Skip to main content
For the complete documentation index for agents and LLMs, see llms.txt.

TikaDocumentConverter

Converts files of various formats to Haystack documents using Apache Tika, which supports a wide range of document, archive, and email formats.

Key Features

  • Supports a broad range of file formats through Apache Tika, including MS Office, PDF, OpenDocument, archives, and email formats.
  • Handles file formats that other converters don't support, such as ZIP, RAR, 7Z, and EML.
  • Works with FileTypeRouter to process files in multi-format indexing pipelines.
  • Connects to a running Tika server via a configurable URL.
  • Optional full file path storage in document metadata.

Apache Tika supports:

  • Document formats: MS Office (DOCX, XLSX, PPTX, PPT, RTF), OpenDocument (ODT, ODS, ODP), PDF (with text extraction, no OCR), markup languages (HTML, XML, XHTML, Markdown), plain text (TXT, CSV, TSV)
  • Archive formats: ZIP, RAR, 7Z, TAR, GZIP, BZIP2
  • Email formats: MDG, EML, MBOX, PST, OST

For the full list of supported formats, see the Tika documentation.

Limitations

  • No OCR support.
  • Requires a running Tika server.

Configuration

  1. Drag the TikaDocumentConverter component onto the canvas from the Component Library.
  2. Click the component to open the configuration panel.
  3. Configure the parameters as needed.

Connections

TikaDocumentConverter accepts a list of file paths or ByteStream objects as input. It outputs a list of converted Haystack documents.

Connect FileTypeRouter to its sources input for multi-format indexing. Connect its documents output to DocumentJoiner to merge with output from other converters, or directly to DocumentSplitter.

Usage Example

In this index, TikaDocumentConverter handles multiple file types including documents, archives, and various formats that other converters might not support.

components:
FileTypeRouter:
type: haystack.components.routers.file_type_router.FileTypeRouter
init_parameters:
mime_types:
- text/plain
- application/pdf
- text/markdown
- text/html
- application/vnd.openxmlformats-officedocument.wordprocessingml.document
- application/vnd.openxmlformats-officedocument.presentationml.presentation
- application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
- text/csv
- application/zip
- application/x-rar-compressed
- application/x-7z-compressed
- message/rfc822
- application/vnd.ms-outlook
additional_mimetypes:
application/vnd.openxmlformats-officedocument.wordprocessingml.document: .docx
application/vnd.openxmlformats-officedocument.presentationml.presentation: .pptx
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet: .xlsx
application/x-rar-compressed: .rar
application/x-7z-compressed: .7z
message/rfc822: .eml
application/vnd.ms-outlook: .msg

TextFileToDocument:
type: haystack.components.converters.txt.TextFileToDocument
init_parameters:
encoding: utf-8
store_full_path: false

PDFMinerToDocument:
type: haystack.components.converters.pdfminer.PDFMinerToDocument
init_parameters:
line_overlap: 0.5
char_margin: 2
line_margin: 0.5
word_margin: 0.1
boxes_flow: 0.5
detect_vertical: true
all_texts: false
store_full_path: false

MarkdownToDocument:
type: haystack.components.converters.markdown.MarkdownToDocument
init_parameters: {}

HTMLToDocument:
type: haystack.components.converters.html.HTMLToDocument
init_parameters:
extraction_kwargs:
output_format: markdown
target_language:
include_tables: true
include_links: true

DOCXToDocument:
type: haystack.components.converters.docx.DOCXToDocument
init_parameters:
link_format: markdown

PPTXToDocument:
type: haystack.components.converters.pptx.PPTXToDocument
init_parameters:
store_full_path: false

XLSXToDocument:
type: haystack.components.converters.xlsx.XLSXToDocument
init_parameters:
store_full_path: false

CSVToDocument:
type: haystack.components.converters.csv.CSVToDocument
init_parameters:
encoding: utf-8
store_full_path: false

TikaDocumentConverter:
type: haystack.components.converters.tika.TikaDocumentConverter
init_parameters:
tika_url: http://localhost:9998/tika
store_full_path: false

DocumentJoiner:
type: haystack.components.joiners.document_joiner.DocumentJoiner
init_parameters: {}

