LangChain / RAG / Vector DBs · Урок

Настройка разбиения документов

Реализуйте продвинутые методы разбиения текста, включая семантическое разбиение и обработку кода или определённых структур данных.

«Настройка разбиения документов» — бесплатный урок LangChain / RAG / Vector DBs на CoddyKit. Это урок 3 из 4. Ты можешь прочитать весь урок бесплатно ниже — а потом практиковать его прямо в браузере с встроенным редактором кода и ИИ-репетитором 24/7. Это часть пути обучения LangChain / RAG / Vector DBs, и твой прогресс синхронизируется между веб-версией и приложением CoddyKit. Курс LangChain / RAG / Vector DBs содержит 4 уроков всего.

Части этого урока еще не переведены и отображаются на английском.

Why Customize Text Splitting?

When preparing documents for Retrieval Augmented Generation (RAG), how you split them into chunks is crucial. Basic text splitters are a good start, but they often fall short for complex or highly structured content.

Customizing your text splitting strategy allows you to maintain better contextual integrity, leading to more accurate retrievals and better LLM responses.

Tailoring Character Splitters

LangChain's CharacterTextSplitter is simple but powerful. You can customize it by providing specific separator characters. This is useful when your documents have unique delimiters you want to respect, like a specific tag or a unique line break pattern.

By defining your own separators, you can ensure logical breaks rather than arbitrary character counts.

from langchain.text_splitter import CharacterTextSplitter

class Main:
    def run(self):
        text = "Chapter 1: Intro.Section 1.1: Basics.Section 1.2: Advanced."
        # Custom separator is "."
        splitter = CharacterTextSplitter(
            separator=".",
            chunk_size=20,
            chunk_overlap=0
        )
        chunks = splitter.split_text(text)
        for i, chunk in enumerate(chunks):
            print(f"Chunk {i+1}: {chunk}")

if __name__ == "__main__":
    Main().run()

Refining Recursive Splitters

The RecursiveCharacterTextSplitter attempts to split text using a list of separators in order, trying to keep chunks as large as possible. You can customize this list to match your document's inherent structure.

For example, you might prioritize splitting by double newlines, then single newlines, then spaces, and finally characters.

from langchain.text_splitter import RecursiveCharacterTextSplitter

class Main:
    def run(self):
        text = "Hello there!\n\nThis is a paragraph.\nAnd this is another sentence."
        # Custom list of separators
        splitter = RecursiveCharacterTextSplitter(
            separators=["\n\n", "\n", " ", ""],
            chunk_size=40,
            chunk_overlap=0
        )
        chunks = splitter.split_text(text)
        for i, chunk in enumerate(chunks):
            print(f"Chunk {i+1}: {chunk}")

if __name__ == "__main__":
    Main().run()

Intro to Semantic Chunking

Instead of relying solely on character counts or delimiters, what if we could split text based on its meaning?

Semantic chunking aims to create chunks that represent complete, coherent ideas or topics. This method helps prevent important concepts from being arbitrarily split across different chunks, which often happens with fixed-size or simple character splitters.

How Semantic Chunking Works

Semantic chunking typically involves a few steps:

Embed Sentences: Each sentence or a small unit of text is converted into a vector embedding.
Measure Similarity: The semantic similarity between adjacent sentences or units is measured using their embeddings.
Identify Breakpoints: Chunks are formed where semantic similarity drops significantly, indicating a topic change or a shift in discussion.

While LangChain doesn't have a single 'semantic splitter' out-of-the-box, it's a pattern you can build using embedding models and custom logic.

Specialized Code Splitters

Code has a unique structure, with functions, classes, comments, and specific syntax. Generic text splitters often break code in awkward places, making the resulting chunks hard to understand or use as context for an LLM.

LangChain provides specialized splitters for different programming languages. These splitters understand the syntax of a language and ensure that chunks are syntactically meaningful, like keeping a whole function or class together.

Python Code Splitter Demo

The RecursiveCharacterTextSplitter.from_language method allows you to specify a programming language. It then uses language-specific separators (like class definitions, function definitions, etc.) to create more intelligent chunks.

