代码文本分割器集成指南

RecursiveCharacterTextSplitter 包含预构建的分隔符列表，这些列表对于按特定编程语言分割文本非常有用。支持的语言保存在 SupportedTextSplitterLanguages 类型中。它们包括：

"cpp",
"go",
"java",
"js",
"php",
"proto",
"python",
"rst",
"ruby",
"rust",
"scala",
"swift",
"markdown",
"latex",
"html",
"sol",

要查看给定语言的分隔符列表，请将此枚举中的一个值传递给

RecursiveCharacterTextSplitter.getSeparatorsForLanguage()

要实例化一个针对特定语言定制的分割器，请将此枚举中的一个值传递给

RecursiveCharacterTextSplitter.fromLanguage()

下面我们展示各种语言的示例。

npm install @langchain/textsplitters

pnpm install @langchain/textsplitters

yarn add @langchain/textsplitters

bun add @langchain/textsplitters

Python

这是一个使用 Python 文本分割器的示例：

const pythonSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "python",
    { chunkSize: 50, chunkOverlap: 0 }
);
const pythonDocs = pythonSplitter.createDocuments([{ pageContent: PYTHON_CODE }]);
console.log(pythonDocs);

[
    Document { metadata: {}, pageContent: 'def hello_world():\n    print("Hello, World!")' },
    Document { metadata: {}, pageContent: '# Call the function\nhello_world()' }
]

JS

这是一个使用 JS 文本分割器的示例：

const JS_CODE = `
function helloWorld() {
  console.log("Hello, World!");
}

// Call the function
helloWorld();
`;

const jsSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "js",
    { chunkSize: 60, chunkOverlap: 0 }
);
const jsDocs = jsSplitter.createDocuments([{ pageContent: JS_CODE }]);
console.log(jsDocs);

[
    Document { metadata: {}, pageContent: 'function helloWorld() {\n  console.log("Hello, World!");\n}' },
    Document { metadata: {}, pageContent: '// Call the function\nhelloWorld()' }
]

TS

这是一个使用 TypeScript 文本分割器的示例：

const TS_CODE = `
function helloWorld(): void {
  console.log("Hello, World!");
}

// Call the function
helloWorld();
`;

const tsSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "ts",
    { chunkSize: 60, chunkOverlap: 0 }
);
const tsDocs = tsSplitter.createDocuments([{ pageContent: TS_CODE }]);
console.log(tsDocs);

[
    Document { metadata: {}, pageContent: 'function helloWorld(): void {' },
    Document { metadata: {}, pageContent: 'console.log("Hello, World!");\n}' },
    Document { metadata: {}, pageContent: '// Call the function\nhelloWorld()' }
]

Markdown

这是一个使用 Markdown 文本分割器的示例：

const markdownText = `
# 🦜️🔗 LangChain

⚡ Building applications with LLMs through composability ⚡

## What is LangChain?

# Hopefully this code block isn't split
LangChain is a framework for...

As an open-source project in a rapidly developing field, we are extremely open to contributions.
`;

const mdSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "markdown",
    { chunkSize: 60, chunkOverlap: 0 }
);
const mdDocs = mdSplitter.createDocuments([ markdownText ]);
console.log(mdDocs);

[
    Document { metadata: {}, pageContent: '# 🦜️🔗 LangChain' },
    Document { metadata: {}, pageContent: '⚡ Building applications with LLMs through composability ⚡' },
    Document { metadata: {}, pageContent: '## What is LangChain?' },
    Document { metadata: {}, pageContent: "# Hopefully this code block isn't split" },
    Document { metadata: {}, pageContent: 'LangChain is a framework for...' },
    Document { metadata: {}, pageContent: 'As an open-source project in a rapidly developing field, we' },
    Document { metadata: {}, pageContent: 'are extremely open to contributions.' }
]

Latex

这是一个关于 Latex 文本的示例：

const latexText = `
\\documentclass{article}

\\begin{document}

\\maketitle

\\section{Introduction}
Large language models (LLMs) are a type of machine learning model that can be trained on vast amounts of text data to generate human-like language. In recent years, LLMs have made significant advances in a variety of natural language processing tasks, including language translation, text generation, and sentiment analysis.

