diff --git a/libs/community/langchain_community/vectorstores/pgvector.py b/libs/community/langchain_community/vectorstores/pgvector.py
index af0f9ad32ff..7a8a49bc48d 100644
--- a/libs/community/langchain_community/vectorstores/pgvector.py
+++ b/libs/community/langchain_community/vectorstores/pgvector.py
@@ -455,7 +455,7 @@ class PGVector(VectorStore):
         return self.CollectionStore.get_by_name(session, self.collection_name)
 
     @classmethod
-    def __from(
+    def _from(
         cls,
         texts: List[str],
         embeddings: List[List[float]],
@@ -623,7 +623,7 @@ class PGVector(VectorStore):
         k: int = 4,
         filter: Optional[dict] = None,
     ) -> List[Tuple[Document, float]]:
-        results = self.__query_collection(embedding=embedding, k=k, filter=filter)
+        results = self._query_collection(embedding=embedding, k=k, filter=filter)
 
         return self._results_to_docs_and_scores(results)
 
@@ -922,7 +922,7 @@ class PGVector(VectorStore):
                 f"Invalid type: Expected a dictionary but got type: {type(filters)}"
             )
 
-    def __query_collection(
+    def _query_collection(
         self,
         embedding: List[float],
         k: int = 4,
@@ -1008,7 +1008,7 @@ class PGVector(VectorStore):
         """
         embeddings = embedding.embed_documents(list(texts))
 
-        return cls.__from(
+        return cls._from(
             texts,
             embeddings,
             embedding,
@@ -1054,7 +1054,7 @@ class PGVector(VectorStore):
         texts = [t[0] for t in text_embeddings]
         embeddings = [t[1] for t in text_embeddings]
 
-        return cls.__from(
+        return cls._from(
             texts,
             embeddings,
             embedding,
@@ -1218,7 +1218,7 @@ class PGVector(VectorStore):
             List[Tuple[Document, float]]: List of Documents selected by maximal marginal
                 relevance to the query and score for each.
         """
-        results = self.__query_collection(embedding=embedding, k=fetch_k, filter=filter)
+        results = self._query_collection(embedding=embedding, k=fetch_k, filter=filter)
 
         embedding_list = [result.EmbeddingStore.embedding for result in results]