This ensures that code snippets passed to an LLM are more coherent.

from langchain.text_splitter import RecursiveCharacterTextSplitter, Language

class Main:
    def run(self):
        python_code = """
def calculate_sum(a, b):
    # This function adds two numbers
    return a + b

class MyCalculator:
    def __init__(self):
        self.result = 0

    def add(self, num):
        self.result += num

if __name__ == "__main__":
    total = calculate_sum(5, 3)
    print(f"Sum: {total}")
    calc = MyCalculator()
    calc.add(10)
    print(f"Calc result: {calc.result}")
"""

        # Initialize splitter for Python code
        python_splitter = RecursiveCharacterTextSplitter.from_language(
            language=Language.PYTHON,
            chunk_size=100, # Adjust chunk size to see more splits
            chunk_overlap=0
        )

        docs = python_splitter.create_documents([python_code])

        for i, doc in enumerate(docs):
            print(f"--- Chunk {i+1} ---")
            print(doc.page_content)

if __name__ == "__main__":
    Main().run()

Beyond Code: Other Structures

LangChain also offers specialized splitters for other structured formats, not just code:

MarkdownTextSplitter: Understands Markdown syntax (headings, code blocks, lists) to create logically grouped chunks.
LatexTextSplitter: Recognizes LaTeX sections, chapters, and environments, preserving the document's academic structure.

These specialized splitters are invaluable for processing documents where the formatting itself conveys important structural information.

Creating Custom Splitter Logic

For truly unique document structures or proprietary data formats, you might need to implement your own splitting logic. LangChain allows you to:

Subclass TextSplitter: Create a new class that inherits from TextSplitter and overrides its methods to define custom splitting rules.
Write a custom function: Develop a function that takes your text and returns a list of chunks based on your specific parsing requirements.

This approach offers maximum flexibility to handle complex regex patterns, custom delimiters, or nested structures unique to your dataset.

Check Your Understanding

You've learned about various ways to customize text splitting for different document types. Let's test your knowledge.

Custom Splitting Recap

In this lesson, we explored how to go beyond basic text splitting to handle diverse and complex document types more effectively:

We customized Character and Recursive Character splitters with specific lists of separators.
We introduced the concept of Semantic Chunking for meaning-based splits.
We learned about Language-specific splitters for code (e.g., Python, Java) and other structured formats like Markdown and LaTeX.
Finally, we discussed the power and flexibility of creating entirely custom splitting logic for unique data.

Mastering customized splitting strategies is a critical step in building accurate and robust RAG applications.

Часто задаваемые вопросы

Урок «Настройка разбиения документов» бесплатный?

Да — полный текст урока «Настройка разбиения документов» бесплатно доступен здесь в веб-версии. Чтобы практиковать его интерактивно (встроенный редактор кода и ИИ-репетитор 24/7) и разблокировать остальной курс LangChain / RAG / Vector DBs, подпишись на CoddyKit PRO. Курс LangChain / RAG / Vector DBs содержит 4 уроков всего.

Чему я научусь в уроке «Настройка разбиения документов»?

Реализуйте продвинутые методы разбиения текста, включая семантическое разбиение и обработку кода или определённых структур данных. Ты практикуешь LangChain / RAG / Vector DBs с помощью реального кода, который запускаешь прямо в браузере, и ИИ-репетитор 24/7 отвечает на твои вопросы во время урока.

Нужен ли мне опыт, чтобы начать LangChain / RAG / Vector DBs?

Предыдущий опыт не требуется. LangChain / RAG / Vector DBs на CoddyKit структурирован для всех уровней — от новичков до продвинутых, поэтому ты можешь начать отсюда или с самого начала и учиться в своем темпе. Это урок 3 из 4.

Сколько времени занимает урок «Настройка разбиения документов»?

Большинство уроков CoddyKit занимают около 5–10 минут. Каждый из них компактный и интерактивный, поэтому ты постоянно делаешь прогресс и продолжаешь с того же места в веб-версии и приложении.

Можно ли писать и запускать код в этом уроке LangChain / RAG / Vector DBs?

Да. Каждый урок LangChain / RAG / Vector DBs включает встроенный редактор кода, поэтому ты пишешь и запускаешь реальный код прямо в браузере и получаешь моментальную обратную связь от AI — локальная установка не требуется.

Все уроки этого курса

Загрузка различных типов документов
Стратегии разбиения текста
Настройка разбиения документов
Работа с метаданными документов и фильтрация

← Назад к LangChain / RAG / Vector DBs