如何按 tokens 拆分文本

语言模型具有 token 限制。你不应超过 token 限制。当你将文本拆分为块时，因此最好计算 token 的数量。有许多分词器。当你在文本中计算 token 时，你应该使用与语言模型中使用的分词器相同的分词器。

tiktoken

注意

tiktoken 是由 OpenAI 创建的快速 BPE 分词器。

我们可以使用 tiktoken 来估计使用的 token 数量。对于 OpenAI 模型，它可能会更准确。

文本如何拆分：按传入的字符拆分。
块大小如何测量：通过 tiktoken 分词器。

CharacterTextSplitter、RecursiveCharacterTextSplitter 和 TokenTextSplitter 可以直接与 tiktoken 一起使用。

%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()

API 参考:CharacterTextSplitter

要使用 CharacterTextSplitter 进行拆分，然后使用 tiktoken 合并块，请使用其 .from_tiktoken_encoder() 方法。请注意，此方法拆分的块可能大于 tiktoken 分词器测量的块大小。

.from_tiktoken_encoder() 方法接受 encoding_name 作为参数（例如 cl100k_base），或 model_name（例如 gpt-4）。所有其他参数（如 chunk_size、chunk_overlap 和 separators）都用于实例化 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.

为了对块大小实施硬性约束，我们可以使用 RecursiveCharacterTextSplitter.from_tiktoken_encoder，如果每个拆分块的大小过大，则会递归拆分。

from langchain_text_splitters import RecursiveCharacterTextSplitter

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

API 参考:RecursiveCharacterTextSplitter

我们还可以加载 TokenTextSplitter 分词器，它可以直接与 tiktoken 一起使用，并将确保每个拆分块都小于块大小。

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])

API 参考:TokenTextSplitter

Madam Speaker, Madam Vice President, our

某些书写语言（例如中文和日语）的字符编码为 2 个或更多 tokens。直接使用 TokenTextSplitter 可能会将字符的 tokens 拆分到两个块之间，从而导致 Unicode 字符格式错误。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

注意

spaCy 是一个用于高级自然语言处理的开源软件库，使用编程语言 Python 和 Cython 编写。

LangChain 实现了基于 spaCy 分词器的拆分器。

文本如何拆分：通过 spaCy 分词器。
块大小如何测量：按字符数。

%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])

API 参考:SpacyTextSplitter

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 是一个专门用于 sentence-transformer 模型的文本拆分器。默认行为是将文本拆分为适合你想要使用的 sentence transformer 模型的 token 窗口的块。

要根据 sentence-transformers 分词器拆分文本并约束 token 计数，请实例化一个 SentenceTransformersTokenTextSplitter。你可以选择指定

chunk_overlap：token 重叠的整数计数；
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 计数。

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)

API 参考:SentenceTransformersTokenTextSplitter

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

注意

自然语言工具包，或更常见的 NLTK，是一套用于符号和统计自然语言处理 (NLP) 的库和程序，用于用 Python 编程语言编写的英语。

与其仅仅在 "\n\n" 上拆分，我们可以使用 NLTK 基于 NLTK 分词器进行拆分。

文本如何拆分：通过 NLTK 分词器。
块大小如何测量：按字符数。

# 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)

API 参考:NLTKTextSplitter

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

注意

KoNLPy：Python 中的韩语 NLP 是一个用于韩语自然语言处理 (NLP) 的 Python 包。

Token 拆分涉及将文本分割成更小、更易于管理的单元，称为 tokens。这些 tokens 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的元素。在像英语这样的语言中，token 拆分通常涉及通过空格和标点符号分隔单词。token 拆分的有效性很大程度上取决于分词器对语言结构的理解，确保生成有意义的 tokens。由于为英语设计的分词器未配备理解其他语言（如韩语）的独特语义结构，因此它们不能有效地用于韩语处理。

使用 KoNLPy 的 Kkma 分析器进行韩语 token 拆分

对于韩语文本，KoNLPy 包括一个名为 Kkma（韩语知识语素分析器）的形态分析器。Kkma 提供了韩语文本的详细形态分析。它将句子分解为单词，并将单词分解为各自的语素，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 以其详细的分析而闻名，但重要的是要注意，这种精度可能会影响处理速度。因此，Kkma 最适合于分析深度优先于快速文本处理的应用。

# 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()

API 参考: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 有许多分词器。

我们使用 Hugging Face 分词器，GPT2TokenizerFast 来计算文本长度，单位为 tokens。

文本如何拆分：按传入的字符拆分。
块大小如何测量：通过 Hugging Face 分词器计算的 token 数量。

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

API 参考: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.

tiktoken​

spaCy​

SentenceTransformers​

NLTK​

KoNLPY​

使用 KoNLPy 的 Kkma 分析器进行韩语 token 拆分​

使用注意事项​

Hugging Face 分词器​

此页内容是否对您有帮助？