1
2
3
4

BaseMedia
 └── Blob           ← 原始二进制数据
Document           ← 可用于 LLM 的文档
BaseDocumentTransformer ← 文档的处理/转换器

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41

class BaseMedia(Serializable):


    # The ID field is optional at the moment.
    # It will likely become required in a future major release after
    # it has been adopted by enough vectorstore implementations.
    id: Optional[str] = Field(default=None, coerce_numbers_to_str=True)
    """An optional identifier for the document.

    Ideally this should be unique across the document collection and formatted
    as a UUID, but this will not be enforced.

    .. versionadded:: 0.2.11
    """

    metadata: dict = Field(default_factory=dict)


class Blob(BaseMedia):
    data: Union[bytes, str, None] = None
    """Raw data associated with the blob."""
    mimetype: Optional[str] = None
    """MimeType not to be confused with a file extension."""
    encoding: str = "utf-8"
    """Encoding to use if decoding the bytes into a string.

    Use utf-8 as default encoding, if decoding to string.
    """
    path: Optional[PathLike] = None
    """Location where the original content was found."""

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
        frozen=True,
    )


class Document(BaseMedia):
    page_content: str
    """String text."""
    type: Literal["Document"] = "Document"