UnstructuredFileConverter Parameters

Check the init and runtime parameters you can specify for the UnstructuredFileConverter component.

YAML Init Parameters

These are the parameters you can specify in pipeline YAML:

Parameter

Type

Possible values

Description

api_url

String

Default: UNSTRUCTURED_HOSTED_API_URL

The URL of the Unstructured API. Defaults to the URL of the hosted version. If you're running the API locally, specify the URL of your local API, for example: "http://localhost:8000/general/v0/general"
Required.

api_key

Secret

The API key for the Unstructured API. If you're connected to Unstructured.io through Connections in deepset Cloud, you don't need to specify it.
Optional.

document_creation_mode

Literal

one-doc-per-file
one-doc-per-page
one-doc-per-element
Default: one-doc-per-file

Specifies how to create documents from the content Unstructured returns. Possible values:

  • one-doc-per-file: Creates one document object per file. All elements are concatenated into one text field.
  • one-doc-per-page: Creates one document object per file page. Alle elements on a page are concatenated into one text field.
  • one-doc-per-element: Creates one document object per returned element.
    Required.

separator

String

Default: \n\n

The separator to use between elements when concatenating them into one text field.
Required.

unstructured_kwargs

Dictionary of string and any

Default: None

Additional parameters passed to the Unstructured API. For available parameters, see Unstructured API docs.
Optional.

progress_bar

Boolean

True, False
Default: True

Shows a progress bar during conversion.
Required.


REST API Runtime Parameters

There are no runtime parameters you can pass to this component when making a request to the Search REST API endpoint.