ConsistentFakeEmbeddings Class — langchain Architecture

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

Class python

Entity Profile

Dependency Diagram

graph TD
  82fdec4c_643f_ba88_9e2f_3cca83facf7d["ConsistentFakeEmbeddings"]
  b1e4f760_c634_d3bf_ca9a_db7ab899cc4a["Embeddings"]
  82fdec4c_643f_ba88_9e2f_3cca83facf7d -->|extends| b1e4f760_c634_d3bf_ca9a_db7ab899cc4a
  b62fe5d9_7b83_0e14_ef50_3645cafa8bc5["common.py"]
  82fdec4c_643f_ba88_9e2f_3cca83facf7d -->|defined in| b62fe5d9_7b83_0e14_ef50_3645cafa8bc5
  951df23f_487e_7b05_2034_014e96a99774["__init__()"]
  82fdec4c_643f_ba88_9e2f_3cca83facf7d -->|method| 951df23f_487e_7b05_2034_014e96a99774
  c7906a5b_be59_8e0f_0985_35c80ce0e933["embed_documents()"]
  82fdec4c_643f_ba88_9e2f_3cca83facf7d -->|method| c7906a5b_be59_8e0f_0985_35c80ce0e933
  bfd25742_f7e1_933a_a6df_484d09d2f8b2["embed_query()"]
  82fdec4c_643f_ba88_9e2f_3cca83facf7d -->|method| bfd25742_f7e1_933a_a6df_484d09d2f8b2

Relationship Graph

Source Code

libs/partners/qdrant/tests/integration_tests/common.py lines 33–58

class ConsistentFakeEmbeddings(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

    def embed_query(self, text: str) -> list[float]:
        """Return consistent embeddings for the text, if seen before, or a constant
        one if the text is unknown.
        """
        return self.embed_documents([text])[0]