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


[docs]class FakeEmbeddings(Embeddings, BaseModel): """Fake embedding model.""" size: int """The size of the embedding vector.""" 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))
[docs] def embed_documents(self, texts: List[str]) -> List[List[float]]: return [self._get_embedding() for _ in texts]
[docs] def embed_query(self, text: str) -> List[float]: return self._get_embedding()
[docs]class DeterministicFakeEmbedding(Embeddings, BaseModel): """ Fake embedding model that always returns the same embedding vector for the same text. """ size: int """The size of the embedding vector.""" 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: """ Get a seed for the random generator, using the hash of the text. """ return int(hashlib.sha256(text.encode("utf-8")).hexdigest(), 16) % 10**8
[docs] def embed_documents(self, texts: List[str]) -> List[List[float]]: return [self._get_embedding(seed=self._get_seed(_)) for _ in texts]
[docs] def embed_query(self, text: str) -> List[float]: return self._get_embedding(seed=self._get_seed(text))