fake.py — langchain Source File

Source Code

"""Module contains a few fake embedding models for testing purposes."""

# Please do not add additional fake embedding model implementations here.
import contextlib
import hashlib

from pydantic import BaseModel
from typing_extensions import override

from langchain_core.embeddings import Embeddings

with contextlib.suppress(ImportError):
    import numpy as np


class FakeEmbeddings(Embeddings, BaseModel):
    """Fake embedding model for unit testing purposes.

    This embedding model creates embeddings by sampling from a normal distribution.

    !!! danger "Toy model"
        Do not use this outside of testing, as it is not a real embedding model.

    Instantiate:
        ```python
        from langchain_core.embeddings import FakeEmbeddings

        embed = FakeEmbeddings(size=100)
        ```

    Embed single text:
        ```python
        input_text = "The meaning of life is 42"
        vector = embed.embed_query(input_text)
        print(vector[:3])
        ```
        ```python
        [-0.700234640213188, -0.581266257710429, -1.1328482266445354]
        ```

    Embed multiple texts:
        ```python
        input_texts = ["Document 1...", "Document 2..."]
        vectors = embed.embed_documents(input_texts)
        print(len(vectors))
        # The first 3 coordinates for the first vector
        print(vectors[0][:3])
        ```
        ```python
        2
        [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]
        ```
    """

    size: int
    """The size of the embedding vector."""

    def _get_embedding(self) -> list[float]:
        return list(np.random.default_rng().normal(size=self.size))

// ... (70 more lines)