.큰 덩어리()

그만큼.chunk()기능은 전략과 옵션을 사용하여 문서를 더 작은 세그먼트로 분할합니다.

예

import { MDocument } from '@mastra/rag'

const doc = MDocument.fromMarkdown(`
# Introduction
This is a sample document that we want to split into chunks.

## Section 1
Here is the first section with some content.

## Section 2 
Here is another section with different content.
`)

// Basic chunking with defaults
const chunks = await doc.chunk()

// Markdown-specific chunking with header extraction
const chunksWithMetadata = await doc.chunk({
  strategy: 'markdown',
  headers: [
    ['#', 'title'],
    ['##', 'section'],
  ],
  extract: {
    summary: true, // Extract summaries with default settings
    keywords: true, // Extract keywords with default settings
  },
})

매개변수

모든 청킹 전략에 다음 매개변수를 사용할 수 있습니다. 각 전략은 특정 사용 사례와 관련된 이러한 매개변수의 하위 집합만 활용합니다.

strategy?:

'recursive' | 'character' | 'token' | 'markdown' | 'semantic-markdown' | 'html' | 'json' | 'latex' | 'sentence'

The chunking strategy to use. If not specified, defaults based on document type. Depending on the chunking strategy, there are additional optionals. Defaults: .md files → 'markdown', .html/.htm → 'html', .json → 'json', .tex → 'latex', others → 'recursive'

maxSize?:

number

= 4000

Maximum size of each chunk. Some strategy configurations (markdown with headers, HTML with headers) ignore this parameter.

overlap?:

number

= 50

Number of characters/tokens that overlap between chunks.

lengthFunction?:

(text: string) => number

Function to calculate text length. Defaults to character count.

separatorPosition?:

'start' | 'end'

Where to position the separator in chunks. 'start' attaches to beginning of next chunk, 'end' attaches to end of current chunk. If not specified, separators are discarded.

addStartIndex?:

boolean

= false

Whether to add start index metadata to chunks.

stripWhitespace?:

boolean

= true

Whether to strip whitespace from chunks.

extract?:

ExtractParams

Metadata extraction configuration.

보다ExtractParams reference for details on the extract parameter.

전략별 옵션

전략별 옵션은 전략 매개변수와 함께 최상위 매개변수로 전달됩니다. 예를 들어:

// Character strategy example
const chunks = await doc.chunk({
  strategy: 'character',
  separator: '.', // Character-specific option
  isSeparatorRegex: false, // Character-specific option
  maxSize: 300, // general option
})

// Recursive strategy example
const chunks = await doc.chunk({
  strategy: 'recursive',
  separators: ['\n\n', '\n', ' '], // Recursive-specific option
  language: 'markdown', // Recursive-specific option
  maxSize: 500, // general option
})

// Sentence strategy example
const chunks = await doc.chunk({
  strategy: 'sentence',
  maxSize: 450, // Required for sentence strategy
  minSize: 50, // Sentence-specific option
  sentenceEnders: ['.'], // Sentence-specific option
  fallbackToCharacters: false, // Sentence-specific option
})

// HTML strategy example
const chunks = await doc.chunk({
  strategy: 'html',
  headers: [
    ['h1', 'title'],
    ['h2', 'subtitle'],
  ], // HTML-specific option
})

// Markdown strategy example
const chunks = await doc.chunk({
  strategy: 'markdown',
  headers: [
    ['#', 'title'],
    ['##', 'section'],
  ], // Markdown-specific option
  stripHeaders: true, // Markdown-specific option
})

// Semantic Markdown strategy example
const chunks = await doc.chunk({
  strategy: 'semantic-markdown',
  joinThreshold: 500, // Semantic Markdown-specific option
  modelName: 'gpt-3.5-turbo', // Semantic Markdown-specific option
})

// Token strategy example
const chunks = await doc.chunk({
  strategy: 'token',
  encodingName: 'gpt2', // Token-specific option
  modelName: 'gpt-3.5-turbo', // Token-specific option
  maxSize: 1000, // general option
})

아래에 설명된 옵션은 별도의 옵션 개체 내에 중첩되지 않고 구성 개체의 최상위 수준에서 직접 전달됩니다.

