_select_relevance_score_fn() — langchain Function Reference

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

Function python CoreAbstractions RunnableInterface calls 1

Entity Profile

CoreAbstractions→ RunnableInterface→ _select_relevance_score_fn() — langchain Function Reference

Dependency Diagram

graph TD
  8c67c864_9e3f_9062_f118_53634c0b8779["_select_relevance_score_fn()"]
  bf62db79_4217_463c_798f_6f8528ed0d6e["Qdrant"]
  8c67c864_9e3f_9062_f118_53634c0b8779 -->|defined in| bf62db79_4217_463c_798f_6f8528ed0d6e
  764dd93f_b65e_f753_9b79_dd9b5db4e0c0["embeddings()"]
  8c67c864_9e3f_9062_f118_53634c0b8779 -->|calls| 764dd93f_b65e_f753_9b79_dd9b5db4e0c0
  style 8c67c864_9e3f_9062_f118_53634c0b8779 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/qdrant/langchain_qdrant/vectorstores.py lines 1950–1968

    def _select_relevance_score_fn(self) -> Callable[[float], float]:
        """Your 'correct' relevance function may differ depending on a few things.

        For example:
        - 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_strategy == "COSINE":
            return self._cosine_relevance_score_fn
        if self.distance_strategy == "DOT":
            return self._max_inner_product_relevance_score_fn
        if self.distance_strategy == "EUCLID":
            return self._euclidean_relevance_score_fn
        msg = (
            "Unknown distance strategy, must be cosine, max_inner_product, or euclidean"
        )
        raise ValueError(msg)