代码拆分

"cpp",
"go",
"java",
"kotlin",
"js",
"ts",
"php",
"proto",
"python",
"rst",
"ruby",
"rust",
"scala",
"swift",
"markdown",
"latex",
"html",
"sol",
"csharp",
"cobol",
"c",
"lua",
"perl",
"haskell"

RecursiveCharacterTextSplitter.get_separators_for_language

RecursiveCharacterTextSplitter.from_language

pip install -qU langchain-text-splitters

from langchain_text_splitters import (
    Language,
    RecursiveCharacterTextSplitter,
)

[e.value for e in Language]

['cpp',
 'go',
 'java',
 'kotlin',
 'js',
 'ts',
 'php',
 'proto',
 'python',
 'rst',
 'ruby',
 'rust',
 'scala',
 'swift',
 'markdown',
 'latex',
 'html',
 'sol',
 'csharp',
 'cobol',
 'c',
 'lua',
 'perl',
 'haskell',
 'elixir',
 'powershell',
 'visualbasic6']

RecursiveCharacterTextSplitter.get_separators_for_language(Language.PYTHON)

['\nclass ', '\ndef ', '\n\tdef ', '\n\n', '\n', ' ', '']

PYTHON_CODE = """
def hello_world():
    print("Hello, World!")

# Call the function
hello_world()
"""
python_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.PYTHON, chunk_size=50, chunk_overlap=0
)
python_docs = python_splitter.create_documents([PYTHON_CODE])
python_docs

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

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

// Call the function
helloWorld();
"""

js_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.JS, chunk_size=60, chunk_overlap=0
)
js_docs = js_splitter.create_documents([JS_CODE])
js_docs

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

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

// Call the function
helloWorld();
"""

ts_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.TS, chunk_size=60, chunk_overlap=0
)
ts_docs = ts_splitter.create_documents([TS_CODE])
ts_docs

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

markdown_text = """
# 🦜️🔗 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.
"""

md_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.MARKDOWN, chunk_size=60, chunk_overlap=0
)
md_docs = md_splitter.create_documents([markdown_text])
md_docs

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

latex_text = """
\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}
"""

latex_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.MARKDOWN, chunk_size=60, chunk_overlap=0
)
latex_docs = latex_splitter.create_documents([latex_text])
latex_docs

[Document(metadata={}, page_content='\\documentclass{article}\n\n\x08egin{document}\n\n\\maketitle'),
 Document(metadata={}, page_content='\\section{Introduction}'),
 Document(metadata={}, page_content='Large language models (LLMs) are a type of machine learning'),
 Document(metadata={}, page_content='model that can be trained on vast amounts of text data to'),
 Document(metadata={}, page_content='generate human-like language. In recent years, LLMs have'),
 Document(metadata={}, page_content='made significant advances in a variety of natural language'),
 Document(metadata={}, page_content='processing tasks, including language translation, text'),
 Document(metadata={}, page_content='generation, and sentiment analysis.'),
 Document(metadata={}, page_content='\\subsection{History of LLMs}'),
 Document(metadata={}, page_content='The earliest LLMs were developed in the 1980s and 1990s,'),
 Document(metadata={}, page_content='but they were limited by the amount of data that could be'),
 Document(metadata={}, page_content='processed and the computational power available at the'),
 Document(metadata={}, page_content='time. In the past decade, however, advances in hardware and'),
 Document(metadata={}, page_content='software have made it possible to train LLMs on massive'),
 Document(metadata={}, page_content='datasets, leading to significant improvements in'),
 Document(metadata={}, page_content='performance.'),
 Document(metadata={}, page_content='\\subsection{Applications of LLMs}'),
 Document(metadata={}, page_content='LLMs have many applications in industry, including'),
 Document(metadata={}, page_content='chatbots, content creation, and virtual assistants. They'),
 Document(metadata={}, page_content='can also be used in academia for research in linguistics,'),
 Document(metadata={}, page_content='psychology, and computational linguistics.'),
 Document(metadata={}, page_content='\\end{document}')]

html_text = """
<!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>
"""

html_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.HTML, chunk_size=60, chunk_overlap=0
)
html_docs = html_splitter.create_documents([html_text])
html_docs

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

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

sol_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.SOL, chunk_size=128, chunk_overlap=0
)
sol_docs = sol_splitter.create_documents([SOL_CODE])
sol_docs

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

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
        }
    }
}
"""
c_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.CSHARP, chunk_size=128, chunk_overlap=0
)
c_docs = c_splitter.create_documents([C_CODE])
c_docs

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

HASKELL_CODE = """
main :: IO ()
main = do
    putStrLn "Hello, World!"
-- Some sample functions
add :: Int -> Int -> Int
add x y = x + y
"""
haskell_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.HASKELL, chunk_size=50, chunk_overlap=0
)
haskell_docs = haskell_splitter.create_documents([HASKELL_CODE])
haskell_docs

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

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;
}"""
php_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.PHP, chunk_size=50, chunk_overlap=0
)
php_docs = php_splitter.create_documents([PHP_CODE])
php_docs

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

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)
}
"""
powershell_splitter = RecursiveCharacterTextSplitter.from_language(
    language=Language.POWERSHELL, chunk_size=100, chunk_overlap=0
)
powershell_docs = powershell_splitter.create_documents([POWERSHELL_CODE])
powershell_docs

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

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
"""
visualbasic6_splitter = RecursiveCharacterTextSplitter.from_language(
    Language.VISUALBASIC6,
    chunk_size=128,
    chunk_overlap=0,
)
visualbasic6_docs = visualbasic6_splitter.create_documents([VISUALBASIC6_CODE])
visualbasic6_docs

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