Skip to content

Files

DocumentIngestor

Bases: BaseComponent

Ingest common office document types into Document for indexing

Document types
  • pdf
  • xlsx, xls
  • docx, doc

Parameters:

Name Type Description Default
pdf_mode

mode for pdf extraction, one of "normal", "mathpix", "ocr" - normal: parse pdf text - mathpix: parse pdf text using mathpix - ocr: parse pdf image using flax

 required
doc_parsers

list of document parsers to parse the document

 required
text_splitter

splitter to split the document into text nodes

 required
override_file_extractors

override file extractors for specific file extensions The default file extractors are stored in KH_DEFAULT_FILE_EXTRACTORS

 required
Source code in libs\kotaemon\kotaemon\indices\ingests\files.py 
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
class DocumentIngestor(BaseComponent):
    """Ingest common office document types into Document for indexing

    Document types:
        - pdf
        - xlsx, xls
        - docx, doc

    Args:
        pdf_mode: mode for pdf extraction, one of "normal", "mathpix", "ocr"
            - normal: parse pdf text
            - mathpix: parse pdf text using mathpix
            - ocr: parse pdf image using flax
        doc_parsers: list of document parsers to parse the document
        text_splitter: splitter to split the document into text nodes
        override_file_extractors: override file extractors for specific file extensions
            The default file extractors are stored in `KH_DEFAULT_FILE_EXTRACTORS`
    """

    pdf_mode: str = "normal"  # "normal", "mathpix", "ocr", "multimodal"
    doc_parsers: list[BaseDocParser] = Param(default_callback=lambda _: [])
    text_splitter: BaseSplitter = TokenSplitter.withx(
        chunk_size=1024,
        chunk_overlap=256,
        separator="\n\n",
        backup_separators=["\n", ".", " ", "\u200B"],
    )
    override_file_extractors: dict[str, Type[BaseReader]] = {}

    def _get_reader(self, input_files: list[str | Path]):
        """Get appropriate readers for the input files based on file extension"""
        file_extractors: dict[str, BaseReader] = {
            ext: reader for ext, reader in KH_DEFAULT_FILE_EXTRACTORS.items()
        }
        for ext, cls in self.override_file_extractors.items():
            file_extractors[ext] = cls()

        if self.pdf_mode == "normal":
            pass  # use default loader of llama-index which is pypdf
        elif self.pdf_mode == "ocr":
            file_extractors[".pdf"] = OCRReader()
        elif self.pdf_mode == "multimodal":
            file_extractors[".pdf"] = AdobeReader()
        else:
            file_extractors[".pdf"] = MathpixPDFReader()

        main_reader = DirectoryReader(
            input_files=input_files,
            file_extractor=file_extractors,
        )

        return main_reader

    def run(self, file_paths: list[str | Path] | str | Path) -> list[Document]:
        """Ingest the file paths into Document

        Args:
            file_paths: list of file paths or a single file path

        Returns:
            list of parsed Documents
        """
        if not isinstance(file_paths, list):
            file_paths = [file_paths]

        documents = self._get_reader(input_files=file_paths)()
        print(f"Read {len(file_paths)} files into {len(documents)} documents.")
        nodes = self.text_splitter(documents)
        print(f"Transform {len(documents)} documents into {len(nodes)} nodes.")
        self.log_progress(".num_docs", num_docs=len(nodes))

        # document parsers call
        if self.doc_parsers:
            for parser in self.doc_parsers:
                nodes = parser(nodes)

        return nodes

run 

1
run(file_paths)

Ingest the file paths into Document

Parameters:

Name Type Description Default
file_paths list[str | Path] | str | Path

list of file paths or a single file path

 required

Returns:

Type Description
list[Document]

list of parsed Documents
Source code in libs\kotaemon\kotaemon\indices\ingests\files.py 
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
def run(self, file_paths: list[str | Path] | str | Path) -> list[Document]:
    """Ingest the file paths into Document

    Args:
        file_paths: list of file paths or a single file path

    Returns:
        list of parsed Documents
    """
    if not isinstance(file_paths, list):
        file_paths = [file_paths]

    documents = self._get_reader(input_files=file_paths)()
    print(f"Read {len(file_paths)} files into {len(documents)} documents.")
    nodes = self.text_splitter(documents)
    print(f"Transform {len(documents)} documents into {len(nodes)} nodes.")
    self.log_progress(".num_docs", num_docs=len(nodes))

    # document parsers call
    if self.doc_parsers:
        for parser in self.doc_parsers:
            nodes = parser(nodes)

    return nodes