包package
io.agentscope.core.rag.readerio.agentscope.core.rag.reader
package io.agentscope.core.rag.reader
io.agentscope.core.rag.reader 属于RAG 与知识库,切分、向量化、存储与检索。 该包共收录 17 个公开类型。
io.agentscope.core.rag.reader belongs to the RAG & knowledge layer and contains 17 public types.
接口Interfaces
| 类型Type | 种类Kind | 说明Description |
|---|---|---|
Reader | 接口interface | 定义读取器契约的接口。 Interface for document readers. |
类Classes
| 类型Type | 种类Kind | 说明Description |
|---|---|---|
AbstractChunkingReader | 类class | 抽象 Chunking 读取器,把私有文档转化为可检索的知识。 Abstract base class for readers that support text chunking. |
ExternalApiReader | 类class | 外部 API 读取器,把私有文档转化为可检索的知识。 Generic external API document parsing reader that supports integration with any third-party
document parsing service. |
ImageReader | 类class | 图像读取器,把私有文档转化为可检索的知识。 Image reader implementation that reads image files. |
PDFReader | 类class | PDF 读取器,把私有文档转化为可检索的知识。 PDF reader implementation that reads and extracts text from PDF files. |
ReaderInput | 类class | 读取器输入,把私有文档转化为可检索的知识。 Input wrapper for document readers. |
ReaderUtils | 类class | 读取器 Utils,把私有文档转化为可检索的知识。 Utility class for common reader operations. |
TextChunker | 类class | 文本切分器,把私有文档转化为可检索的知识。 Utility class for chunking text into smaller pieces. |
TextReader | 类class | 文本读取器,把私有文档转化为可检索的知识。 Text reader implementation that reads and chunks text documents. |
TikaReader | 类class | Tika 读取器,把私有文档转化为可检索的知识。 TikaReader is a document reader that uses Apache Tika to extract text from various document formats. |
WordReader | 类class | Word 读取器,把私有文档转化为可检索的知识。 Word document reader that extracts text, tables, and images from Word files. |
枚举Enums
| 类型Type | 种类Kind | 说明Description |
|---|---|---|
SplitStrategy | 枚举enum | 定义已拆分 Strategy相关取值的枚举。 Strategy for splitting text into chunks. |
TableFormat | 枚举enum | 定义Table 格式相关取值的枚举。 Enumeration of table formatting options for Word document readers. |