ConsistentFakeEmbeddings Class — langchain Architecture

Architecture documentation for the ConsistentFakeEmbeddings class in fake_embeddings.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  c9ef4937_4c8f_65e2_006f_5cf4aee0c299["ConsistentFakeEmbeddings"]
  dca08b34_f922_a3fa_4752_e72b03b86d89["FakeEmbeddings"]
  c9ef4937_4c8f_65e2_006f_5cf4aee0c299 -->|extends| dca08b34_f922_a3fa_4752_e72b03b86d89
  7329f2d2_fa41_f27b_f1da_ed27a7ea1af7["fake_embeddings.py"]
  c9ef4937_4c8f_65e2_006f_5cf4aee0c299 -->|defined in| 7329f2d2_fa41_f27b_f1da_ed27a7ea1af7
  463d938b_ca77_945a_9d1d_5fe896a09728["__init__()"]
  c9ef4937_4c8f_65e2_006f_5cf4aee0c299 -->|method| 463d938b_ca77_945a_9d1d_5fe896a09728
  1f17bb26_27fa_63ce_1206_8a0fb97317b0["embed_documents()"]
  c9ef4937_4c8f_65e2_006f_5cf4aee0c299 -->|method| 1f17bb26_27fa_63ce_1206_8a0fb97317b0
  fe8af560_d512_0d8d_8702_5b02575b62af["embed_query()"]
  c9ef4937_4c8f_65e2_006f_5cf4aee0c299 -->|method| fe8af560_d512_0d8d_8702_5b02575b62af

Relationship Graph

Source Code

libs/langchain/tests/integration_tests/cache/fake_embeddings.py lines 51–87

class ConsistentFakeEmbeddings(FakeEmbeddings):
    """Consistent fake embeddings.

    Fake embeddings which remember all the texts seen so far to return consistent
    vectors for the same texts.
    """

    def __init__(self, dimensionality: int = 10) -> None:
        self.known_texts: list[str] = []
        self.dimensionality = dimensionality

    def embed_documents(self, texts: list[str]) -> list[list[float]]:
        """Return consistent embeddings for each text seen so far."""
        out_vectors = []
        for text in texts:
            if text not in self.known_texts:
                self.known_texts.append(text)
            vector = [1.0] * (self.dimensionality - 1) + [
                float(self.known_texts.index(text)),
            ]
            out_vectors.append(vector)
        return out_vectors

    @override
    def embed_query(self, text: str) -> list[float]:
        """Embed query text.

        Return consistent embeddings for the text, if seen before, or a constant
        one if the text is unknown.

        Args:
            text: Text to embed.

        Returns:
            Embedding.
        """
        return self.embed_documents([text])[0]