UploadDocumentAsyncShrinkRequest (gpdb20160503 3.0.0 API)

java.lang.Object
- com.aliyun.tea.TeaModel
- - com.aliyun.gpdb20160503.models.UploadDocumentAsyncShrinkRequest

public class UploadDocumentAsyncShrinkRequest
extends com.aliyun.tea.TeaModel

字段概要

字段
限定符和类型	字段和说明
`Integer`	`chunkOverlap` The size of data that is overlapped between consecutive chunks.
`Integer`	`chunkSize` example: 250
`String`	`collection` This parameter is required.
`String`	`DBInstanceId` This parameter is required.
`String`	`documentLoaderName` The name of the document loader.
`Boolean`	`dryRun` Specifies whether to perform only document understanding and chunking, but not vectorization and storage.
`String`	`fileName` The file name of the document.
`String`	`fileUrl` This parameter is required.
`String`	`metadataShrink` The metadata.
`String`	`namespace` example: mynamespace
`String`	`namespacePassword` This parameter is required.
`Long`	`ownerId`
`String`	`regionId` The region ID of the instance.
`String`	`separatorsShrink` The separators that are used to split large amounts of data.
`String`	`textSplitterName` The name of the splitter.
`Boolean`	`zhTitleEnhance` Specifies whether to enable title enhancement.

构造器概要

构造器
构造器和说明

UploadDocumentAsyncShrinkRequest()

构造器
构造器和说明
`UploadDocumentAsyncShrinkRequest()`

方法概要

所有方法静态方法实例方法具体方法
限定符和类型	方法和说明
`static UploadDocumentAsyncShrinkRequest`	`build(Map<String,?> map)`
`Integer`	`getChunkOverlap()`
`Integer`	`getChunkSize()`
`String`	`getCollection()`
`String`	`getDBInstanceId()`
`String`	`getDocumentLoaderName()`
`Boolean`	`getDryRun()`
`String`	`getFileName()`
`String`	`getFileUrl()`
`String`	`getMetadataShrink()`
`String`	`getNamespace()`
`String`	`getNamespacePassword()`
`Long`	`getOwnerId()`
`String`	`getRegionId()`
`String`	`getSeparatorsShrink()`
`String`	`getTextSplitterName()`
`Boolean`	`getZhTitleEnhance()`
`UploadDocumentAsyncShrinkRequest`	`setChunkOverlap(Integer chunkOverlap)`
`UploadDocumentAsyncShrinkRequest`	`setChunkSize(Integer chunkSize)`
`UploadDocumentAsyncShrinkRequest`	`setCollection(String collection)`
`UploadDocumentAsyncShrinkRequest`	`setDBInstanceId(String DBInstanceId)`
`UploadDocumentAsyncShrinkRequest`	`setDocumentLoaderName(String documentLoaderName)`
`UploadDocumentAsyncShrinkRequest`	`setDryRun(Boolean dryRun)`
`UploadDocumentAsyncShrinkRequest`	`setFileName(String fileName)`
`UploadDocumentAsyncShrinkRequest`	`setFileUrl(String fileUrl)`
`UploadDocumentAsyncShrinkRequest`	`setMetadataShrink(String metadataShrink)`
`UploadDocumentAsyncShrinkRequest`	`setNamespace(String namespace)`
`UploadDocumentAsyncShrinkRequest`	`setNamespacePassword(String namespacePassword)`
`UploadDocumentAsyncShrinkRequest`	`setOwnerId(Long ownerId)`
`UploadDocumentAsyncShrinkRequest`	`setRegionId(String regionId)`
`UploadDocumentAsyncShrinkRequest`	`setSeparatorsShrink(String separatorsShrink)`
`UploadDocumentAsyncShrinkRequest`	`setTextSplitterName(String textSplitterName)`
`UploadDocumentAsyncShrinkRequest`	`setZhTitleEnhance(Boolean zhTitleEnhance)`

从类继承的方法 com.aliyun.tea.TeaModel
build, buildMap, confirmType, confirmType, parseObject, toMap, toMap, toModel, validate, validateParams

从类继承的方法 java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- 字段详细资料
  - chunkOverlap
```
@NameInMap(value="ChunkOverlap")
public Integer chunkOverlap
```
    The size of data that is overlapped between consecutive chunks. The maximum value of this parameter cannot be greater than the value of the ChunkSize parameter.
    