\\subsection{History of LLMs}
The earliest LLMs were developed in the 1980s and 1990s, but they were limited by the amount of data that could be processed and the computational power available at the time. In the past decade, however, advances in hardware and software have made it possible to train LLMs on massive datasets, leading to significant improvements in performance.

\\subsection{Applications of LLMs}
LLMs have many applications in industry, including chatbots, content creation, and virtual assistants. They can also be used in academia for research in linguistics, psychology, and computational linguistics.

\\end{document}
`;

const latexSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "latex",
    { chunkSize: 60, chunkOverlap: 0 }
);
const latexDocs = latexSplitter.createDocuments([{ pageContent: latexText }]);
console.log(latexDocs);

[
    Document { metadata: {}, pageContent: '\\documentclass{article}\n\n\\begin{document}\n\n\\maketitle' },
    Document { metadata: {}, pageContent: '\\section{Introduction}' },
    Document { metadata: {}, pageContent: 'Large language models (LLMs) are a type of machine learning' },
    Document { metadata: {}, pageContent: 'model that can be trained on vast amounts of text data to' },
    Document { metadata: {}, pageContent: 'generate human-like language. In recent years, LLMs have' },
    Document { metadata: {}, pageContent: 'made significant advances in a variety of natural language' },
    Document { metadata: {}, pageContent: 'processing tasks, including language translation, text' },
    Document { metadata: {}, pageContent: 'generation, and sentiment analysis.' },
    Document { metadata: {}, pageContent: '\\subsection{History of LLMs}' },
    Document { metadata: {}, pageContent: 'The earliest LLMs were developed in the 1980s and 1990s,' },
    Document { metadata: {}, pageContent: 'but they were limited by the amount of data that could be' },
    Document { metadata: {}, pageContent: 'processed and the computational power available at the' },
    Document { metadata: {}, pageContent: 'time. In the past decade, however, advances in hardware and' },
    Document { metadata: {}, pageContent: 'software have made it possible to train LLMs on massive' },
    Document { metadata: {}, pageContent: 'datasets, leading to significant improvements in' },
    Document { metadata: {}, pageContent: 'performance.' },
    Document { metadata: {}, pageContent: '\\subsection{Applications of LLMs}' },
    Document { metadata: {}, pageContent: 'LLMs have many applications in industry, including' },
    Document { metadata: {}, pageContent: 'chatbots, content creation, and virtual assistants. They' },
    Document { metadata: {}, pageContent: 'can also be used in academia for research in linguistics,' },
    Document { metadata: {}, pageContent: 'psychology, and computational linguistics.' },
    Document { metadata: {}, pageContent: '\\end{document}' }
]

HTML

这是一个使用 HTML 文本分割器的示例：

const htmlText = `
<!DOCTYPE html>
<html>
    <head>
        <title>🦜️🔗 LangChain</title>
        <style>
            body {
                font-family: Arial, sans-serif;
            }
            h1 {
                color: darkblue;
            }
        </style>
    </head>
    <body>
        <div>
            <h1>🦜️🔗 LangChain</h1>
            <p>⚡ Building applications with LLMs through composability ⚡</p>
        </div>
        <div>
            As an open-source project in a rapidly developing field, we are extremely open to contributions.
        </div>
    </body>
</html>
`;

const htmlSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "html",
    { chunkSize: 60, chunkOverlap: 0 }
);
const htmlDocs = htmlSplitter.createDocuments([{ pageContent: htmlText }]);
console.log(htmlDocs);

