按 Token 分割 - 文本分割器集成指南 - LangChain LangGraph DeepAgent中文文档

语言模型有 token 限制，不应超过此限制。因此，当您将文本分割成块时，计算 token 数量是个好主意。有许多分词器可供选择。计算文本中的 token 时，应使用与语言模型相同的分词器。

tiktoken

tiktoken 是由 OpenAI 创建的快速 BPE 分词器。

我们可以使用 tiktoken 来估算使用的 token 数。对于 OpenAI 模型，它的估算通常更为准确。

文本如何分割：通过传入的字符。
块大小如何衡量：通过 tiktoken 分词器。

CharacterTextSplitter、RecursiveCharacterTextSplitter 和 TokenTextSplitter 均可直接与 tiktoken 配合使用。

pip install --upgrade --quiet langchain-text-splitters tiktoken

from langchain_text_splitters import CharacterTextSplitter

# This is a long document we can split up.
with open("state_of_the_union.txt") as f:
    state_of_the_union = f.read()

要使用 CharacterTextSplitter 分割并用 tiktoken 合并块，请使用其 .from_tiktoken_encoder() 方法。注意，此方法产生的分割块可能大于 tiktoken 分词器衡量的块大小。 .from_tiktoken_encoder() 方法接受 encoding_name 参数（如 cl100k_base）或 model_name 参数（如 gpt-4）。所有其他参数如 chunk_size、chunk_overlap 和 separators 用于实例化 CharacterTextSplitter：

text_splitter = CharacterTextSplitter.from_tiktoken_encoder(
    encoding_name="cl100k_base", chunk_size=100, chunk_overlap=0
)
texts = text_splitter.split_text(state_of_the_union)

print(texts[0])

Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.

Last year COVID-19 kept us apart. This year we are finally together again.

Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.

With a duty to one another to the American people to the Constitution.

要对块大小实施硬约束，可以使用 RecursiveCharacterTextSplitter.from_tiktoken_encoder，每个超出大小的分割块将被递归地再次分割：

from langchain_text_splitters import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    model_name="gpt-4",
    chunk_size=100,
    chunk_overlap=0,
)

我们也可以加载 TokenTextSplitter 分割器，它直接使用 tiktoken，并确保每个分割块都小于块大小。

from langchain_text_splitters import TokenTextSplitter

text_splitter = TokenTextSplitter(chunk_size=10, chunk_overlap=0)

texts = text_splitter.split_text(state_of_the_union)
print(texts[0])

Madam Speaker, Madam Vice President, our

某些书写语言（如中文和日文）的字符可能编码为两个或更多 token。直接使用 TokenTextSplitter 可能会将某个字符的 token 分割到两个块中，导致 Unicode 字符损坏。请使用 RecursiveCharacterTextSplitter.from_tiktoken_encoder 或 CharacterTextSplitter.from_tiktoken_encoder 以确保块包含有效的 Unicode 字符串。

spaCy

spaCy 是一个用 Python 和 Cython 编写的开源高级自然语言处理软件库。

LangChain 实现了基于 spaCy 分词器的分割器。

文本如何分割：通过 spaCy 分词器。
块大小如何衡量：通过字符数。

pip install --upgrade --quiet  spacy

# This is a long document we can split up.
with open("state_of_the_union.txt") as f:
    state_of_the_union = f.read()

from langchain_text_splitters import SpacyTextSplitter

text_splitter = SpacyTextSplitter(chunk_size=1000)

texts = text_splitter.split_text(state_of_the_union)
print(texts[0])

Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.

Members of Congress and the Cabinet.

Justices of the Supreme Court.

My fellow Americans.

Last year COVID-19 kept us apart.

This year we are finally together again.

Tonight, we meet as Democrats Republicans and Independents.

But most importantly as Americans.

With a duty to one another to the American people to the Constitution.

And with an unwavering resolve that freedom will always triumph over tyranny.

Six days ago, Russia's Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.

But he badly miscalculated.

