AmazonBedrockKnowledgeBaseRetriever

Retrieve documents from an Amazon Bedrock Managed Knowledge Base using semantic search — no separate document store required.

Key Features

• Connects directly to Amazon Bedrock Knowledge Bases, bypassing the need for a separate document store.
• Supports both the standard Retrieve API and the AgenticRetrieveStream API for richer, agent-compatible results.
• Automatically falls back from AgenticRetrieveStream to the standard Retrieve API when the agentic endpoint is unavailable.
• Returns documents with source URIs extracted from S3, web, Confluence, Salesforce, SharePoint, and custom locations.
• Flexible AWS authentication: access keys, session tokens, IAM roles, or named profiles.
• Configurable number of results at init time, overridable at query time.

Configuration

1. Drag the AmazonBedrockKnowledgeBaseRetriever component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Set the knowledge_base_id to the ID of your Bedrock Knowledge Base. You can also set the AWS_KNOWLEDGE_BASE_ID environment variable instead.
   2. Create secrets with your AWS credentials. For instructions, see Create Secrets. Use these environment variable names:
      • AWS_ACCESS_KEY_ID
      • AWS_SECRET_ACCESS_KEY
      • AWS_DEFAULT_REGION
4. Go to the Advanced tab to configure number_of_results and use_agentic_retrieval.

Connections

AmazonBedrockKnowledgeBaseRetriever receives a text query string as input, typically from the Input component. It outputs a list of retrieved Document objects you can connect to PromptBuilder, a ranker, or AnswerBuilder.

Source Code

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

Usage Examples

Basic Configuration

  AmazonBedrockKnowledgeBaseRetriever:
    type: haystack_integrations.components.retrievers.amazon_bedrock.knowledge_base_retriever.AmazonBedrockKnowledgeBaseRetriever
    init_parameters:
      knowledge_base_id: ABCDEFGHIJ
      number_of_results: 5
      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_region_name:
        type: env_var
        env_vars:
        - AWS_DEFAULT_REGION
        strict: false

Using the Component in a Pipeline

# haystack-pipeline
components:
  retriever:
    type: haystack_integrations.components.retrievers.amazon_bedrock.knowledge_base_retriever.AmazonBedrockKnowledgeBaseRetriever
    init_parameters:
      knowledge_base_id: ABCDEFGHIJ
      number_of_results: 5
      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_region_name:
        type: env_var
        env_vars:
        - AWS_DEFAULT_REGION
        strict: false

  prompt_builder:
    type: haystack.components.builders.chat_prompt_builder.ChatPromptBuilder
    init_parameters:
      required_variables: "*"
      template:
      - role: system
        content: Answer questions based on the provided documents.
      - role: user
        content: |
          Documents:
          {% for doc in documents %}
          {{ doc.content }}
          {% endfor %}
          Question: {{ question }}

  llm:
    type: haystack_integrations.components.generators.amazon_bedrock.chat.chat_generator.AmazonBedrockChatGenerator
    init_parameters:
      model: global.anthropic.claude-sonnet-4-6
      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

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

connections:
- sender: retriever.documents
  receiver: prompt_builder.documents
- sender: prompt_builder.prompt
  receiver: llm.messages
- sender: llm.replies
  receiver: answer_builder.replies

max_runs_per_component: 100

metadata: {}

inputs:
  query:
  - retriever.query
  - prompt_builder.question
  - answer_builder.query

outputs:
  answers: answer_builder.answers

Parameters

Inputs

Parameter	Type	Description
query	str	The search query to run against the Knowledge Base.
top_k	Optional[int]	Maximum number of documents to return. Overrides number_of_results when provided.

Outputs

Parameter	Type	Description
documents	List[Document]	The retrieved documents. Each document includes a source URI and a relevance score in its metadata.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
knowledge_base_id	str		The ID of the Bedrock Knowledge Base. Falls back to the AWS_KNOWLEDGE_BASE_ID environment variable.
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 for temporary credentials.
aws_region_name	Optional[Secret or str]	Secret.from_env_var("AWS_DEFAULT_REGION", strict=False)	The AWS region. Required when using region-specific Knowledge Bases.
aws_profile_name	Optional[Secret]	Secret.from_env_var("AWS_PROFILE", strict=False)	The AWS named profile to use for authentication.
number_of_results	int	5	Maximum number of documents to return per query.
use_agentic_retrieval	Optional[bool]	True	When True, the component tries AgenticRetrieveStream first and falls back to the standard Retrieve API. Defaults to the USE_AGENTIC_RETRIEVAL environment variable.

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
query	str		The search query to run against the Knowledge Base.
top_k	Optional[int]	None	Override the init-time number_of_results for this request.

Related Information

• AmazonBedrockChatGenerator
• AmazonBedrockTextEmbedder
• Pipeline Components