如何按标记分割文本

语言模型有 标记 限制。你不应超过标记限制。当你将文本 分割成块 时，最好统计标记数量。有许多标记器。当你统计文本中的标记数量时，应使用与语言模型相同的标记器。

tiktoken

笔记

tiktoken 是由 OpenAI 创建的快速 BPE 分词器。

我们可以使用 tiktoken 来估算使用的标记数。对于 OpenAI 模型来说，这可能更加准确。

1. 文本如何分割：通过传入的字符进行分割。
2. 块大小的测量方式：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

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，此方法产生的拆分块可能比由 tiktoken 分词器测量的块大小更大。

.from_tiktoken_encoder() 方法接受 encoding_name 作为参数（例如 cl100k_base），或者接受 model_name（例如 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.

要对块大小施加硬性约束，我们可以使用 RecursiveCharacterTextSplitter.from_tiktoken_encoder，此时如果某个分块的大小超过指定值，将递归地继续分割：

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

我们还可以加载一个 TokenTextSplitter 分割器，它可以直接与 tiktoken 一起使用，并确保每个分割部分都小于块大小。

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

一些书写语言（例如中文和日文）的字符会编码为两个或多个标记。直接使用 TokenTextSplitter 可能会导致一个字符的标记被分割到两个块中，从而造成无效的Unicode字符。使用 RecursiveCharacterTextSplitter.from_tiktoken_encoder 或 CharacterTextSplitter.from_tiktoken_encoder 可确保每个块包含有效的Unicode字符串。

spaCy

笔记

spaCy 是一个开源的软件库，用于高级自然语言处理，使用 Python 和 Cython 编程语言编写。

LangChain 基于 spaCy 分词器 实现拆分器。

1. 文本是如何分割的：通过 spaCy 分词器。
2. 块大小的度量方式：按字符数量计算。

%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 是专为 sentence-transformer 模型设计的文本分割器。默认行为是将文本分割成适合您想要使用的 sentence-transformer 模型的标记窗口大小的块。

为了根据 sentence-transformers 分词器拆分文本并限制标记数量，请实例化一个 SentenceTransformersTokenTextSplitter。您可以选择性地指定：

• chunk_overlap: 令牌重叠的整数计数；
• model_name: sentence-transformer 模型名称，默认为 "sentence-transformers/all-mpnet-base-v2";
• tokens_per_chunk: 每个块所需的标记数量。

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)

API 参考：SentenceTransformersTokenTextSplitter

2

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

笔记

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

与其仅按 "\n\n" 进行分割，我们可以使用 NLTK 根据 NLTK 分词器 进行分割。

1. 文本是如何分割的：通过 NLTK 分词器。
2. 块大小的度量方式：按字符数量计算。

# 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

笔记

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

令牌分割是指将文本分割成更小、更易处理的单元，称为令牌。这些令牌通常是单词、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，令牌分割通常涉及通过空格和标点符号来分隔单词。令牌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，以确保生成有意义的令牌。由于专为英语设计的分词器无法理解其他语言（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分析器对韩语进行分词

如果是韩语文本，KoNLPY 包含一个名为 Kkma（韩国知识词素分析器）的形态分析器。Kkma 提供韩语文本的详细形态分析。它将句子分解为单词，再将单词分解为其相应的词素，并为每个标记识别词性。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，但需要注意的是，这种精度可能会影响处理速度。因此，Kkma 最适合那些更注重分析深度而非快速文本处理的应用场景。

# 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，即 GPT2TokenizerFast 来计算文本的标记长度。

1. 文本如何分割：通过传入的字符进行分割。
2. 块大小的衡量方式：通过 Hugging Face 分词器计算的标记（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.