He thought he could roll into Ukraine and the world would roll over.

Instead he met a wall of strength he never imagined.

He met the Ukrainian people.

From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.

SentenceTransformers

SentenceTransformersTokenTextSplitter 是专为 sentence-transformer 模型设计的文本分割器。默认行为是将文本分割为适合所选 sentence-transformer 模型 token 窗口的块。要根据 sentence-transformers 分词器分割文本并限制 token 数，请实例化 SentenceTransformersTokenTextSplitter。您可以选择指定：

chunk_overlap：token 重叠的整数数量；
model_name：sentence-transformer 模型名称，默认为 "sentence-transformers/all-mpnet-base-v2"；
tokens_per_chunk：每个块所需的 token 数量。

from langchain_text_splitters import SentenceTransformersTokenTextSplitter

splitter = SentenceTransformersTokenTextSplitter(chunk_overlap=0)
text = "Lorem "

count_start_and_stop_tokens = 2
text_token_count = splitter.count_tokens(text=text) - count_start_and_stop_tokens
print(text_token_count)

token_multiplier = splitter.maximum_tokens_per_chunk // text_token_count + 1

# `text_to_split` does not fit in a single chunk
text_to_split = text * token_multiplier

print(f"tokens in text to split: {splitter.count_tokens(text=text_to_split)}")

tokens in text to split: 514

text_chunks = splitter.split_text(text=text_to_split)

print(text_chunks[1])

lorem

NLTK

自然语言工具包，更常见的名称是 NLTK，是用 Python 编写的符号和统计自然语言处理（NLP）的库和程序套件。

我们不只是在 "\n\n" 处分割，还可以使用 NLTK 基于 NLTK 分词器进行分割。

文本如何分割：通过 NLTK 分词器。
块大小如何衡量：通过字符数。

# pip install nltk

# This is a long document we can split up.
with open("state_of_the_union.txt") as f:
    state_of_the_union = f.read()

from langchain_text_splitters import NLTKTextSplitter

text_splitter = NLTKTextSplitter(chunk_size=1000)

texts = text_splitter.split_text(state_of_the_union)
print(texts[0])

Madam Speaker, Madam Vice President, our First Lady and Second Gentleman.

Members of Congress and the Cabinet.

Justices of the Supreme Court.

My fellow Americans.

Last year COVID-19 kept us apart.

This year we are finally together again.

Tonight, we meet as Democrats Republicans and Independents.

But most importantly as Americans.

With a duty to one another to the American people to the Constitution.

And with an unwavering resolve that freedom will always triumph over tyranny.

Six days ago, Russia's Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways.

But he badly miscalculated.

He thought he could roll into Ukraine and the world would roll over.

Instead he met a wall of strength he never imagined.

He met the Ukrainian people.

From President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world.

Groups of citizens blocking tanks with their bodies.

KoNLPY

KoNLPy: Korean NLP in Python 是用于处理韩语自然语言处理（NLP）的 Python 包。

Token 分割包括将文本分割为更小、更易管理的单元（称为 token）。这些 token 通常是单词、短语、符号或其他对进一步处理和分析至关重要的有意义元素。在英语等语言中，token 分割通常涉及通过空格和标点符号分隔单词。token 分割的效果在很大程度上取决于分词器对语言结构的理解，从而确保生成有意义的 token。由于专为英语设计的分词器无法理解韩语等其他语言的独特语义结构，因此不能有效地用于韩语处理。

使用 KoNLPY 的 kkma 分析器进行韩语 Token 分割

对于韩语文本，KoNLPY 包含一个名为 Kkma（韩国知识形态分析器）的形态分析器。Kkma 对韩语文本提供详细的形态分析，将句子分解为单词，将单词分解为其各自的词素，并识别每个 token 的词性。它可以将一段文本分割成单独的句子，这对于处理长文本特别有用。

使用注意事项

虽然 Kkma 以其详细分析著称，但需要注意的是，这种精度可能影响处理速度。因此，Kkma 最适合那些注重分析深度而非快速文本处理的应用程序。

# pip install konlpy

# This is a long Korean document that we want to split up into its component sentences.
with open("./your_korean_doc.txt") as f:
    korean_document = f.read()

from langchain_text_splitters import KonlpyTextSplitter

text_splitter = KonlpyTextSplitter()

texts = text_splitter.split_text(korean_document)
# The sentences are split with "\n\n" characters.
print(texts[0])

춘향전 옛날에 남원에 이 도령이라는 벼슬아치 아들이 있었다.

