_select_relevance_score_fn() — langchain Function Reference

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

Function python LangChainCore ApiManagement calls 1

Entity Profile

LangChainCore→ ApiManagement→ _select_relevance_score_fn() — langchain Function Reference

Dependency Diagram

graph TD
  57963f92_9313_a2fa_4c10_f6ae0431b144["_select_relevance_score_fn()"]
  671b47a0_cdd3_a89d_e90f_0631a4bd67d3["QdrantVectorStore"]
  57963f92_9313_a2fa_4c10_f6ae0431b144 -->|defined in| 671b47a0_cdd3_a89d_e90f_0631a4bd67d3
  7a5dfd47_12fc_b507_5302_d35ca595d8b7["embeddings()"]
  57963f92_9313_a2fa_4c10_f6ae0431b144 -->|calls| 7a5dfd47_12fc_b507_5302_d35ca595d8b7
  style 57963f92_9313_a2fa_4c10_f6ae0431b144 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/qdrant/langchain_qdrant/qdrant.py lines 1004–1020

    def _select_relevance_score_fn(self) -> Callable[[float], float]:
        """Your "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.
        """
        if self.distance == models.Distance.COSINE:
            return self._cosine_relevance_score_fn
        if self.distance == models.Distance.DOT:
            return self._max_inner_product_relevance_score_fn
        if self.distance == models.Distance.EUCLID:
            return self._euclidean_relevance_score_fn
        msg = "Unknown distance strategy, must be COSINE, DOT, or EUCLID."
        raise ValueError(msg)