text-splitters[minor], langchain[minor], community[patch], templates, docs: langchain-text-splitters 0.0.1 (#18346)

.github/scripts/check_diff.py

@@ -5,6 +5,7 @@ from typing import Dict
 
 LANGCHAIN_DIRS = [
     "libs/core",
+    "libs/text-splitters",
     "libs/community",
     "libs/langchain",
     "libs/experimental",

.github/scripts/get_min_versions.py

@@ -4,7 +4,7 @@ import tomllib
 from packaging.version import parse as parse_version
 import re
 
-MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain"]
+MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain", "langchain-text-splitters"]
 
 
 def get_min_version(version: str) -> str:

cookbook/Multi_modal_RAG.ipynb

@@ -116,7 +116,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "\n",

cookbook/advanced_rag_eval.ipynb

@@ -68,7 +68,7 @@
     "pdf_pages = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
     "all_splits_pypdf = text_splitter.split_documents(pdf_pages)\n",

cookbook/agent_vectorstore.ipynb

@@ -28,9 +28,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "llm = OpenAI(temperature=0)"
    ]

cookbook/autogpt/marathon_times.ipynb

@@ -227,8 +227,8 @@
     "    BaseCombineDocumentsChain,\n",
     "    load_qa_with_sources_chain,\n",
     ")\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain.tools import BaseTool, DuckDuckGoSearchRun\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "from pydantic import Field\n",
     "\n",
     "\n",

cookbook/code-analysis-deeplake.ipynb

@@ -24,7 +24,7 @@
    "source": [
     "1. Prepare data:\n",
     "   1. Upload all python project files using the `langchain_community.document_loaders.TextLoader`. We will call these files the **documents**.\n",
-    "   2. Split all documents to chunks using the `langchain.text_splitter.CharacterTextSplitter`.\n",
+    "   2. Split all documents to chunks using the `langchain_text_splitters.CharacterTextSplitter`.\n",
     "   3. Embed chunks and upload them into the DeepLake using `langchain.embeddings.openai.OpenAIEmbeddings` and `langchain_community.vectorstores.DeepLake`\n",
     "2. Question-Answering:\n",
     "   1. Build a chain from `langchain.chat_models.ChatOpenAI` and `langchain.chains.ConversationalRetrievalChain`\n",
@@ -621,7 +621,7 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)\n",

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -52,12 +52,12 @@
     "import os\n",
     "\n",
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import (\n",
+    "from langchain_community.vectorstores import DeepLake\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import (\n",
     "    CharacterTextSplitter,\n",
     "    RecursiveCharacterTextSplitter,\n",
     ")\n",
-    "from langchain_community.vectorstores import DeepLake\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
     "activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",

cookbook/fireworks_rag.ipynb

@@ -132,7 +132,7 @@
     "data = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)\n",
     "all_splits = text_splitter.split_documents(data)\n",

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,8 +170,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "with open(\"../../state_of_the_union.txt\") as f:\n",
     "    state_of_the_union = f.read()\n",

cookbook/nomic_embedding_rag.ipynb

@@ -124,7 +124,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter.from_tiktoken_encoder(\n",
     "    chunk_size=7500, chunk_overlap=100\n",

cookbook/openai_functions_retrieval_qa.ipynb

@@ -20,10 +20,10 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

cookbook/qianfan_baidu_elasticesearch_RAG.ipynb

@@ -59,13 +59,13 @@
     "from baidubce.auth.bce_credentials import BceCredentials\n",
     "from baidubce.bce_client_configuration import BceClientConfiguration\n",
     "from langchain.chains.retrieval_qa import RetrievalQA\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders.baiducloud_bos_directory import (\n",
     "    BaiduBOSDirectoryLoader,\n",
     ")\n",
     "from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings\n",
     "from langchain_community.llms.baidu_qianfan_endpoint import QianfanLLMEndpoint\n",
-    "from langchain_community.vectorstores import BESVectorStore"
+    "from langchain_community.vectorstores import BESVectorStore\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
    ]
   },
   {

cookbook/rag_with_quantized_embeddings.ipynb

@@ -36,9 +36,6 @@
     "from bs4 import BeautifulSoup as Soup\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryByteStore, LocalFileStore\n",
-    "\n",
-    "# For our example, we'll load docs from the web\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter  # noqa\n",
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
@@ -46,6 +43,9 @@
     "# noqa\n",
     "from langchain_community.vectorstores import Chroma\n",
     "\n",
+    "# For our example, we'll load docs from the web\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter  # noqa\n",
+    "\n",
     "DOCSTORE_DIR = \".\"\n",
     "DOCSTORE_ID_KEY = \"doc_id\""
    ]