그의 외모는 빛나는 달처럼 잘생겼고, 그의 학식과 기예는 남보다 뛰어났다.

한편, 이 마을에는 춘향이라는 절세 가인이 살고 있었다.

춘 향의 아름다움은 꽃과 같아 마을 사람들 로부터 많은 사랑을 받았다.

어느 봄날, 도령은 친구들과 놀러 나갔다가 춘 향을 만 나 첫 눈에 반하고 말았다.

두 사람은 서로 사랑하게 되었고, 이내 비밀스러운 사랑의 맹세를 나누었다.

하지만 좋은 날들은 오래가지 않았다.

도령의 아버지가 다른 곳으로 전근을 가게 되어 도령도 떠나 야만 했다.

이별의 아픔 속에서도, 두 사람은 재회를 기약하며 서로를 믿고 기다리기로 했다.

그러나 새로 부임한 관아의 사또가 춘 향의 아름다움에 욕심을 내 어 그녀에게 강요를 시작했다.

춘 향 은 도령에 대한 자신의 사랑을 지키기 위해, 사또의 요구를 단호히 거절했다.

이에 분노한 사또는 춘 향을 감옥에 가두고 혹독한 형벌을 내렸다.

이야기는 이 도령이 고위 관직에 오른 후, 춘 향을 구해 내는 것으로 끝난다.

두 사람은 오랜 시련 끝에 다시 만나게 되고, 그들의 사랑은 온 세상에 전해 지며 후세에까지 이어진다.

- 춘향전 (The Tale of Chunhyang)

Hugging Face 分词器

Hugging Face 提供许多分词器。我们使用 Hugging Face 分词器 GPT2TokenizerFast 来计算文本的 token 长度。

文本如何分割：通过传入的字符。
块大小如何衡量：通过 Hugging Face 分词器计算的 token 数。

from transformers import GPT2TokenizerFast

tokenizer = GPT2TokenizerFast.from_pretrained("gpt2")

# This is a long document we can split up.
with open("state_of_the_union.txt") as f:
    state_of_the_union = f.read()
from langchain_text_splitters import CharacterTextSplitter

text_splitter = CharacterTextSplitter.from_huggingface_tokenizer(
    tokenizer, chunk_size=100, chunk_overlap=0
)
texts = text_splitter.split_text(state_of_the_union)

print(texts[0])

Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.

Last year COVID-19 kept us apart. This year we are finally together again.

Tonight, we meet as Democrats Republicans and Independents. But most importantly as Americans.

With a duty to one another to the American people to the Constitution.

在 GitHub 上编辑此页面或提交问题。

连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。

Popular Providers

Integrations by component

按 Token 分割 - 文本分割器集成指南

tiktoken

spaCy

SentenceTransformers

NLTK

KoNLPY

使用 KoNLPY 的 kkma 分析器进行韩语 Token 分割

使用注意事项

Hugging Face 分词器

Popular Providers

Integrations by component

​tiktoken

​spaCy

​SentenceTransformers

​NLTK

​KoNLPY

​使用 KoNLPY 的 kkma 分析器进行韩语 Token 分割

​使用注意事项

​Hugging Face 分词器

tiktoken

spaCy

SentenceTransformers

NLTK

KoNLPY

使用 KoNLPY 的 kkma 分析器进行韩语 Token 分割

使用注意事项

Hugging Face 分词器