    This parameter is used to prevent context missing that may occur due to data truncation. For example, when you upload a long text, you can retain specific overlapped text content between consecutive chunks to better understand the context.
    
    example:
    50
  - chunkSize
```
@NameInMap(value="ChunkSize")
public Integer chunkSize
```
    example:
    250
  - collection
```
@NameInMap(value="Collection")
public String collection
```
    This parameter is required.
    example:
    document
  - DBInstanceId
```
@NameInMap(value="DBInstanceId")
public String DBInstanceId
```
    This parameter is required.
    example:
    gp-bp12ga6v69h86****
  - documentLoaderName
```
@NameInMap(value="DocumentLoaderName")
public String documentLoaderName
```
    The name of the document loader. You do not need to specify this parameter. A document loader is automatically specified based on the file extension. Valid values:
    - UnstructuredHTMLLoader: .html
    - UnstructuredMarkdownLoader: .md
    - PyMuPDFLoader: .pdf
    - PyPDFLoader: .pdf
    - RapidOCRPDFLoader: .pdf
    - PDFWithImageRefLoader: .pdf (with the text-image association feature)
    - JSONLoader: .json
    - CSVLoader: .csv
    - RapidOCRLoader: .png, .jpg, .jpeg, and .bmp
    - UnstructuredFileLoader: .eml, .msg, .rst, .txt, .docx, .epub, .odt, .pptx, and .tsv
    example:
    PyMuPDFLoader
  - dryRun
```
@NameInMap(value="DryRun")
public Boolean dryRun
```
    Specifies whether to perform only document understanding and chunking, but not vectorization and storage. Default value: false.
    
    You can set this parameter to true, check the chunking effect, and then perform optimization if needed.
    
    example:
    false
  - fileName
```
@NameInMap(value="FileName")
public String fileName
```
    The file name of the document.
    - We recommend that you add an extension to the file name. Examples: .json, .md, and .pdf. If you do not add an extension, the default loader designed for unstructured data is used.
    - If an image file is involved, the file name must contain an extension. The following extensions are supported: .bmp, .jpg, .jpeg, .png, and .tiff.
    - You can use a compressed package to upload images. The package file name must contain an extension. Supported package file extensions: .tar, .gz, and .zip.
    This parameter is required.
    example:
    mydoc.txt
  - fileUrl
```
@NameInMap(value="FileUrl")
public String fileUrl
```
    This parameter is required.
    example:
    https://xx/mydoc.txt
  - metadataShrink
```
@NameInMap(value="Metadata")
public String metadataShrink
```
    The metadata. The value of this parameter must be the same as the Metadata parameter that is specified when you call the CreateDocumentCollection operation.
  - namespace
```
@NameInMap(value="Namespace")
public String namespace
```
    example:
    mynamespace
  - namespacePassword
```
@NameInMap(value="NamespacePassword")
public String namespacePassword
```
    This parameter is required.
    example:
    testpassword
  - ownerId
```
@NameInMap(value="OwnerId")
public Long ownerId
```
  - regionId
```
@NameInMap(value="RegionId")
public String regionId
```
    The region ID of the instance.
    
    This parameter is required.
    example:
    cn-hangzhou
  - separatorsShrink
```
@NameInMap(value="Separators")
public String separatorsShrink
```
    The separators that are used to split large amounts of data.
    - This is an important parameter that determines the chunking effect. This parameter is related to the splitter that is specified by the TextSplitterName parameter.
    - In most cases, you do not need to specify this parameter. The server assigns separators based on the value of the TextSplitterName parameter.
  - textSplitterName
```
@NameInMap(value="TextSplitterName")
public String textSplitterName
```
    The name of the splitter. Valid values:
    - ChineseRecursiveTextSplitter: inherits from RecursiveCharacterTextSplitter, uses ["\\n\\n","\\n", "。|!|?", "\\.\\s|\\!\\s|\\?\\s", ";|;\\s", ",|,\\s"] as separators by default, and uses regular expressions to match text.
    - RecursiveCharacterTextSplitter: uses ["\\n\\n", "\\n", " ", ""] as separators by default. The splitter supports splitting code in languages such as C++, Go, Java, JS, PHP, Proto, Python, RST, Ruby, Rust, Scala, Swift, Markdown, LaTeX, HTML, Sol, and C Sharp.
    - SpacyTextSplitter: uses \\n\\n as separators by default and uses the en_core_web_sm model of spaCy. The splitter can obtain better splitting effect.
    - MarkdownHeaderTextSplitter: splits text in the [("#", "head1"), ("##", "head2"), ("###", "head3"), ("####", "head4")] format. The splitter is suitable for Markdown text.
    example:
    ChineseRecursiveTextSplitter
  - zhTitleEnhance
```
@NameInMap(value="ZhTitleEnhance")
public Boolean zhTitleEnhance
```
    Specifies whether to enable title enhancement.
    
