Converters
Converters convert data from one format into another. They're most often used in indexing pipelines.
There are several converters available for different file formats:
- AzureOCRDocumentConverter: Converts files of different types using Azure's Document Intelligence service.
- DeepsetDeepLTextTranslator: Uses DeepL's translation services to translate documents into a language you specify.
- DocxToDocument: Converts DOCX files.
- HTMLToDocument Converter: Converts HTML files. You can also use it to convert LinkContentFetcher's output into a proper Document object.
- MarkdownToDocument Converter: Converts Markdown files.
- OutputAdapter: Converts a component's output so that it fits as input of another component.
- PPTXToDocument: Converts PPTX files.
- PyPDFToDocument: Converts PDF files.
- TextFileToDocument: Converts TXT files.
- UnstructuredFileConverter: Converts files to documents using Unstructured services.
Updated 5 days ago