성격

separators?:

string[]

Array of separators to try in order of preference. The strategy will attempt to split on the first separator, then fall back to subsequent ones.

isSeparatorRegex?:

boolean

= false

Whether the separator is a regex pattern

재귀적

separators?:

string[]

Array of separators to try in order of preference. The strategy will attempt to split on the first separator, then fall back to subsequent ones.

isSeparatorRegex?:

boolean

= false

Whether the separators are regex patterns

language?:

Language

Programming or markup language for language-specific splitting behavior. See Language enum for supported values.

문장

maxSize:

number

Maximum size of each chunk (required for sentence strategy)

minSize?:

number

= 50

Minimum size of each chunk. Chunks smaller than this will be merged with adjacent chunks when possible.

targetSize?:

number

Preferred target size for chunks. Defaults to 80% of maxSize. The strategy will try to create chunks close to this size.

sentenceEnders?:

string[]

= ['.', '!', '?']

Array of characters that mark sentence endings for splitting boundaries.

fallbackToWords?:

boolean

= true

Whether to fall back to word-level splitting for sentences that exceed maxSize.

fallbackToCharacters?:

boolean

= true

Whether to fall back to character-level splitting for words that exceed maxSize. Only applies if fallbackToWords is enabled.

HTML

headers:

Array<[string, string]>

Array of [selector, metadata key] pairs for header-based splitting

sections:

Array<[string, string]>

Array of [selector, metadata key] pairs for section-based splitting

returnEachLine?:

boolean

Whether to return each line as a separate chunk

HTML 전략을 사용할 때 모든 일반 옵션은 무시됩니다. 사용headers for header-based splitting or sections for section-based splitting. If used together, sections will be ignored.

가격 인하

headers?:

Array<[string, string]>

Array of [header level, metadata key] pairs

stripHeaders?:

boolean

Whether to remove headers from the output

returnEachLine?:

boolean

Whether to return each line as a separate chunk

사용할 때headers 옵션을 사용하면 마크다운 전략은 모든 일반 옵션을 무시하고 마크다운 헤더 구조를 기준으로 콘텐츠를 분할합니다. 마크다운에서 크기 기반 청킹을 사용하려면 를 생략하세요. headers parameter.

의미론적 마크다운

joinThreshold?:

number

= 500

Maximum token count for merging related sections. Sections exceeding this limit individually are left intact, but smaller sections are merged with siblings or parents if the combined size stays under this threshold.

modelName?:

string

Name of the model for tokenization. If provided, the model's underlying tokenization encodingName will be used.

encodingName?:

string

= cl100k_base

Name of the token encoding to use. Derived from modelName if available.

allowedSpecial?:

Set<string> | 'all'

Set of special tokens allowed during tokenization, or 'all' to allow all special tokens

disallowedSpecial?:

Set<string> | 'all'

= all

Set of special tokens to disallow during tokenization, or 'all' to disallow all special tokens

토큰

encodingName?:

string

Name of the token encoding to use

modelName?:

string

Name of the model for tokenization

allowedSpecial?:

Set<string> | 'all'

Set of special tokens allowed during tokenization, or 'all' to allow all special tokens

disallowedSpecial?:

Set<string> | 'all'

Set of special tokens to disallow during tokenization, or 'all' to disallow all special tokens

JSON

maxSize:

number

Maximum size of each chunk

minSize?:

number

Minimum size of each chunk

ensureAscii?:

boolean

Whether to ensure ASCII encoding

convertLists?:

boolean

Whether to convert lists in the JSON

유액

Latex 전략은 위에 나열된 일반적인 청킹 옵션만 사용합니다. 수학 및 학술 문서에 최적화된 LaTeX 인식 분할을 제공합니다.

반환 값

다음을 반환합니다.MDocument 청킹된 문서를 포함하는 인스턴스입니다. 각 청크에는 다음이 포함됩니다:

interface DocumentNode {
  text: string
  metadata: Record<string, any>
  embedding?: number[]
}