    You can determine the title text, mark the text in the metadata, and then combine the text with the upper-level title to implement text enhancement.
    
    example:
    false
- 构造器详细资料
  - UploadDocumentAsyncShrinkRequest
```
public UploadDocumentAsyncShrinkRequest()
```
- 方法详细资料
  - build
```
public static UploadDocumentAsyncShrinkRequest build(Map<String,?> map)
                                              throws Exception
```
    抛出:
    
    Exception
  - setChunkOverlap
```
public UploadDocumentAsyncShrinkRequest setChunkOverlap(Integer chunkOverlap)
```
  - getChunkOverlap
```
public Integer getChunkOverlap()
```
  - setChunkSize
```
public UploadDocumentAsyncShrinkRequest setChunkSize(Integer chunkSize)
```
  - getChunkSize
```
public Integer getChunkSize()
```
  - setCollection
```
public UploadDocumentAsyncShrinkRequest setCollection(String collection)
```
  - getCollection
```
public String getCollection()
```
  - setDBInstanceId
```
public UploadDocumentAsyncShrinkRequest setDBInstanceId(String DBInstanceId)
```
  - getDBInstanceId
```
public String getDBInstanceId()
```
  - setDocumentLoaderName
```
public UploadDocumentAsyncShrinkRequest setDocumentLoaderName(String documentLoaderName)
```
  - getDocumentLoaderName
```
public String getDocumentLoaderName()
```
  - setDryRun
```
public UploadDocumentAsyncShrinkRequest setDryRun(Boolean dryRun)
```
  - getDryRun
```
public Boolean getDryRun()
```
  - setFileName
```
public UploadDocumentAsyncShrinkRequest setFileName(String fileName)
```
  - getFileName
```
public String getFileName()
```
  - setFileUrl
```
public UploadDocumentAsyncShrinkRequest setFileUrl(String fileUrl)
```
  - getFileUrl
```
public String getFileUrl()
```
  - setMetadataShrink
```
public UploadDocumentAsyncShrinkRequest setMetadataShrink(String metadataShrink)
```
  - getMetadataShrink
```
public String getMetadataShrink()
```
  - setNamespace
```
public UploadDocumentAsyncShrinkRequest setNamespace(String namespace)
```
  - getNamespace
```
public String getNamespace()
```
  - setNamespacePassword
```
public UploadDocumentAsyncShrinkRequest setNamespacePassword(String namespacePassword)
```
  - getNamespacePassword
```
public String getNamespacePassword()
```
  - setOwnerId
```
public UploadDocumentAsyncShrinkRequest setOwnerId(Long ownerId)
```
  - getOwnerId
```
public Long getOwnerId()
```
  - setRegionId
```
public UploadDocumentAsyncShrinkRequest setRegionId(String regionId)
```
  - getRegionId
```
public String getRegionId()
```
  - setSeparatorsShrink
```
public UploadDocumentAsyncShrinkRequest setSeparatorsShrink(String separatorsShrink)
```
  - getSeparatorsShrink
```
public String getSeparatorsShrink()
```
  - setTextSplitterName
```
public UploadDocumentAsyncShrinkRequest setTextSplitterName(String textSplitterName)
```
  - getTextSplitterName
```
public String getTextSplitterName()
```
  - setZhTitleEnhance
```
public UploadDocumentAsyncShrinkRequest setZhTitleEnhance(Boolean zhTitleEnhance)
```
  - getZhTitleEnhance
```
public Boolean getZhTitleEnhance()
```

类 UploadDocumentAsyncShrinkRequest

字段概要

构造器概要

方法概要

从类继承的方法 com.aliyun.tea.TeaModel

从类继承的方法 java.lang.Object

字段详细资料

chunkOverlap

chunkSize

collection

DBInstanceId

documentLoaderName

dryRun

fileName

fileUrl

metadataShrink

namespace

namespacePassword

ownerId

regionId

separatorsShrink

textSplitterName

zhTitleEnhance

构造器详细资料

UploadDocumentAsyncShrinkRequest

方法详细资料

build

setChunkOverlap

getChunkOverlap

setChunkSize

getChunkSize

setCollection

getCollection

setDBInstanceId

getDBInstanceId

setDocumentLoaderName

getDocumentLoaderName

setDryRun

getDryRun

setFileName

getFileName

setFileUrl

getFileUrl

setMetadataShrink

getMetadataShrink

setNamespace

getNamespace

setNamespacePassword

getNamespacePassword

setOwnerId

getOwnerId

setRegionId

getRegionId

setSeparatorsShrink

getSeparatorsShrink

setTextSplitterName

getTextSplitterName

setZhTitleEnhance

getZhTitleEnhance