cookbook/sales_agent_with_context.ipynb

@@ -51,11 +51,11 @@
     "from langchain.chains.base import Chain\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.prompts.base import StringPromptTemplate\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.llms import BaseLLM\n",
     "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.agents import AgentAction, AgentFinish\n",
     "from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "from pydantic import BaseModel, Field"
    ]
   },

cookbook/together_ai.ipynb

@@ -39,7 +39,7 @@
     "data = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)\n",
     "all_splits = text_splitter.split_documents(data)\n",

cookbook/twitter-the-algorithm-analysis-deeplake.ipynb

@@ -2610,7 +2610,7 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)"

docs/docs/get_started/quickstart.mdx

@@ -281,7 +281,7 @@ Then we can build our index:
 
 ```python
 from langchain_community.vectorstores import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 
 
 text_splitter = RecursiveCharacterTextSplitter()
@@ -531,7 +531,7 @@ from langchain_openai import ChatOpenAI
 from langchain_community.document_loaders import WebBaseLoader
 from langchain_openai import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain.tools.retriever import create_retriever_tool
 from langchain_community.tools.tavily_search import TavilySearchResults
 from langchain_openai import ChatOpenAI

docs/docs/guides/privacy/presidio_data_anonymization/qa_privacy_protection.ipynb

@@ -643,9 +643,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "# 2. Load the data: In our case data's already loaded\n",
     "# 3. Anonymize the data before indexing\n",

docs/docs/integrations/callbacks/confident.ipynb

@@ -215,10 +215,10 @@
    "source": [
     "import requests\n",
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_file_url = \"https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt\"\n",
     "\n",

docs/docs/integrations/document_loaders/psychic.ipynb

@@ -78,9 +78,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQAWithSourcesChain\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings"
+    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/document_loaders/source_code.ipynb

@@ -62,9 +62,9 @@
     "warnings.filterwarnings(\"ignore\")\n",
     "from pprint import pprint\n",
     "\n",
-    "from langchain.text_splitter import Language\n",
     "from langchain_community.document_loaders.generic import GenericLoader\n",
-    "from langchain_community.document_loaders.parsers import LanguageParser"
+    "from langchain_community.document_loaders.parsers import LanguageParser\n",
+    "from langchain_text_splitters import Language"
    ]
   },
   {
@@ -323,7 +323,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import (\n",
+    "from langchain_text_splitters import (\n",
     "    Language,\n",
     "    RecursiveCharacterTextSplitter,\n",
     ")"
@@ -426,6 +426,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {},
    "source": [
     "## Adding Languages using Tree-sitter Template\n",

docs/docs/integrations/document_loaders/youtube_audio.ipynb

@@ -168,9 +168,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/llms/llm_caching.ipynb

@@ -1463,7 +1463,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter()"
    ]

docs/docs/integrations/llms/manifest.ipynb

@@ -82,7 +82,7 @@
     "# Map reduce example\n",
     "from langchain.chains.mapreduce import MapReduceChain\n",
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "_prompt = \"\"\"Write a concise summary of the following:\n",
     "\n",

docs/docs/integrations/platforms/openai.mdx

@@ -68,7 +68,7 @@ for OpenAI LLMs.
 
 You can also use it to count tokens when splitting documents with 
 ```python
-from langchain.text_splitter import CharacterTextSplitter
+from langchain_text_splitters import CharacterTextSplitter
 CharacterTextSplitter.from_tiktoken_encoder(...)
 ```
 For a more detailed walkthrough of this, see [this notebook](/docs/modules/data_connection/document_transformers/split_by_token#tiktoken)

docs/docs/integrations/providers/elasticsearch.mdx

@@ -34,7 +34,7 @@ The vector store is a simple wrapper around Elasticsearch. It provides a simple
 from langchain_elasticsearch import ElasticsearchStore
 
 from langchain_community.document_loaders import TextLoader
-from langchain.text_splitter import CharacterTextSplitter
+from langchain_text_splitters import CharacterTextSplitter
 
 loader = TextLoader("./state_of_the_union.txt")
 documents = loader.load()

docs/docs/integrations/providers/ragatouille.ipynb

@@ -87,9 +87,9 @@
    "outputs": [],
    "source": [
     "import requests\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "\n",
     "def get_wikipedia_page(title: str):\n",

docs/docs/integrations/providers/spacy.mdx

@@ -16,7 +16,7 @@ pip install spacy
 See a [usage example](/docs/modules/data_connection/document_transformers/split_by_token#spacy).
 
