DeterministicFakeEmbedding Class — langchain Architecture

Architecture documentation for the DeterministicFakeEmbedding class in fake.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72["DeterministicFakeEmbedding"]
  c58e6864_9429_b081_883b_39ba15df0485["Embeddings"]
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72 -->|extends| c58e6864_9429_b081_883b_39ba15df0485
  11efe23b_60e7_3caa_e6e9_4e2ebbca866c["fake.py"]
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72 -->|defined in| 11efe23b_60e7_3caa_e6e9_4e2ebbca866c
  e833a287_d82a_8433_9954_b8d6a931f533["_get_embedding()"]
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72 -->|method| e833a287_d82a_8433_9954_b8d6a931f533
  f686e370_58b4_dc46_9246_4c5e8efd32d1["_get_seed()"]
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72 -->|method| f686e370_58b4_dc46_9246_4c5e8efd32d1
  315b1daa_e924_7e9b_d93f_2f52a904593d["embed_documents()"]
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72 -->|method| 315b1daa_e924_7e9b_d93f_2f52a904593d
  9234e065_ff83_9ceb_311f_333bded4222b["embed_query()"]
  fe9b759a_d8f2_7e0f_ebb7_a43c9ba18e72 -->|method| 9234e065_ff83_9ceb_311f_333bded4222b

Relationship Graph

Source Code

libs/core/langchain_core/embeddings/fake.py lines 70–129

class DeterministicFakeEmbedding(Embeddings, BaseModel):
    """Deterministic fake embedding model for unit testing purposes.

    This embedding model creates embeddings by sampling from a normal distribution
    with a seed based on the hash of the text.

    !!! 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 DeterministicFakeEmbedding

        embed = DeterministicFakeEmbedding(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, seed: int) -> list[float]:
        # set the seed for the random generator
        rng = np.random.default_rng(seed)
        return list(rng.normal(size=self.size))

    @staticmethod
    def _get_seed(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

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

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