[
    Document { metadata: {}, pageContent: '<!DOCTYPE html>\n<html>' },
    Document { metadata: {}, pageContent: '<head>\n        <title>🦜️🔗 LangChain</title>' },
    Document { metadata: {}, pageContent: '<style>\n            body {\n                font-family: Aria' },
    Document { metadata: {}, pageContent: 'l, sans-serif;\n            }\n            h1 {' },
    Document { metadata: {}, pageContent: 'color: darkblue;\n            }\n        </style>\n    </head' },
    Document { metadata: {}, pageContent: '>' },
    Document { metadata: {}, pageContent: '<body>' },
    Document { metadata: {}, pageContent: '<div>\n            <h1>🦜️🔗 LangChain</h1>' },
    Document { metadata: {}, pageContent: '<p>⚡ Building applications with LLMs through composability ⚡' },
    Document { metadata: {}, pageContent: '</p>\n        </div>' },
    Document { metadata: {}, pageContent: '<div>\n            As an open-source project in a rapidly dev' },
    Document { metadata: {}, pageContent: 'eloping field, we are extremely open to contributions.' },
    Document { metadata: {}, pageContent: '</div>\n    </body>\n</html>' }
]

Solidity

这是一个使用 Solidity 文本分割器的示例：

const SOL_CODE = `
pragma solidity ^0.8.20;
contract HelloWorld {
   function add(uint a, uint b) pure public returns(uint) {
       return a + b;
   }
}
`;

const solSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "sol",
    { chunkSize: 128, chunkOverlap: 0 }
);
const solDocs = solSplitter.createDocuments([{ pageContent: SOL_CODE }]);
console.log(solDocs);

[
    Document { metadata: {}, pageContent: 'pragma solidity ^0.8.20;' },
    Document { metadata: {}, pageContent: 'contract HelloWorld {\n   function add(uint a, uint b) pure public returns(uint) {\n       return a + b;\n   }\n}' }
]

C#

这是一个使用 C# 文本分割器的示例：

const C_CODE = `
using System;
class Program
{
    static void Main()
    {
        int age = 30; // Change the age value as needed

        // Categorize the age without any console output
        if (age < 18)
        {
            // Age is under 18
        }
        else if (age >= 18 && age < 65)
        {
            // Age is an adult
        }
        else
        {
            // Age is a senior citizen
        }
    }
}
`;

const csharpSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "csharp",
    { chunkSize: 128, chunkOverlap: 0 }
);
const csharpDocs = csharpSplitter.createDocuments([{ pageContent: C_CODE }]);
console.log(csharpDocs);

[
    Document { metadata: {}, pageContent: 'using System;' },
    Document { metadata: {}, pageContent: 'class Program\n{\n    static void Main()\n    {\n        int age = 30; // Change the age value as needed' },
    Document { metadata: {}, pageContent: '// Categorize the age without any console output\n        if (age < 18)\n        {\n            // Age is under 18' },
    Document { metadata: {}, pageContent: '}\n        else if (age >= 18 && age < 65)\n        {\n            // Age is an adult\n        }\n        else\n        {' },
    Document { metadata: {}, pageContent: '// Age is a senior citizen\n        }\n    }\n}' }
]

Haskell

这是一个使用 Haskell 文本分割器的示例：

const HASKELL_CODE = `
main :: IO ()
main = do
    putStrLn "Hello, World!"
-- Some sample functions
add :: Int -> Int -> Int
add x y = x + y
`;

const haskellSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "haskell",
    { chunkSize: 50, chunkOverlap: 0 }
);
const haskellDocs = haskellSplitter.createDocuments([{ pageContent: HASKELL_CODE }]);
console.log(haskellDocs);

[
    Document { metadata: {}, pageContent: 'main :: IO ()' },
    Document { metadata: {}, pageContent: 'main = do\n    putStrLn "Hello, World!"\n-- Some' },
    Document { metadata: {}, pageContent: 'sample functions\nadd :: Int -> Int -> Int\nadd x y' },
    Document { metadata: {}, pageContent: '= x + y' }
]

