S3Downloader

Download files from AWS S3 buckets to the local filesystem. Use this component in indexes when your documents reference files stored in S3 that need to be processed locally.

Key Features

• Downloads files from Amazon S3 buckets for pipeline processing.
• Supports concurrent downloads with a configurable number of workers.
• File extension filtering to download only specific file types.
• Caches downloaded files to improve performance on repeated runs.
• Supports custom S3 key generation functions for flexible file path mapping.

Configuration

Authentication

To use this component, you need AWS credentials. Connect Haystack Platform to your AWS account by creating secrets with the following keys: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_DEFAULT_REGION.

For details on how to create secrets, see Add Secrets.

1. Drag the S3Downloader component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. Configure the parameters as needed. You can set the AWS credentials, file root path, file extensions, and other parameters directly or through environment variables.

Connections

S3Downloader accepts a list of documents with S3 file references in their metadata as input. It outputs a list of documents with the file_path metadata updated to point to the downloaded local files.

Connect a converter like MultiFileConverter to the documents input to provide file references. Connect the documents output to a cleaner or splitter for further processing.

Usage Example

This is an example indexing pipeline with S3Downloader to download and process files from S3:

components:
  s3_downloader:
    type: haystack_integrations.components.downloaders.s3.s3_downloader.S3Downloader
    init_parameters:
      aws_access_key_id:
        type: env_var
        env_vars:
        - AWS_ACCESS_KEY_ID
        strict: false
      aws_secret_access_key:
        type: env_var
        env_vars:
        - AWS_SECRET_ACCESS_KEY
        strict: false
      aws_session_token:
        type: env_var
        env_vars:
        - AWS_SESSION_TOKEN
        strict: false
      aws_region_name:
        type: env_var
        env_vars:
        - AWS_DEFAULT_REGION
        strict: false
      aws_profile_name:
        type: env_var
        env_vars:
        - AWS_PROFILE
        strict: false
      boto3_config:
      file_root_path:
      file_extensions:
      - .pdf
      - .txt
      - .docx
      - .html
      file_name_meta_key: file_name
      max_workers: 32
      max_cache_size: 100
      s3_key_generation_function: deepset_cloud_custom_nodes.utils.storage.get_s3_key

  converter:
    type: haystack.components.converters.multi_file_converter.MultiFileConverter
    init_parameters:
      encoding: utf-8

  cleaner:
    type: haystack.components.preprocessors.document_cleaner.DocumentCleaner
    init_parameters:
      remove_empty_lines: true
      remove_extra_whitespaces: true
      remove_repeated_substrings: false
      keep_id: false

  splitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: sentence
      split_length: 5
      split_overlap: 1
      split_threshold: 0

  document_embedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.document_embedder.DeepsetNvidiaDocumentEmbedder
    init_parameters:
      model: intfloat/e5-base-v2
      normalize_embeddings: true

  writer:
    type: haystack.components.writers.document_writer.DocumentWriter
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'default'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      policy: OVERWRITE

connections:
- sender: cleaner.documents
  receiver: splitter.documents
- sender: splitter.documents
  receiver: document_embedder.documents
- sender: document_embedder.documents
  receiver: writer.documents
- sender: converter.documents
  receiver: s3_downloader.documents
- sender: s3_downloader.documents
  receiver: cleaner.documents

max_runs_per_component: 100

metadata: {}

inputs:
  files:
  - converter.sources

Parameters

Inputs

Parameter	Type	Default	Description
documents	List[Document]		A list of documents with S3 file references in their metadata.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		Documents with the file_path metadata updated to point to the downloaded local files.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
aws_access_key_id	Optional[Secret]	Secret.from_env_var('AWS_ACCESS_KEY_ID')	AWS access key ID.
aws_secret_access_key	Optional[Secret]	Secret.from_env_var('AWS_SECRET_ACCESS_KEY')	AWS secret access key.
aws_session_token	Optional[Secret]	Secret.from_env_var('AWS_SESSION_TOKEN')	AWS session token for temporary credentials.
aws_region_name	Optional[Secret]	Secret.from_env_var('AWS_DEFAULT_REGION')	AWS region name.
aws_profile_name	Optional[Secret]	Secret.from_env_var('AWS_PROFILE')	AWS profile name.
boto3_config	Optional[Dict[str, Any]]	None	Configuration for the boto3 client.
file_root_path	Optional[str]	None	The path where files are downloaded. Can be set through this parameter or the FILE_ROOT_PATH environment variable. If the specified directory doesn't exits, it's created.
file_extensions	Optional[List[str]]	None	File extensions permitted for download. By default, all file extensions are allowed.
file_name_meta_key	str	"file_name"	The metadata key that contains the file name to download.
max_workers	int	32	Maximum number of workers for concurrent downloads.
max_cache_size	int	100	Maximum number of files to cache.
s3_key_generation_function	Optional[Callable]	None	A function to generate S3 keys from documents.

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 with S3 file references in their metadata.