类class agentscope.rag

ExcelParser

class ExcelParser(ParserBase)

源码Source agentscope/rag/_parser/_excel.py:197–553

Excel 解析器，把私有文档转化为可检索的知识。位于 agentscope.rag 包，继承自 ParserBase。核心成员包括 supported_extensions、parse。

Each sheet is scanned for tabular data and (optionally) images. Tables are rendered as Markdown pipe-tables or JSON arrays; images are emitted as standalone :class:DataBlock sections, including on sheets without cell values. Header-only tables are preserved.

When separate_sheet=True each sheet becomes a batch of sections that never intermix with other sheets, making it possible for a downstream chunker to keep sheets apart.

构造器摘要Constructor Summary

构造器Constructor	说明Description
`def __init__(include_sheet_names: bool = True, include_cell_coordinates: bool = False, include_image: bool = False, sep…`	初始化 `ExcelParser` 实例。 Initialize the Excel parser.

属性摘要Attribute Summary

属性Attribute	类型Type	说明Description	值Value
`supported_media_types`	list[str]	`supported_media_types` 字段。	`['application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'application/vnd.ms-excel']`

方法摘要Method Summary

方法Method	说明Description
`def supported_extensions() -> list[str]`	返回`[".xlsx", ".xls"]`。 Return ``[".xlsx", ".xls"]``.
`async def parse(file: bytes \| str, filename: str) -> list[Section]`async	执行解析相关操作。 Parse an Excel file into a list of :class:`Section` objects.

构造器详情Constructor Detail

ExcelParser

def __init__(include_sheet_names: bool = True, include_cell_coordinates: bool = False, include_image: bool = False, separate_sheet: bool = False, table_format: Literal['markdown', 'json'] = 'markdown') -> None

初始化 ExcelParser 实例。

Initialize the Excel parser.

参数Parameters

名称Name	类型Type	说明Description
`include_sheet_names`默认default `True`	bool	include sheet names（类型 `bool`）。Whether to prepend each sheet's name as a header.
`include_cell_coordinates`默认default `False`	bool	include cell coordinates（类型 `bool`）。Whether to include cell coordinates (e.g. `[A1]`) in the rendered table.
`include_image`默认default `False`	bool	include 图像（类型 `bool`）。Whether to extract and include embedded images. Requires `openpyxl`.
`separate_sheet`默认default `False`	bool	separate sheet（类型 `bool`）。If `True`, images and table text from different sheets are never combined into the same section. table_format (`Literal["markdown", "json"]`, defaults to `"markdown"`): How to render tables.
`table_format`默认default `'markdown'`	Literal['markdown', 'json']	table 格式（类型 `Literal['markdown', 'json']`）。The table format.

异常Raises

当`ValueError`:If`table_format`是不`"markdown"`时抛出 `Exception`。`ValueError`: If `table_format` is not `"markdown"`
可能抛出 `Exception`。or `"json"`.

源码Source agentscope/rag/_parser/_excel.py:237–276

属性详情Attribute Detail

supported_media_types

list[str] = ['application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'application/vnd.ms-excel']

supported_media_types 字段。声明为 list[str]。

The supported media types field.

源码Source agentscope/rag/_parser/_excel.py:227

方法详情Method Detail

supported_extensions

def supported_extensions() -> list[str]

返回[".xlsx", ".xls"]。

Return [".xlsx", ".xls"].

返回Returns list[str]

返回str列表。Returns a list of str.

源码Source agentscope/rag/_parser/_excel.py:233–235

parse

async def parse(file: bytes | str, filename: str) -> list[Section]

async

执行解析相关操作。

Parse an Excel file into a list of :class:Section objects.

参数Parameters

名称Name	类型Type	说明Description
`file`	bytes \| str	文件（类型 `bytes \| str`）。Either the raw Excel bytes, or a filesystem path to the Excel file.
`filename`	str	filename（类型 `str`）。The source filename, copied into each Section's :attr:`Section.source`.

返回Returns list[Section]

返回Section列表。`list[Section]`:

异常Raises

可能抛出 `Exception`。`FileNotFoundError`: If `file` is a `str` pointing to
可能抛出 `Exception`。a path that does not exist.
可能抛出 `Exception`。`ImportError`: If :mod:`pandas` is not installed.
可能抛出 `Exception`。`ValueError`: If the workbook or any worksheet cannot be parsed.

源码Source agentscope/rag/_parser/_excel.py:278–363