PHP

这是一个使用 PHP 文本分割器的示例：

const PHP_CODE = `<?php
namespace foo;
class Hello {
    public function __construct() { }
}
function hello() {
    echo "Hello World!";
}
interface Human {
    public function breath();
}
trait Foo { }
enum Color
{
    case Red;
    case Blue;
}`;

const phpSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "php",
    { chunkSize: 50, chunkOverlap: 0 }
);
const phpDocs = phpSplitter.createDocuments([{ pageContent: PHP_CODE }]);
console.log(phpDocs);

[
    Document { metadata: {}, pageContent: '<?php\nnamespace foo;' },
    Document { metadata: {}, pageContent: 'class Hello {' },
    Document { metadata: {}, pageContent: 'public function __construct() { }\n}' },
    Document { metadata: {}, pageContent: 'function hello() {\n    echo "Hello World!";\n}' },
    Document { metadata: {}, pageContent: 'interface Human {\n    public function breath();\n}' },
    Document { metadata: {}, pageContent: 'trait Foo { }\nenum Color\n{\n    case Red;' },
    Document { metadata: {}, pageContent: 'case Blue;\n}' }
]

PowerShell

这是一个使用 PowerShell 文本分割器的示例：

const POWERSHELL_CODE = `
$directoryPath = Get-Location

$items = Get-ChildItem -Path $directoryPath

$files = $items | Where-Object { -not $_.PSIsContainer }

$sortedFiles = $files | Sort-Object LastWriteTime

foreach ($file in $sortedFiles) {
    Write-Output ("Name: " + $file.Name + " | Last Write Time: " + $file.LastWriteTime)
}
`;

const powershellSplitter = RecursiveCharacterTextSplitter.fromLanguage(
    "powershell",
    { chunkSize: 100, chunkOverlap: 0 }
);
const powershellDocs = powershellSplitter.createDocuments([{ pageContent: POWERSHELL_CODE }]);
console.log(powershellDocs);

[
    Document { metadata: {}, pageContent: '$directoryPath = Get-Location\n\n$items = Get-ChildItem -Path $directoryPath' },
    Document { metadata: {}, pageContent: '$files = $items | Where-Object { -not $_.PSIsContainer }' },
    Document { metadata: {}, pageContent: '$sortedFiles = $files | Sort-Object LastWriteTime' },
    Document { metadata: {}, pageContent: 'foreach ($file in $sortedFiles) {' },
    Document { metadata: {}, pageContent: 'Write-Output ("Name: " + $file.Name + " | Last Write Time: " + $file.LastWriteTime)\n}' }
]

Visual basic 6

const VISUALBASIC6_CODE = `Option Explicit

Public Sub HelloWorld()
    MsgBox "Hello, World!"
End Sub

Private Function Add(a As Integer, b As Integer) As Integer
    Add = a + b
End Function
`;

const visualbasic6Splitter = RecursiveCharacterTextSplitter.fromLanguage(
    "visualbasic6",
    { chunkSize: 128, chunkOverlap: 0 }
);
const visualbasic6Docs = visualbasic6Splitter.createDocuments([{ pageContent: VISUALBASIC6_CODE }]);
console.log(visualbasic6Docs);

[
    Document { metadata: {}, pageContent: 'Option Explicit' },
    Document { metadata: {}, pageContent: 'Public Sub HelloWorld()\n    MsgBox "Hello, World!"\nEnd Sub' },
    Document { metadata: {}, pageContent: 'Private Function Add(a As Integer, b As Integer) As Integer\n    Add = a + b\nEnd Function' }
]

将这些文档连接到 Claude、VSCode 等，通过 MCP 获取实时答案。

在 GitHub 上编辑此页面或提交问题。

Popular Providers

General integrations

RAG integrations

代码文本分割器集成指南

Python

JS

TS

Markdown

Latex

HTML

Solidity

C#

Haskell

PHP

PowerShell

Visual basic 6

​Python

​JS

​TS

​Markdown

​Latex

​HTML

​Solidity

​C#

​Haskell

​PHP

​PowerShell

​Visual basic 6

Python

JS

TS

Markdown

Latex

HTML

Solidity

C#

Haskell

PHP

PowerShell

Visual basic 6