FakeEmbeddings Class — langchain Architecture

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

Class python

Entity Profile

Dependency Diagram

graph TD
  e940e4d4_ddda_75d4_837c_c81c126d33c3["FakeEmbeddings"]
  b1e4f760_c634_d3bf_ca9a_db7ab899cc4a["Embeddings"]
  e940e4d4_ddda_75d4_837c_c81c126d33c3 -->|extends| b1e4f760_c634_d3bf_ca9a_db7ab899cc4a
  7329f2d2_fa41_f27b_f1da_ed27a7ea1af7["fake_embeddings.py"]
  e940e4d4_ddda_75d4_837c_c81c126d33c3 -->|defined in| 7329f2d2_fa41_f27b_f1da_ed27a7ea1af7
  adc2e5ee_2c56_2e04_882f_3b17eca2f467["embed_documents()"]
  e940e4d4_ddda_75d4_837c_c81c126d33c3 -->|method| adc2e5ee_2c56_2e04_882f_3b17eca2f467
  90b04c46_c2a4_dab2_4da0_de4a67b970cc["aembed_documents()"]
  e940e4d4_ddda_75d4_837c_c81c126d33c3 -->|method| 90b04c46_c2a4_dab2_4da0_de4a67b970cc
  f91f62e2_f3f4_c3b1_fa56_7ac7544ca8e1["embed_query()"]
  e940e4d4_ddda_75d4_837c_c81c126d33c3 -->|method| f91f62e2_f3f4_c3b1_fa56_7ac7544ca8e1
  d3c8ddf7_7eb1_4b5c_257d_653887ce641b["aembed_query()"]
  e940e4d4_ddda_75d4_837c_c81c126d33c3 -->|method| d3c8ddf7_7eb1_4b5c_257d_653887ce641b

Relationship Graph

Source Code

libs/langchain/tests/integration_tests/cache/fake_embeddings.py lines 11–48

class FakeEmbeddings(Embeddings):
    """Fake embeddings functionality for testing."""

    @override
    def embed_documents(self, texts: list[str]) -> list[list[float]]:
        """Return simple embeddings.

        Embeddings encode each text as its index.

        Args:
            texts: List of text to embed.

        Returns:
            List of embeddings.
        """
        return [[1.0] * 9 + [float(i)] for i in range(len(texts))]

    async def aembed_documents(self, texts: list[str]) -> list[list[float]]:
        return self.embed_documents(texts)

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

        Embeddings are identical to embed_documents(texts)[0].
        Distance to each text will be that text's index,
        as it was passed to embed_documents.

        Args:
            text: Text to embed.

        Returns:
            Embedding.
        """
        return [1.0] * 9 + [0.0]

    async def aembed_query(self, text: str) -> list[float]:
        return self.embed_query(text)