langchain_community: Checking text property first in neo4j to avoid duplicate nodes

libs/community/langchain_community/vectorstores/neo4j_vector.py

@@ -1,28 +1,29 @@
 from __future__ import annotations
 
 import enum
 import logging
 import os
 import uuid
+import hashlib
 from typing import (
     Any,
     Callable,
     Dict,
     Iterable,
     List,
     Optional,
     Tuple,
     Type,
 )
 
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
 from langchain_core.utils import get_from_env
 from langchain_core.vectorstores import VectorStore
 
 from langchain_community.vectorstores.utils import DistanceStrategy
 
 DEFAULT_DISTANCE_STRATEGY = DistanceStrategy.COSINE
 DISTANCE_MAPPING = {
     DistanceStrategy.EUCLIDEAN_DISTANCE: "euclidean",
     DistanceStrategy.COSINE: "cosine",
@@ -493,7 +494,8 @@
             kwargs: vectorstore specific parameters
         """
         if ids is None:
-            ids = [str(uuid.uuid1()) for _ in texts]
+            ids = [hashlib.sha256(text.encode('utf-8')).hexdigest()
+               for text in texts]
 
         if not metadatas:
             metadatas = [{} for _ in texts]