FileToFileContent

Converts local files into FileContent objects that can be embedded into ChatMessage objects and passed to an LLM.

FileContent objects contain the base64-encoded file data, MIME type, and filename. The component automatically detects the MIME type of each file. Empty files are skipped with a warning.

Key Features

• Converts files of any supported format to FileContent objects for direct LLM input.
• Automatically detects MIME types.
• Supports optional extra metadata for provider-specific information.
• Skips empty files gracefully with a warning.

Configuration

1. Drag the FileToFileContent component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.

This component has no init parameters to configure in Pipeline Builder.

Connections

FileToFileContent accepts a list of file paths or ByteStream objects through its sources input. It outputs a list of FileContent objects.

It typically connects with:

• FileTypeRouter: receives files routed by MIME type.
• ChatPromptBuilder: sends FileContent objects for inclusion in chat messages to an LLM.

Source Code

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

Usage Examples

Basic Configuration

  FileToFileContent:
    type: haystack.components.converters.file_to_file_content.FileToFileContent
    init_parameters: {}

Using the Component in a Pipeline

In this pipeline, FileToFileContent converts files and passes them to a chat generator through a ChatPromptBuilder:

# haystack-pipeline
components:
  FileToFileContent:
    type: haystack.components.converters.file_to_file_content.FileToFileContent
    init_parameters: {}
  ChatPromptBuilder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      template:
      - _content:
        - text: "Analyze the following files and answer questions about them."
        _role: system
      - _content:
        - text: "{{ query }}"
        _role: user
      required_variables:
      variables:
  ChatGenerator:
    type: haystack.components.generators.chat.openai.OpenAIChatGenerator
    init_parameters:
      model: gpt-4o
      api_key:
        type: env_var
        env_vars:
          - OPENAI_API_KEY
        strict: false

connections:
- sender: FileToFileContent.file_contents
  receiver: ChatPromptBuilder.file_contents
- sender: ChatPromptBuilder.prompt
  receiver: ChatGenerator.messages

inputs:
  files:
  - FileToFileContent.sources
  query:
  - ChatPromptBuilder.query

outputs:
  replies: ChatGenerator.replies

max_runs_per_component: 100

metadata: {}

Parameters

Inputs

Parameter	Type	Default	Description
sources	List[Union[str, Path, ByteStream]]		List of file paths or ByteStream objects to convert.
extra	Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]	None	Optional extra information to attach to the FileContent objects. Can be used to store provider-specific information. Values should be JSON serializable. This value can be a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the extra of all produced FileContent objects. If it's a list, its length must match the number of sources as they're zipped together.

Outputs

Parameter	Type	Description
file_contents	List[FileContent]	A list of FileContent objects created from the input files.

Init Parameters

This component has no init parameters.

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]]		List of file paths or ByteStream objects to convert.
extra	Optional[Union[Dict[str, Any], List[Dict[str, Any]]]]	None	Optional extra information to attach to the FileContent objects. Can be used to store provider-specific information. Values should be JSON serializable. This value can be a list of dictionaries or a single dictionary. If it's a single dictionary, its content is added to the extra of all produced FileContent objects. If it's a list, its length must match the number of sources as they're zipped together.