Haystack docs home page

🎉 We are working to make this website better, stay tuned. In the meantime, have a look at our up to date API Reference section in the new docs.

Module base

BaseConverter

class BaseConverter(BaseComponent)

Base class for implementing file converts to transform input documents to text format for ingestion in DocumentStore.

BaseConverter.__init__

def __init__(remove_numeric_tables: bool = False,
             valid_languages: Optional[List[str]] = None,
             id_hash_keys: Optional[List[str]] = None,
             progress_bar: bool = True)

Arguments:

  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.
  • progress_bar: Show a progress bar for the conversion.

BaseConverter.convert

@abstractmethod
def convert(file_path: Path,
            meta: Optional[Dict[str, Any]],
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = "UTF-8",
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Convert a file to a dictionary containing the text and any associated meta data.

File converters may extract file meta like name or size. In addition to it, user supplied meta data like author, url, external IDs can be supplied as a dictionary.

Arguments:

  • file_path: path of the file to convert
  • meta: dictionary of meta data key-value pairs to append in the returned document.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Select the file encoding (default is UTF-8)
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

BaseConverter.validate_language

def validate_language(text: str,
                      valid_languages: Optional[List[str]] = None) -> bool

Validate if the language of the text is one of valid languages.

BaseConverter.run

def run(file_paths: Union[Path, List[Path]],
        meta: Optional[Union[Dict[str, str],
                             List[Optional[Dict[str, str]]]]] = None,
        remove_numeric_tables: Optional[bool] = None,
        known_ligatures: Dict[str, str] = KNOWN_LIGATURES,
        valid_languages: Optional[List[str]] = None,
        encoding: Optional[str] = "UTF-8",
        id_hash_keys: Optional[List[str]] = None)

Extract text from a file.

Arguments:

  • file_paths: Path to the files you want to convert
  • meta: Optional dictionary with metadata that shall be attached to all resulting documents. Can be any custom keys and values.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • known_ligatures: Some converters tends to recognize clusters of letters as ligatures, such as "ff" (double f). Such ligatures however make text hard to compare with the content of other files, which are generally ligature free. Therefore we automatically find and replace the most common ligatures with their split counterparts. The default mapping is in haystack.nodes.file_converter.base.KNOWN_LIGATURES: it is rather biased towards Latin alphabeths but excludes all ligatures that are known to be used in IPA. You can use this parameter to provide your own set of ligatures to clean up from the documents.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Select the file encoding (default is UTF-8)
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Module docx

DocxToTextConverter

class DocxToTextConverter(BaseConverter)

DocxToTextConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, str]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = None,
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Extract text from a .docx file.

Note: As docx doesn't contain "page" information, we actually extract and return a list of paragraphs here. For compliance with other converters we nevertheless opted for keeping the methods name.

Arguments:

  • file_path: Path to the .docx file you want to convert
  • meta: dictionary of meta data key-value pairs to append in the returned document.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Not applicable
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Module image

ImageToTextConverter

class ImageToTextConverter(BaseConverter)

ImageToTextConverter.__init__

def __init__(remove_numeric_tables: bool = False,
             valid_languages: Optional[List[str]] = ["eng"],
             id_hash_keys: Optional[List[str]] = None)

Arguments:

  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified here (https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html) This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text. Run the following line of code to check available language packs:

List of available languages

print(pytesseract.get_languages(config=''))

  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

ImageToTextConverter.convert

def convert(file_path: Union[Path, str],
            meta: Optional[Dict[str, str]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = None,
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Extract text from image file using the pytesseract library (https://github.com/madmaze/pytesseract)

Arguments:

  • file_path: path to image file
  • meta: Optional dictionary with metadata that shall be attached to all resulting documents. Can be any custom keys and values.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages supported by tessarect (https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html). This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Not applicable
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Module markdown

MarkdownConverter

class MarkdownConverter(BaseConverter)

MarkdownConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, str]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = "utf-8",
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Reads text from a markdown file and executes optional preprocessing steps.

Arguments:

  • file_path: path of the file to convert
  • meta: dictionary of meta data key-value pairs to append in the returned document.
  • encoding: Select the file encoding (default is utf-8)
  • remove_numeric_tables: Not applicable
  • valid_languages: Not applicable
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

MarkdownConverter.markdown_to_text

@staticmethod
def markdown_to_text(markdown_string: str) -> str

Converts a markdown string to plaintext

Arguments:

  • markdown_string: String in markdown format

Module pdf

PDFToTextConverter

class PDFToTextConverter(BaseConverter)

PDFToTextConverter.__init__

def __init__(remove_numeric_tables: bool = False,
             valid_languages: Optional[List[str]] = None,
             id_hash_keys: Optional[List[str]] = None,
             encoding: Optional[str] = "UTF-8",
             keep_physical_layout: bool = False)

Arguments:

  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.
  • encoding: Encoding that will be passed as -enc parameter to pdftotext. Defaults to "UTF-8" in order to support special characters (e.g. German Umlauts, Cyrillic ...). (See list of available encodings, such as "Latin1", by running pdftotext -listenc in the terminal)
  • keep_physical_layout: This option will maintain original physical layout on the extracted text. It works by passing the -layout parameter to pdftotext. When disabled, PDF is read in the stream order.

PDFToTextConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, Any]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = None,
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Extract text from a .pdf file using the pdftotext library (https://www.xpdfreader.com/pdftotext-man.html)

Arguments:

  • file_path: Path to the .pdf file you want to convert
  • meta: Optional dictionary with metadata that shall be attached to all resulting documents. Can be any custom keys and values.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Encoding that overwrites self.encoding and will be passed as -enc parameter to pdftotext. (See list of available encodings by running pdftotext -listenc in the terminal)
  • keep_physical_layout: This option will maintain original physical layout on the extracted text. It works by passing the -layout parameter to pdftotext. When disabled, PDF is read in the stream order.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

PDFToTextOCRConverter

class PDFToTextOCRConverter(BaseConverter)

PDFToTextOCRConverter.__init__

def __init__(remove_numeric_tables: bool = False,
             valid_languages: Optional[List[str]] = ["eng"],
             id_hash_keys: Optional[List[str]] = None)

Extract text from image file using the pytesseract library (https://github.com/madmaze/pytesseract)

Arguments:

  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages supported by tessarect (https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html). This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

PDFToTextOCRConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, Any]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = None,
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Convert a file to a dictionary containing the text and any associated meta data.

File converters may extract file meta like name or size. In addition to it, user supplied meta data like author, url, external IDs can be supplied as a dictionary.

Arguments:

  • file_path: path of the file to convert
  • meta: dictionary of meta data key-value pairs to append in the returned document.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Not applicable
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Module parsr

ParsrConverter

class ParsrConverter(BaseConverter)

File converter that makes use of the open-source Parsr tool by axa-group. (https://github.com/axa-group/Parsr). This Converter extracts both text and tables. Supported file formats are: PDF, DOCX

ParsrConverter.__init__

def __init__(parsr_url: str = "http://localhost:3001",
             extractor: Literal["pdfminer", "pdfjs"] = "pdfminer",
             table_detection_mode: Literal["lattice", "stream"] = "lattice",
             preceding_context_len: int = 3,
             following_context_len: int = 3,
             remove_page_headers: bool = False,
             remove_page_footers: bool = False,
             remove_table_of_contents: bool = False,
             valid_languages: Optional[List[str]] = None,
             id_hash_keys: Optional[List[str]] = None,
             add_page_number: bool = True)

Arguments:

  • parsr_url: URL endpoint to Parsr"s REST API.
  • extractor: Backend used to extract textual structured from PDFs. ("pdfminer" or "pdfjs")
  • table_detection_mode: Parsing method used to detect tables and their cells. "lattice" detects tables and their cells by demarcated lines between cells. "stream" detects tables and their cells by looking at whitespace between cells.
  • preceding_context_len: Number of lines before a table to extract as preceding context (will be returned as part of meta data).
  • following_context_len: Number of lines after a table to extract as preceding context (will be returned as part of meta data).
  • remove_page_headers: Whether to remove text that Parsr detected as a page header.
  • remove_page_footers: Whether to remove text that Parsr detected as a page footer.
  • remove_table_of_contents: Whether to remove text that Parsr detected as a table of contents.
  • valid_languages: Validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.
  • add_page_number: Adds the number of the page a table occurs in to the Document's meta field "page".

ParsrConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, Any]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = "utf-8",
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Extract text and tables from a PDF or DOCX using the open-source Parsr tool.

Arguments:

  • file_path: Path to the file you want to convert.
  • meta: Optional dictionary with metadata that shall be attached to all resulting documents. Can be any custom keys and values.
  • remove_numeric_tables: Not applicable.
  • valid_languages: Validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Not applicable.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Module azure

AzureConverter

class AzureConverter(BaseConverter)

File converter that makes use of Microsoft Azure's Form Recognizer service (https://azure.microsoft.com/en-us/services/form-recognizer/). This Converter extracts both text and tables. Supported file formats are: PDF, JPEG, PNG, BMP and TIFF.

