类class agentscope.rag

PPTParser

class PPTParser(ParserBase)

源码Source agentscope/rag/_parser/_ppt.py:130–393

用于PowerPoint.pptx文件的解析器。位于 agentscope.rag 包，继承自 ParserBase。核心成员包括 supported_extensions、parse。

Slide order is preserved. Within a slide, shapes are visited in document order and grouped into a minimum number of sections:

Text shapes and table shapes contribute to one running text section. When separate_table=True a table closes the running section and starts a new one of its own.
Picture shapes emit a standalone :class:Section whose content is a :class:DataBlock holding the base64-encoded image bytes.

slide_prefix / slide_suffix are wrapped around each slide's text content (the prefix is prepended to the slide's first text section, the suffix is appended to its last text section). Use None on either to disable wrapping.

构造器摘要Constructor Summary

构造器Constructor	说明Description
`def __init__(include_image: bool = True, separate_table: bool = False, table_format: Literal['markdown', 'json'] = 'mar…`	初始化 `PPTParser` 实例。 Initialize the PowerPoint 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.presentationml.presentation']`

方法摘要Method Summary

方法Method	说明Description
`def supported_extensions() -> list[str]`	返回 `supported_extensions` 结果。 Return ``[".pptx"]`` — the only format ``python-pptx`` reads.
`async def parse(file: bytes \| str, filename: str) -> list[Section]`async	执行解析相关操作。 Parse a PPTX file into a list of :class:`Section` objects.

构造器详情Constructor Detail

PPTParser

def __init__(include_image: bool = True, separate_table: bool = False, table_format: Literal['markdown', 'json'] = 'markdown', slide_prefix: str | None = '<slide index={index}>', slide_suffix: str | None = '</slide>') -> None

初始化 PPTParser 实例。

Initialize the PowerPoint parser.

参数Parameters

名称Name	类型Type	说明Description
`include_image`默认default `True`	bool	include 图像（类型 `bool`）。When `True`, picture shapes are emitted as :class:`DataBlock` sections. Set to `False` to keep a text-only index.
`separate_table`默认default `False`	bool	separate table（类型 `bool`）。When `True`, each table becomes its own text section, never merged with surrounding text. table_format (`Literal["markdown", "json"]`, defaults to `"markdown"`): How to render tables. `"markdown"` uses pipe-table syntax, escaping pipes and rendering cell line breaks as ` `; `"json"` emits a JSON array prefixed with a ` ` marker and preserves extracted cell strings without Markdown rendering. slide_prefix (`str \| None`, defaults to `" "`): Prepended to the first text section of each slide. Supports the `{index}` placeholder (starting at 1). Use `None` to disable.
`table_format`默认default `'markdown'`	Literal['markdown', 'json']	table 格式（类型 `Literal['markdown', 'json']`）。The table format.
`slide_prefix`默认default `'<slide index={index}>'`	str \| None	slide prefix（类型 `str \| None`）。The slide prefix.
`slide_suffix`默认default `'</slide>'`	str \| None	slide suffix（类型 `str \| None`）。Appended to the last text section of each slide. Use `None` to disable.

异常Raises

可能抛出 `Exception`。`ValueError`: If `table_format` is not one of
可能抛出 `Exception`。`"markdown"` / `"json"`.

源码Source agentscope/rag/_parser/_ppt.py:160–207

属性详情Attribute Detail

supported_media_types

list[str] = ['application/vnd.openxmlformats-officedocument.presentationml.presentation']

supported_media_types 字段。声明为 list[str]。

The supported media types field.

源码Source agentscope/rag/_parser/_ppt.py:149

方法详情Method Detail

supported_extensions

def supported_extensions() -> list[str]

返回 supported_extensions 结果。

Return [".pptx"] — the only format python-pptx reads.

返回Returns list[str]

返回str列表。Returns a list of str.

源码Source agentscope/rag/_parser/_ppt.py:155–158

parse

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

async

执行解析相关操作。

Parse a PPTX 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 PPTX bytes, or a filesystem path to the PPTX 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:`python-pptx` is not installed.
可能抛出 `Exception`。`ValueError`: If the bytes cannot be parsed.

源码Source agentscope/rag/_parser/_ppt.py:209–268