_compute_score() — langchain Function Reference

Architecture documentation for the _compute_score() function in base.py from the langchain codebase.

Function python LangChainCore LanguageModelBase calls 3 called by 4

Entity Profile

LangChainCore→ LanguageModelBase→ _compute_score() — langchain Function Reference

Dependency Diagram

graph TD
  af8d1584_7461_17c4_1dc0_409b11712821["_compute_score()"]
  dc2d52f5_736c_0ec2_ad57_0e2fdaa94e04["_EmbeddingDistanceChainMixin"]
  af8d1584_7461_17c4_1dc0_409b11712821 -->|defined in| dc2d52f5_736c_0ec2_ad57_0e2fdaa94e04
  b87deb74_80b9_1b59_d7bb_3ea345fa69b3["_call()"]
  b87deb74_80b9_1b59_d7bb_3ea345fa69b3 -->|calls| af8d1584_7461_17c4_1dc0_409b11712821
  0aaa55c8_a3a2_76b1_2dcd_56a0d3853e7e["_acall()"]
  0aaa55c8_a3a2_76b1_2dcd_56a0d3853e7e -->|calls| af8d1584_7461_17c4_1dc0_409b11712821
  55bba962_c474_7d72_fad4_2419ad83c3a7["_call()"]
  55bba962_c474_7d72_fad4_2419ad83c3a7 -->|calls| af8d1584_7461_17c4_1dc0_409b11712821
  5cbc8187_38d5_da15_88a2_96912b92daeb["_acall()"]
  5cbc8187_38d5_da15_88a2_96912b92daeb -->|calls| af8d1584_7461_17c4_1dc0_409b11712821
  ce394d48_537e_9c2f_6235_1e3ee8acabb5["_get_metric()"]
  af8d1584_7461_17c4_1dc0_409b11712821 -->|calls| ce394d48_537e_9c2f_6235_1e3ee8acabb5
  91b8ba41_75bf_8afd_e893_d85d055226da["_check_numpy()"]
  af8d1584_7461_17c4_1dc0_409b11712821 -->|calls| 91b8ba41_75bf_8afd_e893_d85d055226da
  caa53c2b_01ef_7204_a5e6_ad683c86dbd2["_import_numpy()"]
  af8d1584_7461_17c4_1dc0_409b11712821 -->|calls| caa53c2b_01ef_7204_a5e6_ad683c86dbd2
  style af8d1584_7461_17c4_1dc0_409b11712821 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/evaluation/embedding_distance/base.py lines 329–343

    def _compute_score(self, vectors: Any) -> float:
        """Compute the score based on the distance metric.

        Args:
            vectors (np.ndarray): The input vectors.

        Returns:
            The computed score.
        """
        metric = self._get_metric(self.distance_metric)
        if _check_numpy() and isinstance(vectors, _import_numpy().ndarray):
            score = metric(vectors[0].reshape(1, -1), vectors[1].reshape(1, -1)).item()
        else:
            score = metric(vectors[0], vectors[1])
        return float(score)