In order to be able to use this Converter, you need an active Azure account and a Form Recognizer or Cognitive Services resource. (Here you can find information on how to set this up: https://docs.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/quickstarts/try-v3-python-sdk#prerequisites)

AzureConverter.__init__

def __init__(endpoint: str,
             credential_key: str,
             model_id: str = "prebuilt-document",
             valid_languages: Optional[List[str]] = None,
             save_json: bool = False,
             preceding_context_len: int = 3,
             following_context_len: int = 3,
             merge_multiple_column_headers: bool = True,
             id_hash_keys: Optional[List[str]] = None,
             add_page_number: bool = True)

Arguments:

  • endpoint: Your Form Recognizer or Cognitive Services resource's endpoint.
  • credential_key: Your Form Recognizer or Cognitive Services resource's subscription key.
  • model_id: The identifier of the model you want to use to extract information out of your file. Default: "prebuilt-document". General purpose models are "prebuilt-document" and "prebuilt-layout". List of available prebuilt models: https://azuresdkdocs.blob.core.windows.net/$web/python/azure-ai-formrecognizer/3.2.0b1/index.html#documentanalysisclient
  • valid_languages: Validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • save_json: Whether to save the output of the Form Recognizer to a JSON file.
  • preceding_context_len: Number of lines before a table to extract as preceding context (will be returned as part of meta data).
  • following_context_len: Number of lines after a table to extract as subsequent context (will be returned as part of meta data).
  • merge_multiple_column_headers: Some tables contain more than one row as a column header (i.e., column description). This parameter lets you choose, whether to merge multiple column header rows to a single row.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.
  • add_page_number: Adds the number of the page a table occurs in to the Document's meta field "page".

AzureConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, Any]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = "utf-8",
            id_hash_keys: Optional[List[str]] = None,
            pages: Optional[str] = None,
            known_language: Optional[str] = None) -> List[Document]

Extract text and tables from a PDF, JPEG, PNG, BMP or TIFF file using Azure's Form Recognizer service.

Arguments:

  • file_path: Path to the file you want to convert.
  • meta: Optional dictionary with metadata that shall be attached to all resulting documents. Can be any custom keys and values.
  • remove_numeric_tables: Not applicable.
  • valid_languages: Validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Not applicable.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.
  • pages: Custom page numbers for multi-page documents(PDF/TIFF). Input the page numbers and/or ranges of pages you want to get in the result. For a range of pages, use a hyphen, like pages=”1-3, 5-6”. Separate each page number or range with a comma.
  • known_language: Locale hint of the input document. See supported locales here: https://aka.ms/azsdk/formrecognizer/supportedlocales.

AzureConverter.convert_azure_json

def convert_azure_json(
        file_path: Path,
        meta: Optional[Dict[str, Any]] = None,
        valid_languages: Optional[List[str]] = None,
        id_hash_keys: Optional[List[str]] = None) -> List[Document]

Extract text and tables from the JSON output of Azure's Form Recognizer service.

Arguments:

  • file_path: Path to the JSON-file you want to convert.
  • meta: Optional dictionary with metadata that shall be attached to all resulting documents. Can be any custom keys and values.
  • valid_languages: Validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Module tika

TikaConverter

class TikaConverter(BaseConverter)

TikaConverter.__init__

def __init__(tika_url: str = "http://localhost:9998/tika",
             remove_numeric_tables: bool = False,
             valid_languages: Optional[List[str]] = None,
             id_hash_keys: Optional[List[str]] = None)

Arguments:

  • tika_url: URL of the Tika server
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

TikaConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, str]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = None,
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Arguments:

  • file_path: path of the file to convert
  • meta: dictionary of meta data key-value pairs to append in the returned document.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Not applicable
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.

Returns:

A list of pages and the extracted meta data of the file.

Module txt

TextConverter

class TextConverter(BaseConverter)

TextConverter.convert

def convert(file_path: Path,
            meta: Optional[Dict[str, str]] = None,
            remove_numeric_tables: Optional[bool] = None,
            valid_languages: Optional[List[str]] = None,
            encoding: Optional[str] = "utf-8",
            id_hash_keys: Optional[List[str]] = None) -> List[Document]

Reads text from a txt file and executes optional preprocessing steps.

Arguments:

  • file_path: path of the file to convert
  • meta: dictionary of meta data key-value pairs to append in the returned document.
  • remove_numeric_tables: This option uses heuristics to remove numeric rows from the tables. The tabular structures in documents might be noise for the reader model if it does not have table parsing capability for finding answers. However, tables may also have long strings that could possible candidate for searching answers. The rows containing strings are thus retained in this option.
  • valid_languages: validate languages from a list of languages specified in the ISO 639-1 (https://en.wikipedia.org/wiki/ISO_639-1) format. This option can be used to add test for encoding errors. If the extracted text is not one of the valid languages, then it might likely be encoding error resulting in garbled text.
  • encoding: Select the file encoding (default is utf-8)
  • id_hash_keys: Generate the document id from a custom list of strings that refer to the document's attributes. If you want to ensure you don't have duplicate documents in your DocumentStore but texts are not unique, you can modify the metadata and pass e.g. "meta" to this field (e.g. ["content", "meta"]). In this case the id will be generated by using the content and the defined metadata.