Skip to content

Amazon Bedrock

Amazon Bedrock connects your flows to the AI models Amazon Bedrock offers in your AWS account. You can use it in two ways: as the model of an agent, by connecting its Model output to the agent’s Model input, or on its own, so that it answers the text that reaches its Input.

When to use it

  • Give an agent the model it uses to understand requests, decide which tools to use and answer.
  • Write, summarise or classify texts inside a flow, without an agent.
  • Process a list of texts one by one, for example all the reviews of a month, with Batch Mode.
  • Use the models contracted in your company’s AWS account.

Configuration

In the Common tab:

FieldWhat it does
Model IDThe model that answers. Choose it from the list; use a text model. Default: anthropic.claude-3-haiku-20240307-v1:0.
Credential (required)The credential of the service Amazon Bedrock API. Pick one from the list (Choose an option) or create one with Add new credential. See Credentials.

The AWS region and the access keys are stored in the credential.

ConnectionWhat to connect
InputThe text the model must answer when it works on its own, for example the message of a Chat Input or the result of a Prompt.

Advanced options

In the Advanced tab:

FieldWhat it does
System MessageGeneral instructions for the model when it works on its own: its role, the tone, what to avoid. You can type them or connect them from another component.
StreamShows the answer in the chat while it is being written, instead of waiting until it is finished. It only has an effect in the chat. Default: off.
Endpoint URLA custom address for the service, if your company uses one. Leave it empty to use AWS’s.
Other optionsModel Kwargs: fine-tuning settings for advanced users. Leave them as they are if you don’t need them.

Batch processing

With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.

Output

OutputWhat it contains
ModelThe configured model. It sits at the top of the component. Connect it to the Model input of an agent or of any other component that asks for a model.
TextThe model’s answer to the text received in Input. Connect it, for example, to a Chat Output or to another component that works with text.

The two ways of using it exclude each other: when you connect the Model output, the component hides Input and Text, because the model now works inside the other component; and if you connect Input, Model is hidden.

Example

The Hoteles Mirador chain runs on AWS. It connects Amazon Bedrock to the Model input of an agent that answers guests, chooses the credential with its account keys and keeps the default model.

Good practices

  • Use a low Temperature when you need exact answers, such as classifying or extracting data, and raise it for more creative texts.
  • If you use the model with an agent, configure only the model here: the instructions and the tools are set in the agent.