 ```python
-from langchain.text_splitter import SpacyTextSplitter
+from langchain_text_splitters import SpacyTextSplitter
 ```
 
 ## Text Embedding Models

docs/docs/integrations/retrievers/activeloop.ipynb

@@ -192,7 +192,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "chunk_size = 4096\n",
     "docs_new = []\n",

docs/docs/integrations/retrievers/cohere-reranker.ipynb

@@ -301,10 +301,10 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings import CohereEmbeddings\n",
     "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "documents = TextLoader(\"../../modules/state_of_the_union.txt\").load()\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n",

docs/docs/integrations/retrievers/flashrank-reranker.ipynb

@@ -288,10 +288,10 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "documents = TextLoader(\n",
     "    \"../../modules/state_of_the_union.txt\",\n",

docs/docs/integrations/retrievers/jaguar.ipynb

@@ -52,10 +52,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores.jaguar import Jaguar\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "\"\"\" \n",
     "Load a text file into a set of documents \n",

docs/docs/integrations/retrievers/llmlingua.ipynb

@@ -282,10 +282,10 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "documents = TextLoader(\n",
     "    \"../../modules/state_of_the_union.txt\",\n",

docs/docs/integrations/retrievers/re_phrase.ipynb

@@ -28,10 +28,10 @@
     "import logging\n",
     "\n",
     "from langchain.retrievers import RePhraseQueryRetriever\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
     "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/retrievers/self_query/vectara_self_query.ipynb

@@ -89,12 +89,12 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain.chains.query_constructor.base import AttributeInfo\n",
     "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings import FakeEmbeddings\n",
     "from langchain_community.vectorstores import Vectara\n",
     "from langchain_core.documents import Document\n",
-    "from langchain_openai import OpenAI"
+    "from langchain_openai import OpenAI\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/retrievers/singlestoredb.ipynb

@@ -50,10 +50,10 @@
     "# We want to use OpenAIEmbeddings so we have to get the OpenAI API Key.\n",
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
     "\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import SingleStoreDB\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/toolkits/document_comparison_toolkit.ipynb

@@ -21,10 +21,10 @@
    "source": [
     "from langchain.agents import Tool\n",
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import PyPDFLoader\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "from pydantic import BaseModel, Field"
    ]
   },

docs/docs/integrations/vectorstores/activeloop_deeplake.ipynb

@@ -51,9 +51,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import DeepLake\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/alibabacloud_opensearch.ipynb

@@ -129,12 +129,12 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import (\n",
     "    AlibabaCloudOpenSearch,\n",
     "    AlibabaCloudOpenSearchSettings,\n",
     ")\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/analyticdb.ipynb

@@ -23,9 +23,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import AnalyticDB\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/annoy.ipynb

@@ -148,8 +148,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txtn.txtn.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/apache_doris.ipynb

@@ -70,7 +70,6 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import TokenTextSplitter\n",
     "from langchain_community.document_loaders import (\n",
     "    DirectoryLoader,\n",
     "    UnstructuredMarkdownLoader,\n",
@@ -80,6 +79,7 @@
     "    ApacheDorisSettings,\n",
     ")\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import TokenTextSplitter\n",
     "\n",
     "update_vectordb = False"
    ]

docs/docs/integrations/vectorstores/astradb.ipynb

@@ -91,13 +91,13 @@
     "from datasets import (\n",
     "    load_dataset,\n",
     ")\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import PyPDFLoader\n",
     "from langchain_core.documents import Document\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/atlas.ipynb

@@ -71,9 +71,9 @@
    "source": [
     "import time\n",
     "\n",
-    "from langchain.text_splitter import SpacyTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.vectorstores import AtlasDB"
+    "from langchain_community.vectorstores import AtlasDB\n",
+    "from langchain_text_splitters import SpacyTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/awadb.ipynb

@@ -28,9 +28,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.vectorstores import AwaDB"
+    "from langchain_community.vectorstores import AwaDB\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/azure_cosmos_db.ipynb

@@ -130,13 +130,13 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores.azure_cosmos_db import (\n",
     "    AzureCosmosDBVectorSearch,\n",
     "    CosmosDBSimilarityType,\n",
     ")\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "SOURCE_FILE_NAME = \"../../modules/state_of_the_union.txt\"\n",
     "\n",

docs/docs/integrations/vectorstores/azuresearch.ipynb

@@ -234,8 +234,8 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\", encoding=\"utf-8\")\n",
     "\n",

docs/docs/integrations/vectorstores/bageldb.ipynb

@@ -108,8 +108,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/baiducloud_vector_search.ipynb

@@ -77,8 +77,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/cassandra.ipynb

@@ -74,13 +74,13 @@
     "from datasets import (\n",
     "    load_dataset,\n",
     ")\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import PyPDFLoader\n",
     "from langchain_core.documents import Document\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/chroma.ipynb

@@ -65,12 +65,12 @@
    ],
    "source": [
     "# import\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings.sentence_transformer import (\n",
