# FileLoader **`class FileLoader(config)`** Bases: [`Loader`](squirro.lib.nlp.steps.loaders.Loader.md#squirro.lib.nlp.steps.loaders.Loader) The file [`Loader`](squirro.lib.nlp.steps.loaders.Loader.md#squirro.lib.nlp.steps.loaders.Loader) looks in a specified directory_field directory for files and loads these files either line by line or as a whole and transforms them into [`Document`](../technical/libnlp/base.md#squirro.lib.nlp.document.Document) items. Parameters - `type` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – file - `directory_field` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – name of field to store directory path of a loaded file - `encoding` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)`, ``'utf-8'`) – given file’s encoding - `output_field` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – name of field to store line or whole file - `per_line` ([`bool`](https://docs.python.org/3.11/library/functions.html#bool)`, ``False`) – indicates if each line represents a different item document **Example** ```json { "step": "loader", "type": "file", "directory_field": "loaded_file_path", "output_field": "file_content" } ``` Methods SummaryMethods Documentation **`process(directory)`** Process a directory and yield documents. Parameters `directory` ([`str`](https://docs.python.org/3.11/library/stdtypes.html#str)) – path to directory with *.txt files Returns Generator of Documents read from files Return type generator([Document](../technical/libnlp/base.md#squirro.lib.nlp.document.Document))