DocumentSplitter:
type: haystack.components.preprocessors.document_splitter.DocumentSplitter
init_parameters:
split_by: word
split_length: 1000
split_overlap: 200

DocumentWriter:
type: haystack.components.writers.document_writer.DocumentWriter
init_parameters:
document_store:
type: haystack.document_stores.opensearch.OpenSearchDocumentStore
init_parameters:
host: localhost
port: 9200
username: admin
password:
type: env_var
env_vars:
- OPENSEARCH_PASSWORD
strict: false
index: documents
embedding_dim: 768
similarity: cosine

connections:
- sender: FileTypeRouter.text/plain
receiver: TextFileToDocument.sources
- sender: FileTypeRouter.application/pdf
receiver: PDFMinerToDocument.sources
- sender: FileTypeRouter.text/markdown
receiver: MarkdownToDocument.sources
- sender: FileTypeRouter.text/html
receiver: HTMLToDocument.sources
- sender: FileTypeRouter.application/vnd.openxmlformats-officedocument.wordprocessingml.document
receiver: DOCXToDocument.sources
- sender: FileTypeRouter.application/vnd.openxmlformats-officedocument.presentationml.presentation
receiver: PPTXToDocument.sources
- sender: FileTypeRouter.application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
receiver: XLSXToDocument.sources
- sender: FileTypeRouter.text/csv
receiver: CSVToDocument.sources
- sender: FileTypeRouter.application/zip
receiver: TikaDocumentConverter.sources
- sender: FileTypeRouter.application/x-rar-compressed
receiver: TikaDocumentConverter.sources
- sender: FileTypeRouter.application/x-7z-compressed
receiver: TikaDocumentConverter.sources
- sender: FileTypeRouter.message/rfc822
receiver: TikaDocumentConverter.sources
- sender: FileTypeRouter.application/vnd.ms-outlook
receiver: TikaDocumentConverter.sources
- sender: FileTypeRouter.unclassified
receiver: TikaDocumentConverter.sources
- sender: TextFileToDocument.documents
receiver: DocumentJoiner.documents
- sender: PDFMinerToDocument.documents
receiver: DocumentJoiner.documents
- sender: MarkdownToDocument.documents
receiver: DocumentJoiner.documents
- sender: HTMLToDocument.documents
receiver: DocumentJoiner.documents
- sender: DOCXToDocument.documents
receiver: DocumentJoiner.documents
- sender: PPTXToDocument.documents
receiver: DocumentJoiner.documents
- sender: XLSXToDocument.documents
receiver: DocumentJoiner.documents
- sender: CSVToDocument.documents
receiver: DocumentJoiner.documents
- sender: TikaDocumentConverter.documents
receiver: DocumentJoiner.documents
- sender: DocumentJoiner.documents
receiver: DocumentSplitter.documents
- sender: DocumentSplitter.documents
receiver: DocumentWriter.documents

Parameters

Inputs

ParameterTypeDefaultDescription
sourcesList[Union[str, Path, ByteStream]]List of HTML file paths or ByteStream objects to convert.
metaOptional[Union[Dict[str, Any], List[Dict[str, Any]]]]NoneOptional metadata to attach to the documents. This value can be either a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the metadata of all produced Documents. If it's a list, the length of the list must match the number of sources, because the two lists will be zipped. If sources contains ByteStream objects, their meta will be added to the output Documents.

Outputs

ParameterTypeDefaultDescription
documentsList[Document]Converted documents.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

ParameterTypeDefaultDescription
tika_urlstrhttp://localhost:9998/tikaTika server URL.
store_full_pathboolFalseIf True, the full path of the file is stored in the metadata of the document. If False, only the file name is stored.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

ParameterTypeDefaultDescription
sourcesList[Union[str, Path, ByteStream]]List of HTML file paths or ByteStream objects to convert.
metaOptional[Union[Dict[str, Any], List[Dict[str, Any]]]]NoneOptional metadata to attach to the documents. This value can be either a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the metadata of all produced Documents. If it's a list, the length of the list must match the number of sources, because the two lists will be zipped. If sources contains ByteStream objects, their meta will be added to the output Documents.