Method add_files

llmware/library.py:516–625

Main method to integrate documents into a Library - pass a local filepath folder and all files will be routed to appropriate parser by file type extension. Parameters ---------- input_folder_path : str, default=None The path

(self, input_folder_path=None, encoding="utf-8",chunk_size=400,
                   get_images=True,get_tables=True, smart_chunking=1, max_chunk_size=600,
                   table_grid=True, get_header_text=True, table_strategy=1, strip_header=False,
                   verbose_level=2, copy_files_to_library=True, set_custom_logging=-1,
                   use_logging_file=False)

        return self.add_files()

    def add_files (self, input_folder_path=None, encoding="utf-8",chunk_size=400,
                   get_images=True,get_tables=True, smart_chunking=1, max_chunk_size=600,
                   table_grid=True, get_header_text=True, table_strategy=1, strip_header=False,
                   verbose_level=2, copy_files_to_library=True, set_custom_logging=-1,
                   use_logging_file=False):

        """Main method to integrate documents into a Library - pass a local filepath folder and all files will be
        routed to appropriate parser by file type extension.
        
            Parameters
            ----------
            input_folder_path : str, default=None
                The path to the folder containing files to be ingested. If not provided, defaults to None.

            encoding : str, default="utf-8"
                The encoding to use for reading files.

            chunk_size : int, default=400
                The size of text chunks to create during parsing.

            get_images : bool, default=True
                Whether to extract images from the documents.

            get_tables : bool, default=True
                Whether to extract tables from the documents.

            smart_chunking : int, default=1
                The strategy for smart chunking of text.

            max_chunk_size : int, default=600
                The maximum size of text chunks.

            table_grid : bool, default=True
                Whether to use a grid for tables.

            get_header_text : bool, default=True
                Whether to extract header text from the documents.

            table_strategy : int, default=1
                The strategy to use for table extraction.

            strip_header : bool, default=False
                Whether to strip headers from the documents.

            verbose_level : int, default=2
                The level of verbosity for logging.

            copy_files_to_library : bool, default=True
                Whether to copy the files to the library.

            set_custom_logging : int, default=-1, will apply a custom logging level between 0-50 for the
                parsing job.

            use_logging_file : bool, default=False
                Whether parse should log to stdout (default) or to file (set to True)

            Returns
            -------