     "    SentenceTransformerEmbeddings,\n",
     ")\n",
     "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "# load the document and split it into chunks\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",

docs/docs/integrations/vectorstores/clarifai.ipynb

@@ -79,9 +79,9 @@
    "outputs": [],
    "source": [
     "# Import the required modules\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.vectorstores import Clarifai"
+    "from langchain_community.vectorstores import Clarifai\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/clickhouse.ipynb

@@ -101,9 +101,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Clickhouse, ClickhouseSettings\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/dashvector.ipynb

@@ -101,9 +101,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.embeddings.dashscope import DashScopeEmbeddings\n",
-    "from langchain_community.vectorstores import DashVector"
+    "from langchain_community.vectorstores import DashVector\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/databricks_vector_search.ipynb

@@ -59,9 +59,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/dingo.ipynb

@@ -68,10 +68,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Dingo\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {
@@ -130,10 +130,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Dingo\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/docarray_hnsw.ipynb

@@ -73,10 +73,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import DocArrayHnswSearch\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/docarray_in_memory.ipynb

@@ -70,10 +70,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/elasticsearch.ipynb

@@ -216,8 +216,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/epsilla.ipynb

@@ -67,8 +67,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/faiss.ipynb

@@ -88,10 +88,10 @@
     "# Uncomment the following line if you need to initialize FAISS with no AVX2 optimization\n",
     "# os.environ['FAISS_NO_AVX2'] = '1'\n",
     "\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/faiss_async.ipynb

@@ -56,10 +56,10 @@
     "# Uncomment the following line if you need to initialize FAISS with no AVX2 optimization\n",
     "# os.environ['FAISS_NO_AVX2'] = '1'\n",
     "\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../../extras/modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/google_memorystore_redis.ipynb

@@ -184,8 +184,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"./state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/hippo.ipynb

@@ -97,10 +97,10 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores.hippo import Hippo\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/hologres.ipynb

@@ -33,9 +33,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Hologres\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/jaguar.ipynb

@@ -56,13 +56,13 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQAWithSourcesChain\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores.jaguar import Jaguar\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables import RunnablePassthrough\n",
     "from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "\"\"\" \n",
     "Load a text file into a set of documents \n",

docs/docs/integrations/vectorstores/kinetica.ipynb

@@ -114,14 +114,14 @@
    "outputs": [],
    "source": [
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import (\n",
     "    DistanceStrategy,\n",
     "    Kinetica,\n",
     "    KineticaSettings,\n",
     ")\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/lancedb.ipynb

@@ -104,7 +104,7 @@
    "outputs": [],
    "source": [
     "from langchain.document_loaders import TextLoader\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/lantern.ipynb

@@ -107,11 +107,11 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings import OpenAIEmbeddings\n",
     "from langchain_community.vectorstores import Lantern\n",
-    "from langchain_core.documents import Document"
+    "from langchain_core.documents import Document\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/marqo.ipynb

@@ -38,9 +38,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.vectorstores import Marqo"
+    "from langchain_community.vectorstores import Marqo\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/meilisearch.ipynb

@@ -126,9 +126,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Meilisearch\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"
    ]

docs/docs/integrations/vectorstores/milvus.ipynb

@@ -66,10 +66,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Milvus\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {
@@ -204,6 +204,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {
     "collapsed": false,
     "pycharm": {
@@ -221,6 +222,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
+   "id": "acae54e37e7d407bbb7b55eff062a284",
    "metadata": {
     "collapsed": false,
     "pycharm": {
@@ -246,6 +248,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "9a63283cbaf04dbcab1f6479b197f3a8",
    "metadata": {
     "collapsed": false,
     "pycharm": {
@@ -267,6 +270,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
+   "id": "8dd0d8092fe74a7c96281538738b07e2",
    "metadata": {
     "collapsed": false,
     "pycharm": {
@@ -295,6 +299,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
+   "id": "72eea5119410473aa328ad9291626812",
    "metadata": {
     "collapsed": false,
     "pycharm": {

docs/docs/integrations/vectorstores/momento_vector_index.ipynb

@@ -143,10 +143,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import MomentoVectorIndex\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/mongodb_atlas.ipynb

@@ -171,7 +171,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)\n",
     "docs = text_splitter.split_documents(data)"

docs/docs/integrations/vectorstores/myscale.ipynb

@@ -98,10 +98,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import MyScale\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/neo4jvector.ipynb

@@ -73,10 +73,10 @@
    "outputs": [],
    "source": [
