Parse Output

result = doc_ai.get_parsed_result(parse_id)

class ParseResult(BaseModel):
    # Parsed document specific fields
    chunks: Optional[List[Chunk]] = Field(
        default=None,
        description="Chunks of layout text extracted from the document. This is a vector of `Chunk` objects, each containing a piece of text extracted from the document. The chunks are typically used for further processing, such as indexing or searching. The value will vary depending on the chunking strategy used during parsing.",
    )
    document_layout: Optional[Document] = Field(
        default=None,
        description="The layout of the document. This is a JSON object that contains the layout information of the document. It can be used to understand the structure of the document, such as the position of text, tables, figures, etc.",
    )
    page_classes: Optional[Dict[str, PageClass]] = Field(
        default=None,
        description="Page classes extracted from the document. This is a map where the keys are page class names provided in the parse request under the `page_classification_options` field, and the values are PageClass objects containing the class name and page numbers where each page class appears.",
    )
    structured_data: Optional[
        Dict[str, Union[StructuredData, List[StructuredData]]]
    ] = Field(
        default=None,
        description="Structured data extracted from the document. The structured data is a map where the keys are the names of the json schema provided in the parse request, and the values are `StructuredData` objects containing the structured data extracted from the document; formatted according to the schema. When the `structured_extraction` option uses a `chunking_strategy` of `None`, the structured data will be extracted from the entire document, and it will be represented as a single entry in the map with the schema name as the key. When the `structured_extraction` option uses a `chunking_strategy`, the structured data will be extracted from each chunk of text, and it will be represented as multiple entries in the map, with the schema name as the key and a vector of `StructuredData` objects as the value. This is used to extract structured information from the document, such as tables, forms, or other structured content.",
    )

    # ParseResult specific fields
    parse_id: str = Field(description="The unique identifier for the parse job")
    parsed_pages_count: int = Field(
        description="The number of pages that were parsed successfully.", ge=0
    )
    status: ParseStatus = Field(description="The status of the parse job.")
    created_at: str = Field(
        description="The date and time when the parse job was created in RFC 3339 format."
    )
    options: ParseRequestOptions = Field(
        description="The options used for scheduling the parse job."
    )

    # Optional fields
    errors: Optional[dict] = Field(
        None, description="Error occurred during any part of the parse execution."
    )
    finished_at: Optional[str] = Field(
        None,
        description="The date and time when the parse job was finished in RFC 3339 format.",
    )
    labels: Optional[dict] = Field(
        None, description="Labels associated with the parse job."
    )
    tasks_completed_count: Optional[int] = Field(
        None,
        description="The number of tasks that have been completed for the parse job.",
        ge=0,
    )
    tasks_total_count: Optional[int] = Field(
        None,
        description="The total number of tasks that are expected to be completed for the parse job.",
        ge=0,
    )