_VectorStoreExampleSelector Class — langchain Architecture

Architecture documentation for the _VectorStoreExampleSelector class in semantic_similarity.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  a80787c0_fd68_ab68_1e5d_400de9d4457f["_VectorStoreExampleSelector"]
  24f4d101_08ec_c1e7_bd03_b1308f5aa1aa["BaseExampleSelector"]
  a80787c0_fd68_ab68_1e5d_400de9d4457f -->|extends| 24f4d101_08ec_c1e7_bd03_b1308f5aa1aa
  68b41b07_21c1_a50f_08fe_c4151de58027["semantic_similarity.py"]
  a80787c0_fd68_ab68_1e5d_400de9d4457f -->|defined in| 68b41b07_21c1_a50f_08fe_c4151de58027
  06f73539_fe12_1c9c_b0b0_60530c6bf341["_example_to_text()"]
  a80787c0_fd68_ab68_1e5d_400de9d4457f -->|method| 06f73539_fe12_1c9c_b0b0_60530c6bf341
  27e09fc4_bf9b_d1a5_5626_387af543d2c7["_documents_to_examples()"]
  a80787c0_fd68_ab68_1e5d_400de9d4457f -->|method| 27e09fc4_bf9b_d1a5_5626_387af543d2c7
  cff2e64a_c9b6_f943_4cfe_92ed35138c3e["add_example()"]
  a80787c0_fd68_ab68_1e5d_400de9d4457f -->|method| cff2e64a_c9b6_f943_4cfe_92ed35138c3e
  99e00c13_46c4_810f_2aad_79ef0d688a4c["aadd_example()"]
  a80787c0_fd68_ab68_1e5d_400de9d4457f -->|method| 99e00c13_46c4_810f_2aad_79ef0d688a4c

Relationship Graph

Source Code

libs/core/langchain_core/example_selectors/semantic_similarity.py lines 31–94

class _VectorStoreExampleSelector(BaseExampleSelector, BaseModel, ABC):
    """Example selector that selects examples based on SemanticSimilarity."""

    vectorstore: VectorStore
    """VectorStore that contains information about examples."""
    k: int = 4
    """Number of examples to select."""
    example_keys: list[str] | None = None
    """Optional keys to filter examples to."""
    input_keys: list[str] | None = None
    """Optional keys to filter input to. If provided, the search is based on
    the input variables instead of all variables."""
    vectorstore_kwargs: dict[str, Any] | None = None
    """Extra arguments passed to similarity_search function of the `VectorStore`."""

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
        extra="forbid",
    )

    @staticmethod
    def _example_to_text(example: dict[str, str], input_keys: list[str] | None) -> str:
        if input_keys:
            return " ".join(sorted_values({key: example[key] for key in input_keys}))
        return " ".join(sorted_values(example))

    def _documents_to_examples(self, documents: list[Document]) -> list[dict]:
        # Get the examples from the metadata.
        # This assumes that examples are stored in metadata.
        examples = [dict(e.metadata) for e in documents]
        # If example keys are provided, filter examples to those keys.
        if self.example_keys:
            examples = [{k: eg[k] for k in self.example_keys} for eg in examples]
        return examples

    def add_example(self, example: dict[str, str]) -> str:
        """Add a new example to vectorstore.

        Args:
            example: A dictionary with keys as input variables
                and values as their values.

        Returns:
            The ID of the added example.
        """
        ids = self.vectorstore.add_texts(
            [self._example_to_text(example, self.input_keys)], metadatas=[example]
        )
        return ids[0]

    async def aadd_example(self, example: dict[str, str]) -> str:
        """Async add new example to vectorstore.

        Args:
            example: A dictionary with keys as input variables
                and values as their values.

        Returns:
            The ID of the added example.
        """
        ids = await self.vectorstore.aadd_texts(
            [self._example_to_text(example, self.input_keys)], metadatas=[example]
        )
        return ids[0]