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Neo4jVector\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/opensearch.ipynb

@@ -68,10 +68,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import OpenSearchVectorSearch\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/pgembedding.ipynb

@@ -82,10 +82,10 @@
    "outputs": [],
    "source": [
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import PGEmbedding\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/pgvecto_rs.ipynb

@@ -27,10 +27,10 @@
     "from typing import List\n",
     "\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings.fake import FakeEmbeddings\n",
-    "from langchain_community.vectorstores.pgvecto_rs import PGVecto_rs"
+    "from langchain_community.vectorstores.pgvecto_rs import PGVecto_rs\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/pgvector.ipynb

@@ -101,10 +101,10 @@
    "outputs": [],
    "source": [
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores.pgvector import PGVector\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/pinecone.ipynb

@@ -52,9 +52,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/qdrant.ipynb

@@ -78,10 +78,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Qdrant\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/rockset.ipynb

@@ -108,10 +108,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Rockset\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/sap_hanavector.ipynb

@@ -110,10 +110,10 @@
    "outputs": [],
    "source": [
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores.hanavector import HanaDB\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_documents = TextLoader(\"../../modules/state_of_the_union.txt\").load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",

docs/docs/integrations/vectorstores/scann.ipynb

@@ -59,10 +59,10 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import ScaNN\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/semadb.ipynb

@@ -61,8 +61,8 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/singlestoredb.ipynb

@@ -46,10 +46,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import SingleStoreDB\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/sklearn.ipynb

@@ -60,10 +60,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import SKLearnVectorStore\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/sqlitevss.ipynb

@@ -69,12 +69,12 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings.sentence_transformer import (\n",
     "    SentenceTransformerEmbeddings,\n",
     ")\n",
     "from langchain_community.vectorstores import SQLiteVSS\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "# load the document and split it into chunks\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
@@ -146,12 +146,12 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings.sentence_transformer import (\n",
     "    SentenceTransformerEmbeddings,\n",
     ")\n",
     "from langchain_community.vectorstores import SQLiteVSS\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "# load the document and split it into chunks\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",

docs/docs/integrations/vectorstores/starrocks.ipynb

@@ -58,7 +58,6 @@
    ],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import TokenTextSplitter\n",
     "from langchain_community.document_loaders import (\n",
     "    DirectoryLoader,\n",
     "    UnstructuredMarkdownLoader,\n",
@@ -66,6 +65,7 @@
     "from langchain_community.vectorstores import StarRocks\n",
     "from langchain_community.vectorstores.starrocks import StarRocksSettings\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters import TokenTextSplitter\n",
     "\n",
     "update_vectordb = False"
    ]

docs/docs/integrations/vectorstores/supabase.ipynb

@@ -183,8 +183,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",

docs/docs/integrations/vectorstores/surrealdb.ipynb

@@ -73,10 +73,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
-    "from langchain_community.vectorstores import SurrealDBStore"
+    "from langchain_community.vectorstores import SurrealDBStore\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/tair.ipynb

@@ -20,9 +20,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.embeddings.fake import FakeEmbeddings\n",
-    "from langchain_community.vectorstores import Tair"
+    "from langchain_community.vectorstores import Tair\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/tencentvectordb.ipynb

@@ -33,11 +33,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings.fake import FakeEmbeddings\n",
     "from langchain_community.vectorstores import TencentVectorDB\n",
-    "from langchain_community.vectorstores.tencentvectordb import ConnectionParams"
+    "from langchain_community.vectorstores.tencentvectordb import ConnectionParams\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/tigris.ipynb

@@ -85,10 +85,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Tigris\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/tiledb.ipynb

@@ -43,10 +43,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.embeddings import HuggingFaceEmbeddings\n",
     "from langchain_community.vectorstores import TileDB\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "raw_documents = TextLoader(\"../../modules/state_of_the_union.txt\").load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",

docs/docs/integrations/vectorstores/timescalevector.ipynb

@@ -123,11 +123,11 @@
     "from datetime import datetime, timedelta\n",
     "\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.document_loaders.json_loader import JSONLoader\n",
     "from langchain_community.vectorstores.timescalevector import TimescaleVector\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/typesense.ipynb

@@ -84,10 +84,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Typesense\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {

docs/docs/integrations/vectorstores/usearch.ipynb

@@ -55,10 +55,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import USearch\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {