DocumentTypeRouter

Route documents to different pipeline branches based on their MIME types.

Key Features

• Routes documents by MIME type to separate output connections.
• Supports exact MIME type matching and regex patterns.
• Infers MIME types from document metadata or file path metadata.
• Routes unclassified documents (no matching MIME type) to a dedicated unclassified output.
• Supports custom MIME type mappings for uncommon or proprietary file types.

Configuration

1. Drag the DocumentTypeRouter component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Set MIME Types to the list of MIME types or regex patterns to classify documents (for example, ["text/plain", "application/pdf"]).
   • Set MIME Type Meta Field to the name of the document metadata field that contains the MIME type, if available.
   • Set File Path Meta Field to the name of the document metadata field that contains the file path, if you want the component to infer the MIME type from the file extension.
4. Go to the Advanced tab to set Additional MIME Types, a dictionary mapping MIME types to file extensions for uncommon or custom file types (for example, {"application/vnd.custom-type": ".custom"}).

Connections

DocumentTypeRouter receives a List[Document] from any upstream component. For each MIME type you specify, it creates a named output connection (for example, text/plain or application/pdf). Documents that don't match any MIME type go to the unclassified output. Connect each named output to the appropriate downstream component, such as a specific converter for that file type.

Source Code

To check this component's source code, open document_type_router.py in the Haystack repository.

Usage Examples

Basic Configuration

  DocumentTypeRouter:
    type: haystack.components.routers.document_type_router.DocumentTypeRouter
    init_parameters:
      mime_types:
      - text/plain
      - application/pdf

Parameters

Inputs

Parameter	Type	Description
documents	List[Document]	A list of documents to categorize based on their MIME type.

Outputs

Parameter	Type	Description
unclassified	List[Document]	Documents that don't match any of the specified MIME types.
[mime_type]	List[Document]	Documents matching each specified MIME type (for example, text/plain or application/pdf).

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
mime_types	List[str]		A list of MIME types or regex patterns to classify the input documents (for example, ["text/plain", "audio/x-wav", "image/jpeg"]).
mime_type_meta_field	Optional[str]	None	The name of the metadata field that holds the MIME type.
file_path_meta_field	Optional[str]	None	The name of the metadata field that holds the file path. Used to infer the MIME type if mime_type_meta_field is not provided or missing in a document.
additional_mimetypes	Optional[Dict[str, str]]	None	A dictionary mapping MIME types to file extensions to enhance or override the standard mimetypes module. Useful for uncommon or custom file types. For example: {"application/vnd.custom-type": ".custom"}.

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.

Parameter	Type	Default	Description
documents	List[Document]		A list of documents to categorize based on their MIME type.