FileConverters


Position in a Pipeline	At the very beginning of an indexing Pipeline
Input	Filename
Output	Documents
Classes	PDFToTextConverter PDFToTextOCRConverter DocxToTextConverter AzureConverter ImageToTextConverter MarkdownConverter ParsrConverter TikaConverter TextConverter

👍
Tutorial
To see an example of file converters in a pipeline, see the advanced indexing tutorial.

File Converter Classes

Here's what each of the file convertes type can do:

PDFToTextConverter: Extracts text from a PDF file using the pdftotext library.
PDFToTextOCRConverter: Extracts text from PDF files that contain images using the pytesseract library.
DocxToTextConverter: Extracts text from .docx files.
AzureConverter: Extracts text and tables from files in the following formats: PDF, JPEG, PNG, BMP, and TIFF. Uses Microsoft Azure's Form Recognizer. To use this converter, you must have an active Azure account and a Form Recognizer or Cognitive Services resource. For more information, see Form Recognizer.
ImageToTextConverter: Extracts text from image files using the pytesseract library.
MarkdownConverter: Converts markdown to plain text.
ParsrConverter: Extracts text and tables from PDF and .docx files using the open-source Parsr by axa-group.
TikaConverter: Converts files into Documents using Apache Tika.
TextConverter: Preprocesses text files and returns documents.

Usage

Click a tab to read more about each converter and see how to initialize it:

from haystack.nodes import PDFToTextConverter

converter = PDFToTextConverter(
    remove_numeric_tables=True,
    valid_languages=["de","en"]
)
docs = converter.convert(file_path=Path("my-file.pdf"), meta=None)

# Alternatively, if you have a PDF containing images, Haystack uses the pytessaract library under the hood for optical character recognition of image PDFs.

from haystack.nodes import PDFToTextOCRConverter
converter = PDFToTextOCRConverter(
    remove_numeric_tables=False,
    valid_languages=["deu","eng"]
)
docs = converter.convert(file_path=Path("my-file.pdf"), meta=None)

from haystack.nodes import DocxToTextConverter</code>

converter = DocxToTextConverter(
    remove_numeric_tables=True,
    valid_languages=["de","en"]
)
docs = converter.convert(file_path=Path("my-file.docx"), meta=None)

# We recommend the Azure Form Recognizer service for parsing tables from PDFs or other complex document structures.
# (https://azure.microsoft.com/en-us/services/form-recognizer/)
from haystack.nodes import AzureConverter

converter = AzureConverter(
    endpoint="some-url",
    credential_key="my-secret-key"
)

docs = converter.convert(file_path=Path("my-file.pdf"), meta=None)

# Haystack supports extraction of text from images using OCR.
from haystack.nodes import ImageToTextConverter

converter = ImageToTextConverter(
    remove_numeric_tables=True,
    valid_languages=["de","en"]
)

docs = converter.convert(file_path=Path("my-file.png"), meta=None)

from haystack.nodes import MarkdownConverter

converter = MarkdownConverter(
    remove_numeric_tables=True,
    valid_languages=["de","en"]
)
docs = converter.convert(file_path=Path("my-file.md"), meta=None)

Haystack also has a convert_files_to_docs() utility function that will convert all txt or pdf files in a given directory.

from haystack.utils.preprocessing import convert_files_to_docs
docs = convert_files_to_docs(dir_path=doc_dir)