Source code for langchain_community.embeddings.fake
import hashlib
from typing import List
import numpy as np
from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel
[docs]class FakeEmbeddings(Embeddings, BaseModel):
"""樑ζε΅ε
₯樑εγ"""
size: int
"""ε΅ε
₯ειη倧ε°γ"""
def _get_embedding(self) -> List[float]:
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):
"""δΈδΈͺεηε΅ε
₯樑εοΌε―ΉδΊηΈεηζζ¬ε§η»θΏεηΈεηε΅ε
₯ειγ"""
size: int
"""ε΅ε
₯ειη倧ε°γ"""
def _get_embedding(self, seed: int) -> List[float]:
# 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:
"""
θ·ειζΊηζε¨ηη§εοΌδ½Ώη¨ζζ¬ηεεΈεΌγ
"""
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))