Source code for langchain_core.embeddings.fake

import hashlib
from typing import List

from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel


class FakeEmbeddings(Embeddings, BaseModel):
    """虚假的嵌入模型。"""

    size: int
    """嵌入向量的大小。"""

    def _get_embedding(self) -> List[float]:
        import numpy as np  # type: ignore[import-not-found, import-untyped]

        return list(np.random.normal(size=self.size))

    def embed_documents(self, texts: List[str]) -> List[List[float]]:
        return [self._get_embedding() for _ in texts]

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


class DeterministicFakeEmbedding(Embeddings, BaseModel):
    """虚拟嵌入模型，始终为相同文本返回相同的嵌入向量。
"""

    size: int
    """嵌入向量的大小。"""

    def _get_embedding(self, seed: int) -> List[float]:
        import numpy as np  # type: ignore[import-not-found, import-untyped]

        # set the seed for the random generator
        np.random.seed(seed)
        return list(np.random.normal(size=self.size))

    def _get_seed(self, text: str) -> int:
        """
        使用文本的哈希值获取随机生成器的种子。
        """
        return int(hashlib.sha256(text.encode("utf-8")).hexdigest(), 16) % 10**8

    def embed_documents(self, texts: List[str]) -> List[List[float]]:
        return [self._get_embedding(seed=self._get_seed(_)) for _ in texts]

    def embed_query(self, text: str) -> List[float]:
        return self._get_embedding(seed=self._get_seed(text))