AmazonBedrockGenerator

Generate text using models hosted on Amazon Bedrock.

Basic Information

Type: haystack_integrations.components.generators.amazon_bedrock.generator.AmazonBedrockGenerator
Components it can connect with:
- PromptBuilder: AmazonBedrockGenerator receives instructions and optionally also documents from PromptBuilder.
- AnswerBuilder: AmazonBedrockGenerator sends the generated replies to AnswerBuilder, which uses them to build the final output.

Inputs

Parameter	Type	Default	Description
prompt	str		The prompt with instructions for the model.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	A callback function to invoke when the model starts streaming responses.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments passed to the model.

Outputs

Parameter	Type	Default	Description
replies	List[str]		Responses generated by the model.
meta	Dict[str, Any]		Metadata related to the response.

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.

With AmazonBedrockGenerator, you can generate text using models from AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon. The models currently supported are:

Anthropic's Claude
AI21 Labs' Jurassic-2
Stability AI's Stable Diffusion
Cohere's Command
Meta's Llama 2
Amazon Titan

Authentication

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

The region name
Access key ID
Secret access key

Add Workspace-Level Integration

Click your profile icon and choose Settings.
Go to Workspace>Integrations.
Find the provider you want to connect and click Connect next to them.
Enter the API key and any other required details.
Click Connect. You can use this integration in pipelines and indexes in the current workspace.

Add Organization-Level Integration

Click your profile icon and choose Settings.
Go to Organization>Integrations.
Find the provider you want to connect and click Connect next to them.
Enter the API key and any other required details.
Click Connect. You can use this integration in pipelines and indexes in all workspaces in the current organization.

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

Usage Example

Initializing the Component

components:
  AmazonBedrockGenerator:
    type: amazon_bedrock.src.haystack_integrations.components.generators.amazon_bedrock.generator.AmazonBedrockGenerator
    init_parameters:

Using the Component in a Pipeline

This is a RAG chat pipeline that uses AmazonBedrockGenerator:

# 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:
  bm25_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.bm25_retriever.OpenSearchBM25Retriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'Standard-Index-English'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return
      fuzziness: 0

  query_embedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
    init_parameters:
      normalize_embeddings: true
      model: intfloat/e5-base-v2

  embedding_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          hosts:
          index: 'Standard-Index-English'
          max_chunk_bytes: 104857600
          embedding_dim: 768
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          http_auth:
          use_ssl:
          verify_certs:
          timeout:
      top_k: 20 # The number of results to return

  document_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: intfloat/simlm-msmarco-reranker
      top_k: 8

  meta_field_grouping_ranker:
    type: haystack.components.rankers.meta_field_grouping_ranker.MetaFieldGroupingRanker
    init_parameters:
      group_by: file_id
      subgroup_by:
      sort_docs_by: split_id

  prompt_builder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: |-
        You are a technical expert.
        You answer questions truthfully based on provided documents.
        If the answer exists in several documents, summarize them.
        Ignore documents that don't contain the answer to the question.
        Only answer based on the documents provided. Don't make things up.
        If no information related to the question can be found in the document, say so.
        Always use references in the form [NUMBER OF DOCUMENT] when using information from a document, e.g. [3] for Document [3] .
        Never name the documents, only enter a number in square brackets as a reference.
        The reference must only refer to the number that comes in square brackets after the document.
        Otherwise, do not use brackets in your answer and reference ONLY the number of the document without mentioning the word document.

        These are the documents:
        {%- if documents|length > 0 %}
        {%- for document in documents %}
        Document [{{ loop.index }}] :
        Name of Source File: {{ document.meta.file_name }}
        {{ document.content }}
        {% endfor -%}
        {%- else %}
        No relevant documents found.
        Respond with "Sorry, no matching documents were found, please adjust the filters or try a different question."
        {% endif %}

        Question: {{ question }}
        Answer:

      required_variables: "*"
  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

  AmazonBedrockGenerator:
    type: haystack_integrations.components.generators.amazon_bedrock.generator.AmazonBedrockGenerator
    init_parameters:
      model: anthropic.claude-3-5-sonnet-20241022-v2:0
      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
      max_length:
      truncate:
      streaming_callback:
      boto3_config:
      model_family:

connections:  # Defines how the components are connected
- sender: bm25_retriever.documents
  receiver: document_joiner.documents
- sender: query_embedder.embedding
  receiver: embedding_retriever.query_embedding
- sender: embedding_retriever.documents
  receiver: document_joiner.documents
- sender: document_joiner.documents
  receiver: ranker.documents
- sender: ranker.documents
  receiver: meta_field_grouping_ranker.documents
- sender: meta_field_grouping_ranker.documents
  receiver: prompt_builder.documents
- sender: meta_field_grouping_ranker.documents
  receiver: answer_builder.documents
- sender: prompt_builder.prompt
  receiver: answer_builder.prompt
- sender: prompt_builder.prompt
  receiver: AmazonBedrockGenerator.prompt
- sender: AmazonBedrockGenerator.replies
  receiver: answer_builder.replies

inputs:  # Define the inputs for your pipeline
  query:  # These components will receive the query as input
  - "bm25_retriever.query"
  - "query_embedder.text"
  - "ranker.query"
  - "prompt_builder.question"
  - "answer_builder.query"

  filters:  # These components will receive a potential query filter as input
  - "bm25_retriever.filters"
  - "embedding_retriever.filters"

outputs:  # Defines the output of your pipeline
  documents: "meta_field_grouping_ranker.documents"  # The output of the pipeline is the retrieved documents
  answers: "answer_builder.answers"  # The output of the pipeline is the generated answers

max_runs_per_component: 100

metadata: {}

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
model	str		The name of the model to use.
aws_access_key_id	Optional[Secret]	Secret.from_env_var('AWS_ACCESS_KEY_ID', strict=False)	The AWS access key ID.
aws_secret_access_key	Optional[Secret]	Secret.from_env_var('AWS_SECRET_ACCESS_KEY', strict=False)	The AWS secret access key.
aws_session_token	Optional[Secret]	Secret.from_env_var('AWS_SESSION_TOKEN', strict=False)	The AWS session token.
aws_region_name	Optional[Secret]	Secret.from_env_var('AWS_DEFAULT_REGION', strict=False)	The AWS region name. Make sure the region you set supports Amazon Bedrock.
aws_profile_name	Optional[Secret]	Secret.from_env_var('AWS_PROFILE', strict=False)	The AWS profile name.
max_length	Optional[int]	None	The maximum length of the generated text. This can also be set in the `kwargs` parameter by using the model specific parameter name.
truncate	Optional[bool]	None	Deprecated. This parameter no longer has any effect.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	A callback function that is called when a new token is received from the stream. The callback function accepts StreamingChunk as an argument.
boto3_config	Optional[Dict[str, Any]]	None	The configuration for the boto3 client.
model_family	Optional[MODEL_FAMILIES]	None	The model family to use. If not provided, the model adapter is selected based on the model name.
kwargs	Any		Additional keyword arguments to be passed to the model. You can find the model specific arguments in AWS Bedrock's documentation. These arguments are specific to the model. You can find them in the model's documentation.

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
prompt	str		The prompt to generate a response for.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	A callback function that is called when a new token is received from the stream.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments passed to the generator.

Was this page helpful?

Basic Information​

Inputs​

Outputs​

Overview​

Authentication​

Add Workspace-Level Integration​

Add Organization-Level Integration​

Usage Example​

Initializing the Component​

Using the Component in a Pipeline​

Parameters​

Init Parameters​

Run Method Parameters​