
        if not tokens:
            return vector

        for token in tokens:
            digest = hashlib.sha256(token.encode("utf-8")).digest()
            bucket = int.from_bytes(digest[:4], "big") % self.dimensions
            sign = 1.0 if digest[4] % 2 == 0 else -1.0
            vector[bucket] += sign

        norm = math.sqrt(sum(value * value for value in vector)) or 1.0
        return [value / norm for value in vector]

    @staticmethod
    def _tokenize(text: str) -> list[str]:
        return [token.strip().lower() for token in text.replace("\n", " ").split() if token.strip()]