langchain_upstage.layout_analysis_parsers.UpstageLayoutAnalysisParser

class langchain_upstage.layout_analysis_parsers.UpstageLayoutAnalysisParser(api_key: Optional[str] = None, output_type: Union[Literal['text', 'html'], dict] = 'html', split: Literal['none', 'element', 'page'] = 'none', use_ocr: bool = False, exclude: list = [])[source]

Upstage Layout Analysis Parser.

To use, you should have the environment variable UPSTAGE_API_KEY set with your API key or pass it as a named parameter to the constructor.

Example

from langchain_upstage import UpstageLayoutAnalysisParser

loader = UpstageLayoutAnalysisParser(split="page", output_type="text")

Initializes an instance of the Upstage class.

Parameters
  • api_key (str, optional) – The API key for accessing the Upstage API. Defaults to None, in which case it will be fetched from the environment variable UPSTAGE_API_KEY.

  • output_type (Union[OutputType, dict], optional) – The type of output to be generated by the parser. Defaults to “html”.

  • split (SplitType, optional) – The type of splitting to be applied. Defaults to “none” (no splitting).

  • use_ocr (bool, optional) – Extract text from images in the document. Defaults to False. (Use text info in PDF file)

  • exclude (list, optional) – Exclude specific elements from the output. Defaults to [] (all included).

Methods

__init__([api_key, output_type, split, ...])

Initializes an instance of the Upstage class.

lazy_parse(blob[, is_batch])

Lazily parses a document and yields Document objects based on the specified split type.

parse(blob)

Eagerly parse the blob into a document or documents.

__init__(api_key: Optional[str] = None, output_type: Union[Literal['text', 'html'], dict] = 'html', split: Literal['none', 'element', 'page'] = 'none', use_ocr: bool = False, exclude: list = [])[source]

Initializes an instance of the Upstage class.

Parameters
  • api_key (str, optional) – The API key for accessing the Upstage API. Defaults to None, in which case it will be fetched from the environment variable UPSTAGE_API_KEY.

  • output_type (Union[OutputType, dict], optional) – The type of output to be generated by the parser. Defaults to “html”.

  • split (SplitType, optional) – The type of splitting to be applied. Defaults to “none” (no splitting).

  • use_ocr (bool, optional) – Extract text from images in the document. Defaults to False. (Use text info in PDF file)

  • exclude (list, optional) – Exclude specific elements from the output. Defaults to [] (all included).

lazy_parse(blob: Blob, is_batch: bool = False) Iterator[Document][source]

Lazily parses a document and yields Document objects based on the specified split type.

Parameters
  • blob (Blob) – The input document blob to parse.

  • is_batch (bool, optional) – Whether to parse the document in batches. Defaults to False (single page parsing)

Yields

Document – The parsed document object.

Raises

ValueError – If an invalid split type is provided.

Return type

Iterator[Document]

parse(blob: Blob) List[Document]

Eagerly parse the blob into a document or documents.

This is a convenience method for interactive development environment.

Production applications should favor the lazy_parse method instead.

Subclasses should generally not over-ride this parse method.

Parameters

blob (Blob) – Blob instance

Returns

List of documents

Return type

List[Document]