AmazonBedrockChatGenerator

Use chat completion models hosted on Amazon Bedrock. This component supports models from AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon.

Key Features

• Supports chat completion models from multiple providers on Amazon Bedrock.
• Accepts a list of ChatMessage objects as input for multi-turn conversations.
• Supports streaming responses through a configurable callback function.
• Passes custom generation parameters to the underlying model.
• Supports tool use (function calling) for compatible models.
• Works with Haystack Platform's Amazon Bedrock integration.

Configuration

Authentication

To use this component, connect Haystack Platform with Amazon Bedrock first. You need the region name, access key ID, and secret access key. For connection instructions, see the setup guide below.

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

1. Drag the AmazonBedrockChatGenerator component onto the canvas from the Component Library.
2. Click the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name, for example amazon.nova-pro-v1:0.
4. Go to the Advanced tab to configure AWS credentials, generation parameters, streaming callback, and tools.

Connections

AmazonBedrockChatGenerator accepts a list of ChatMessage objects (messages) as input, along with an optional streaming_callback and generation_kwargs.

Connect ChatPromptBuilder to the messages input to provide formatted chat prompts. Connect the replies output to AnswerBuilder or an OutputAdapter to build the final response.

Usage Example

This is an example of a RAG chat pipeline with AmazonBedrockChatGenerator. It receives instructions from ChatPromptBuilder and needs an OutputAdapter to send the generated replies to DeepsetAnswerBuilder:

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

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

  AmazonBedrockChatGenerator:
    type: haystack_integrations.components.generators.amazon_bedrock.chat.chat_generator.AmazonBedrockChatGenerator
    init_parameters:
      model: amazon.nova-pro-v1:0
      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
      generation_kwargs:
      stop_words:
      streaming_callback:
      boto3_config:
      tools:
  ChatPromptBuilder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      template:
      - _content:
        - text: "You are a helpful assistant answering the user's questions based on the provided documents.\nIf the answer is not in the documents, rely on the web_search tool to find information.\nDo not use your own knowledge.\n"
        _role: system
      - _content:
        - text: "Provided documents:\n{% for document in documents %}\nDocument [{{ loop.index }}] :\n{{ document.content }}\n{% endfor %}\n\nQuestion: {{ query }}\n"
        _role: user
      required_variables:
      variables:
  OutputAdapter:
    type: haystack.components.converters.output_adapter.OutputAdapter
    init_parameters:
      template: '{{ replies[0] }}'
      output_type: List[str]
      custom_filters:
      unsafe: false

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: answer_builder.documents
- sender: meta_field_grouping_ranker.documents
  receiver: ChatPromptBuilder.documents
- sender: ChatPromptBuilder.prompt
  receiver: AmazonBedrockChatGenerator.messages
- sender: AmazonBedrockChatGenerator.replies
  receiver: OutputAdapter.replies
- sender: OutputAdapter.output
  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"
  - "answer_builder.query"
  - "ChatPromptBuilder.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

Inputs

Parameter	Type	Default	Description
messages	List[ChatMessage]		A list of ChatMessage objects that form the chat history.
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.
tools	Optional[Union[List[Tool], Toolset]]	None	A list of tools for the model to call.

Outputs

Parameter	Type	Default	Description
replies	List[ChatMessage]		Responses generated by the model.

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.