UnstructuredIO

class UnstructuredIO:

A class to handle various functionalities provided by the Unstructured library, including version checking, parsing, cleaning, extracting, staging, chunking data, and integrating with cloud services like S3 and Azure for data connection.

References: https://docs.unstructured.io/

create_element_from_text

def create_element_from_text(
    text: str,
    element_id: Optional[str] = None,
    embeddings: Optional[List[float]] = None,
    filename: Optional[str] = None,
    file_directory: Optional[str] = None,
    last_modified: Optional[str] = None,
    filetype: Optional[str] = None,
    parent_id: Optional[str] = None
):

Creates a Text element from a given text input, with optional metadata and embeddings.

Parameters:

  • text (str): The text content for the element.
  • element_id (Optional[str], optional): Unique identifier for the element. (default: :obj:None)
  • embeddings (List[float], optional): A list of float numbers representing the text embeddings. (default: :obj:None)
  • filename (Optional[str], optional): The name of the file the element is associated with. (default: :obj:None)
  • file_directory (Optional[str], optional): The directory path where the file is located. (default: :obj:None)
  • last_modified (Optional[str], optional): The last modified date of the file. (default: :obj:None)
  • filetype (Optional[str], optional): The type of the file. (default: :obj:None)
  • parent_id (Optional[str], optional): The identifier of the parent element. (default: :obj:None)

Returns:

Element: An instance of Text with the provided content and metadata.

parse_file_or_url

def parse_file_or_url(input_path: str, **kwargs: Any):

Loads a file or a URL and parses its contents into elements.

Parameters:

  • input_path (str): Path to the file or URL to be parsed. **kwargs: Extra kwargs passed to the partition function.

Returns:

Union[List[Element],None]: List of elements after parsing the file or URL if success.

parse_bytes

def parse_bytes(file: IO[bytes], **kwargs: Any):

Parses a bytes stream and converts its contents into elements.

Parameters:

  • file (IO[bytes]): The file in bytes format to be parsed. **kwargs: Extra kwargs passed to the partition function.

Returns:

Union[List[Element], None]: List of elements after parsing the file if successful, otherwise None.

Notes: Supported file types: “csv”, “doc”, “docx”, “epub”, “image”, “md”, “msg”, “odt”, “org”, “pdf”, “ppt”, “pptx”, “rtf”, “rst”, “tsv”, “xlsx”.

References: https://docs.unstructured.io/open-source/core-functionality/partitioning

clean_text_data

def clean_text_data(
    text: str,
    clean_options: Optional[List[Tuple[str, Dict[str, Any]]]] = None
):

Cleans text data using a variety of cleaning functions provided by the unstructured library.

This function applies multiple text cleaning utilities by calling the unstructured library’s cleaning bricks for operations like replacing Unicode quotes, removing extra whitespace, dashes, non-ascii characters, and more.

If no cleaning options are provided, a default set of cleaning operations is applied. These defaults including operations “replace_unicode_quotes”, “clean_non_ascii_chars”, “group_broken_paragraphs”, and “clean_extra_whitespace”.

Parameters:

  • text (str): The text to be cleaned.
  • clean_options (dict): A dictionary specifying which cleaning options to apply. The keys should match the names of the cleaning functions, and the values should be dictionaries containing the parameters for each function. Supported types: ‘clean_extra_whitespace’, ‘clean_bullets’, ‘clean_ordered_bullets’, ‘clean_postfix’, ‘clean_prefix’, ‘clean_dashes’, ‘clean_trailing_punctuation’, ‘clean_non_ascii_chars’, ‘group_broken_paragraphs’, ‘remove_punctuation’, ‘replace_unicode_quotes’, ‘bytes_string_to_string’, ‘translate_text’.

Returns:

str: The cleaned text.

extract_data_from_text

def extract_data_from_text(
    text: str,
    extract_type: Literal['extract_datetimetz', 'extract_email_address', 'extract_ip_address', 'extract_ip_address_name', 'extract_mapi_id', 'extract_ordered_bullets', 'extract_text_after', 'extract_text_before', 'extract_us_phone_number'],
    **kwargs
):

Extracts various types of data from text using functions from unstructured.cleaners.extract.

Parameters:

  • text (str): Text to extract data from. extract_type (Literal[‘extract_datetimetz’, ‘extract_email_address’, ‘extract_ip_address’, ‘extract_ip_address_name’, ‘extract_mapi_id’, ‘extract_ordered_bullets’, ‘extract_text_after’, ‘extract_text_before’, ‘extract_us_phone_number’]): Type of data to extract. **kwargs: Additional keyword arguments for specific extraction functions.

Returns:

Any: The extracted data, type depends on extract_type.

References: https://unstructured-io.github.io/unstructured/

stage_elements

def stage_elements(
    elements: List[Any],
    stage_type: Literal['convert_to_csv', 'convert_to_dataframe', 'convert_to_dict', 'dict_to_elements', 'stage_csv_for_prodigy', 'stage_for_prodigy', 'stage_for_baseplate', 'stage_for_datasaur', 'stage_for_label_box', 'stage_for_label_studio', 'stage_for_weaviate'],
    **kwargs
):

Stages elements for various platforms based on the specified staging type.

This function applies multiple staging utilities to format data for different NLP annotation and machine learning tools. It uses the ‘unstructured.staging’ module’s functions for operations like converting to CSV, DataFrame, dictionary, or formatting for specific platforms like Prodigy, etc.

Parameters:

  • elements (List[Any]): List of Element objects to be staged. stage_type (Literal[‘convert_to_csv’, ‘convert_to_dataframe’, ‘convert_to_dict’, ‘dict_to_elements’, ‘stage_csv_for_prodigy’, ‘stage_for_prodigy’, ‘stage_for_baseplate’, ‘stage_for_datasaur’, ‘stage_for_label_box’, ‘stage_for_label_studio’, ‘stage_for_weaviate’]): Type of staging to perform. **kwargs: Additional keyword arguments specific to the staging type.

Returns:

Union[str, List[Dict], Any]: Staged data in the format appropriate for the specified staging type.

chunk_elements

def chunk_elements(elements: List['Element'], chunk_type: str, **kwargs):

Chunks elements by titles.

Parameters:

  • elements (List[Element]): List of Element objects to be chunked.
  • chunk_type (str): Type chunk going to apply. Supported types: ‘chunk_by_title’. **kwargs: Additional keyword arguments for chunking.

Returns:

List[Dict]: List of chunked sections.

References: https://unstructured-io.github.io/unstructured/