community: Opensearch - added score function for similarity_score_threshold (#23928)

This PR resolves the NotImplemented error for the
similarity_score_threshold search type for OpenSearch.

libs/community/langchain_community/vectorstores/opensearch_vector_search.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import uuid
 import warnings
-from typing import Any, Dict, Iterable, List, Optional, Tuple
+from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple
 
 import numpy as np
 from langchain_core.documents import Document
@@ -733,6 +733,23 @@ class OpenSearchVectorSearch(VectorStore):
             item.get("delete", {}).get("error") for item in response["items"]
         )
 
+    @staticmethod
+    def _identity_fn(score: float) -> float:
+        return score
+
+    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.
+        """
+        return self._identity_fn
+
     def similarity_search(
         self,
         query: str,