DeepsetSourceToBase64Image

Convert file sources directly to base64-encoded images.

Deprecation Notice

This component is deprecated. It will continue to work in your existing pipelines for now.

Key Features

• Converts file sources (such as image files) directly to base64-encoded Base64Image objects.
• Configurable detail level (auto, low, or high) for image processing.
• Used in visual question answering pipelines to prepare images for vision-capable generators.

Configuration

1. Drag the DeepsetSourceToBase64Image component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab, configure the Detail level: auto (default), low, or high.
4. Go to the Advanced tab to configure additional settings.

Connections

DeepsetSourceToBase64Image receives file sources through its input and outputs a list of Base64Image objects. You typically connect its output to a vision-capable Generator or to Base64ImageJoiner when combining images from multiple sources.

Usage Examples

Basic Configuration

  DeepsetSourceToBase64Image:
    type: deepset_cloud_custom_nodes.converters.file_to_image.DeepsetSourceToBase64Image
    init_parameters: {}

Using the Component in a Pipeline

This example converts uploaded image files to base64 for a vision pipeline:

# haystack-pipeline
components:
  source_to_image:
    type: deepset_cloud_custom_nodes.converters.file_to_image.DeepsetSourceToBase64Image
    init_parameters:
      detail: auto

inputs:
  sources:
  - source_to_image.sources

outputs:
  base64_images: source_to_image.base64_images

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Description
sources	List[Union[str, Path, ByteStream]]	A list of file sources to convert to base64-encoded images.

Outputs

Parameter	Type	Description
base64_images	List[Base64Image]	A list of base64-encoded images.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
detail	Literal['auto', 'low', 'high']	auto	Controls how the model processes the image and generates its textual understanding. Choose high for best results and low for lowest inference costs.

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
sources	List[Union[str, Path, ByteStream]]		A list of file sources to convert to base64-encoded images.