AActionAWS BedrockUpdated September 2026

How do I run RAG retrieval against a Bedrock Knowledge Base?

Short answer: You can knowledge bases retrieve in AWS Bedrock by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the AWS Bedrock Knowledge Bases Retrieve action to a workflow, map its 3 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Knowledge Bases Retrieve in AWS Bedrock — start free All 3 AWS Bedrock actions

Knowledge Bases Retrieve in AWS Bedrock — start free

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Knowledge Base ID knowledge_base_id	string	Required	Knowledge Base ID (required)
Query query	string	Required	Query (required)
Number of Results number_of_results	string	Optional	Number of Results

Sample request

{
  "knowledge_base_id": "{{trigger.knowledge_base_id}}",
  "query": "{{trigger.query}}",
  "number_of_results": "{{trigger.number_of_results}}"
}

Returns

{
  "retrievalResults": [
    {
      "score": 0.91,
      "content": {
        "text": "..."
      },
      "location": {
        "type": "S3",
        "s3Location": {
          "uri": "s3://x/y"
        }
      }
    }
  ]
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Knowledge Bases Retrieve.

Any of these apps can fire this action as part of a workflow.

Google Sheets → AWS Bedrock

2 Google Sheets triggers

HubSpot → AWS Bedrock

18 HubSpot triggers

FAQ

Questions about Knowledge Bases Retrieve.

What does the Knowledge Bases Retrieve action do in AWS Bedrock?

Semantic-searches a configured Bedrock Knowledge Base (which sits on top of S3-stored documents indexed into a vector store) and returns the most relevant chunks with citations. Saves you from building and managing your own RAG ingestion pipeline.

What inputs does Knowledge Bases Retrieve require?

Required: Knowledge Base ID, Query. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if AWS Bedrock returns an error?

The run history shows the failed step with its input and the error message AWS Bedrock returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.

Does Knowledge Bases Retrieve support batch operations?

Run Knowledge Bases Retrieve inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within AWS Bedrock's rate limits.

More actions

Other AWS Bedrock actions.

Action

Bedrock Converse

The model-agnostic chat API — same message-array shape works across Claude, Llama, Mistral, and other chat-capable Bedrock models. Swap models with a single parameter change. The recommended default for new Bedrock workflows since it abstracts away model-specific request quirks.

Action

Invoke Model (Raw)

Model-specific Invoke API for cases where the unified Converse API doesn't expose what you need (e.g., specific Claude-only parameters, specific generation modes for image/embedding models). Each model has its own request shape — check Bedrock's per-model docs.

Knowledge Bases Retrieve in AWS Bedrock — start free