_select_relevance_score_fn() — langchain Function Reference

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

Function python DataProcessing VectorStores calls 1 called by 2

Entity Profile

DataProcessing→ VectorStores→ _select_relevance_score_fn() — langchain Function Reference

Dependency Diagram

graph TD
  33645b34_9b5d_1213_3ea8_78c13a480380["_select_relevance_score_fn()"]
  6c336ac6_f55c_1ad7_6db3_73dbd71fb625["VectorStore"]
  33645b34_9b5d_1213_3ea8_78c13a480380 -->|defined in| 6c336ac6_f55c_1ad7_6db3_73dbd71fb625
  af56f371_686f_e656_d90d_d283b46d217f["_similarity_search_with_relevance_scores()"]
  af56f371_686f_e656_d90d_d283b46d217f -->|calls| 33645b34_9b5d_1213_3ea8_78c13a480380
  37ad19f9_1964_1b28_9306_a16c8d128f6e["_asimilarity_search_with_relevance_scores()"]
  37ad19f9_1964_1b28_9306_a16c8d128f6e -->|calls| 33645b34_9b5d_1213_3ea8_78c13a480380
  0cd8a5fb_f912_cf41_5d28_286a9342680c["embeddings()"]
  33645b34_9b5d_1213_3ea8_78c13a480380 -->|calls| 0cd8a5fb_f912_cf41_5d28_286a9342680c
  style 33645b34_9b5d_1213_3ea8_78c13a480380 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/vectorstores/base.py lines 403–415

    def _select_relevance_score_fn(self) -> Callable[[float], float]:
        """The 'correct' relevance function.

        May differ depending on a few things, including:

        - The distance / similarity metric used by the VectorStore
        - The scale of your embeddings (OpenAI's are unit normed. Many others are not!)
        - Embedding dimensionality
        - etc.

        Vectorstores should define their own selection-based method of relevance.
        """
        raise NotImplementedError