MCPcopy Create free account
hub / github.com/Tencent/WeKnora / Document

Class Document

docreader/models/document.py:62–87  ·  view source on GitHub ↗

Document including document content, document metadata.

Source from the content-addressed store, hash-verified

60
61
62class Document(BaseModel):
63 """Document including document content, document metadata."""
64
65 model_config = {"arbitrary_types_allowed": True}
66
67 content: str = Field(default="", description="document text content")
68 images: Dict[str, str] = Field(
69 default_factory=dict, description="Images in the document"
70 )
71
72 chunks: List[Chunk] = Field(default_factory=list, description="document chunks")
73 metadata: Dict[str, Any] = Field(
74 default_factory=dict,
75 description="metadata fields",
76 )
77
78 def set_content(self, content: str) -> None:
79 """Set document content."""
80 self.content = content
81
82 def get_content(self) -> str:
83 """Get document content."""
84 return self.content
85
86 def is_valid(self) -> bool:
87 return self.content != ""

Callers 15

parse_into_textMethod · 0.90
parse_into_textMethod · 0.90
parse_into_textMethod · 0.90
parse_into_textMethod · 0.90
_routeMethod · 0.90
parse_into_textMethod · 0.90
_parse_with_antiwordMethod · 0.90
_parse_with_textractMethod · 0.90
parse_into_textMethod · 0.90
parse_into_textMethod · 0.90
parse_into_textMethod · 0.90
parse_into_textMethod · 0.90

Calls

no outgoing calls

Tested by

no test coverage detected