_max_inner_product_relevance_score_fn() — langchain Function Reference

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

Function python DataProcessing DocumentLoaders

Entity Profile

DataProcessing→ DocumentLoaders→ _max_inner_product_relevance_score_fn() — langchain Function Reference

Dependency Diagram

graph TD
  854a3ced_1bf0_79b1_0922_00ada25aa626["_max_inner_product_relevance_score_fn()"]
  6c336ac6_f55c_1ad7_6db3_73dbd71fb625["VectorStore"]
  854a3ced_1bf0_79b1_0922_00ada25aa626 -->|defined in| 6c336ac6_f55c_1ad7_6db3_73dbd71fb625
  style 854a3ced_1bf0_79b1_0922_00ada25aa626 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/vectorstores/base.py lines 396–401

    def _max_inner_product_relevance_score_fn(distance: float) -> float:
        """Normalize the distance to a score on a scale [0, 1]."""
        if distance > 0:
            return 1.0 - distance

        return -1.0 * distance