AmazonBedrockDocumentEmbedder

Calculate document embeddings using models through Amazon Bedrock API.

Basic Information

• Type: haystack_integrations.components.embedders.amazon_bedrock.document_embedder.AmazonBedrockDocumentEmbedder
• Components it can connect with:
  • Preprocessors: AmazonBedrockDocumentEmbedder can receive documents to embed from a Preprocessor, like DocumentSplitter.
  • DocumentWriter: AmazonBedrockDocumentEmbedder can send embedded documents to DocumentWriter that writes them into the document store.

Inputs

Parameter	Type	Default	Description
documents	List[Document]		The documents to embed.

Outputs

Parameter	Type	Default	Description
documents	List[Document]		The documents with the embedding field populated with the calculated embedding.

Overview

Amazon Bedrock is a fully managed service that makes state-of-the-art language models available for use through a unified API. To learn more, see Amazon Bedrock documentation.

You can use this component with the following models:

• amazon.titan-embed-text-v1
• cohere.embed-english-v3
• cohere.embed-multilingual-v3
• amazon.titan-embed-text-v2:0

Embedding Models in Query Pipelines and Indexes

The embedding model you use to embed documents in your indexing pipeline must be the same as the embedding model you use to embed the query in your query pipeline.

This means the embedders for your indexing and query pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

Batch Computing

Only Cohere models support computing embeddings for more documents with the same request.

Use AmazonBedrockDocumentEmbedder to embed a list of documents. To embed a string, such as user query, use AmazonBedrockTextEmbedder.

Authentication

To use this component, connect deepset with Amazon Bedrock first. You'll need:

• The region name
• Access key ID
• Secret access key

Connection Instructions

1. Click your profile icon in the top right corner and choose Integrations.
   
2. Click Connect next to the provider.
3. Enter your API key and submit it.

For detailed explanation, see Use Amazon Bedrock and SageMaker Models.

Embedding Document Metadata

You can embed documents' metadata along with the document text. This is useful if the metadata are semantically meaningful and embedding them can improve retrieval. To do this, list the fields to embed in the meta_fields_to_embed parameter:

Usage Example

Initializing the Component

components:
  AmazonBedrockDocumentEmbedder:
    type: amazon_bedrock.src.haystack_integrations.components.embedders.amazon_bedrock.document_embedder.AmazonBedrockDocumentEmbedder
    init_parameters:

Using the Component in an Index

This is an example of a standard English index where AmazonBedrockDocumentEmbedder receives the documents from DocumentJoiner and sends them to DocumentWriter. It also has a list of metadata fields to embed:

# If you need help with the YAML format, have a look at https://docs.cloud.deepset.ai/v2.0/docs/create-a-pipeline#create-a-pipeline-using-pipeline-editor.
# This section defines components that you want to use in your pipelines. Each component must have a name and a type. You can also set the component's parameters here.
# The name is up to you, you can give your component a friendly name. You then use components' names when specifying the connections in the pipeline.
# Type is the class path of the component. You can check the type on the component's documentation page.
components:
  file_classifier:
    type: haystack.components.routers.file_type_router.FileTypeRouter
    init_parameters:
      mime_types:
      - text/plain
      - application/pdf
      - text/markdown
      - text/html
      - application/vnd.openxmlformats-officedocument.wordprocessingml.document
      - application/vnd.openxmlformats-officedocument.presentationml.presentation
      - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
      - text/csv

  text_converter:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8

  pdf_converter:
    type: haystack.components.converters.pdfminer.PDFMinerToDocument
    init_parameters:
      line_overlap: 0.5
      char_margin: 2
      line_margin: 0.5
      word_margin: 0.1
      boxes_flow: 0.5
      detect_vertical: true
      all_texts: false
      store_full_path: false

  markdown_converter:
    type: haystack.components.converters.txt.TextFileToDocument
    init_parameters:
      encoding: utf-8

  html_converter:
    type: haystack.components.converters.html.HTMLToDocument
    init_parameters:
      # A dictionary of keyword arguments to customize how you want to extract content from your HTML files.
      # For the full list of available arguments, see
      # the [Trafilatura documentation](https://trafilatura.readthedocs.io/en/latest/corefunctions.html#extract).
      extraction_kwargs:
        output_format: markdown # Extract text from HTML. You can also also choose "txt"
        target_language:       # You can define a language (using the ISO 639-1 format) to discard documents that don't match that language.
        include_tables: true  # If true, includes tables in the output
        include_links: true  # If true, keeps links along with their targets

  docx_converter:
    type: haystack.components.converters.docx.DOCXToDocument
    init_parameters:
      link_format: markdown

  pptx_converter:
    type: haystack.components.converters.pptx.PPTXToDocument
    init_parameters: {}

  xlsx_converter:
    type: haystack.components.converters.xlsx.XLSXToDocument
    init_parameters: {}

  csv_converter:
    type: haystack.components.converters.csv.CSVToDocument
    init_parameters:
      encoding: utf-8

  joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      sort_by_score: false

  joiner_xlsx:  # merge split documents with non-split xlsx documents
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
      sort_by_score: false

  splitter:
    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
    init_parameters:
      split_by: word
      split_length: 250
      split_overlap: 30
      respect_sentence_boundary: true
      language: en

  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: ''
          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

  AmazonBedrockDocumentEmbedder:
    type: haystack_integrations.components.embedders.amazon_bedrock.document_embedder.AmazonBedrockDocumentEmbedder
    init_parameters:
      model: amazon.titan-embed-text-v1
      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
      batch_size: 32
      progress_bar: true
      meta_fields_to_embed:
      - title: travelling_in_africa
      - type: guide
      embedding_separator: \n
      boto3_config:

connections:  # Defines how the components are connected
- sender: file_classifier.text/plain
  receiver: text_converter.sources
- sender: file_classifier.application/pdf
  receiver: pdf_converter.sources
- sender: file_classifier.text/markdown
  receiver: markdown_converter.sources
- sender: file_classifier.text/html
  receiver: html_converter.sources
- sender: file_classifier.application/vnd.openxmlformats-officedocument.wordprocessingml.document
  receiver: docx_converter.sources
- sender: file_classifier.application/vnd.openxmlformats-officedocument.presentationml.presentation
  receiver: pptx_converter.sources
- sender: file_classifier.application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
  receiver: xlsx_converter.sources
- sender: file_classifier.text/csv
  receiver: csv_converter.sources
- sender: text_converter.documents
  receiver: joiner.documents
- sender: pdf_converter.documents
  receiver: joiner.documents
- sender: markdown_converter.documents
  receiver: joiner.documents
- sender: html_converter.documents
  receiver: joiner.documents
- sender: docx_converter.documents
  receiver: joiner.documents
- sender: pptx_converter.documents
  receiver: joiner.documents
- sender: joiner.documents
  receiver: splitter.documents
- sender: splitter.documents
  receiver: joiner_xlsx.documents
- sender: xlsx_converter.documents
  receiver: joiner_xlsx.documents
- sender: csv_converter.documents
  receiver: joiner_xlsx.documents
- sender: joiner_xlsx.documents
  receiver: AmazonBedrockDocumentEmbedder.documents
- sender: AmazonBedrockDocumentEmbedder.documents
  receiver: writer.documents

inputs:  # Define the inputs for your pipeline
  files:                            # This component will receive the files to index as input
  - file_classifier.sources

max_runs_per_component: 100

metadata: {}

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	Literal['amazon.titan-embed-text-v1', 'cohere.embed-english-v3', 'cohere.embed-multilingual-v3', 'amazon.titan-embed-text-v2:0']		The embedding model to use. Choose the model from the list on the component card.
aws_access_key_id	Optional[Secret]	Secret.from_env_var('AWS_ACCESS_KEY_ID', strict=False)	AWS access key ID. Connect deepset to Amazon Bedrock on the Integrations page.
aws_secret_access_key	Optional[Secret]	Secret.from_env_var('AWS_SECRET_ACCESS_KEY', strict=False)	AWS secret access key. Connect deepset to Amazon Bedrock on the Integrations page.
aws_session_token	Optional[Secret]	Secret.from_env_var('AWS_SESSION_TOKEN', strict=False)	AWS session token. Connect deepset to Amazon Bedrock on the Integrations page.
aws_region_name	Optional[Secret]	Secret.from_env_var('AWS_DEFAULT_REGION', strict=False)	AWS region name. Connect deepset to Amazon Bedrock on the Integrations page.
aws_profile_name	Optional[Secret]	Secret.from_env_var('AWS_PROFILE', strict=False)	AWS profile name. Connect deepset to Amazon Bedrock on the Integrations page.
batch_size	int	32	Number of documents to embed at once. Only Cohere models support batch inference. This parameter is ignored for Amazon Titan models.
progress_bar	bool	True	Shows a progress bar or not. We recommend disabling it in production deployments to keep the logs clean.
meta_fields_to_embed	Optional[List[str]]	None	List of metadata fields to embedd along with the document text.
embedding_separator	str	\n	Separator used to concatenate the metadata fields to the document text.
boto3_config	Optional[Dict[str, Any]]	None	The configuration for the boto3 client.
kwargs	Any		Additional parameters to pass for model inference. For example, input_type and truncate for Cohere models.

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]		The documents to embed.