aws bedrock agent runtime sink AWS Bedrock Agent Runtime Sink

Provided by: "Apache Software Foundation"

Support Level for this Kamelet is: "Stable"

Send data for invoking a knowledge base from AWS Bedrock.

The basic authentication method for the Bedrock service is to specify an access key and a secret key. These parameters are optional because the Kamelet provides a default credentials provider.

If you use the default credentials provider, the Bedrock client loads the credentials through this provider and doesn’t use the basic authentication method.

Configuration Options

The following table summarizes the configuration options available for the aws-bedrock-agent-runtime-sink Kamelet:

Property Name Description Type Default Example

knowledgeBaseId

Knowledge Base Id

Required The Knowledge Base Id to be used to retrieve and generate responses.

string

modelId

Model Id

Required The model Id to be used to generate responses.

Enum values:

* anthropic.claude-instant-v1 * anthropic.claude-v2 * anthropic.claude-v2:1 * anthropic.claude-3-sonnet-20240229-v1:0

string

region

AWS Region

Required The AWS region to access.

Enum values:

* us-east-1 * us-west-1

string

accessKey

Access Key

The access key obtained from AWS.

string

overrideEndpoint

Endpoint Overwrite

Select this option to override the endpoint URI. To use this option, you must also provide a URI for the uriEndpointOverride option.

boolean

false

secretKey

Secret Key

The secret key obtained from AWS.

string

uriEndpointOverride

Overwrite Endpoint URI

The overriding endpoint URI. To use this option, you must also select the overrideEndpoint option.

string

useDefaultCredentialsProvider

Default Credentials Provider

If true, the Bedrock client loads credentials through a default credentials provider. If false, it uses the basic authentication method (access key and secret key).

boolean

false

Dependencies

At runtime, the aws-bedrock-agent-runtime-sink Kamelet relies upon the presence of the following dependencies:

  • camel:core

  • camel:aws-bedrock

  • camel:kamelet

Camel JBang usage

Prerequisites

  • You’ve installed JBang.

  • You have executed the following command:

jbang app install camel@apache/camel

Supposing you have a file named route.yaml with this content:

- route:
    from:
      uri: "kamelet:timer-source"
      parameters:
        period: 10000
        message: 'test'
      steps:
        - to:
            uri: "kamelet:log-sink"

You can now run it directly through the following command

camel run route.yaml

Camel K Environment Usage

This section describes how you can use the aws-bedrock-agent-runtime-sink.

Knative sink

You can use the aws-bedrock-agent-runtime-sink Kamelet as a Knative sink by binding it to a Knative object.

aws-bedrock-agent-runtime-sink-pipe.yaml
apiVersion: camel.apache.org/v1
kind: Pipe
metadata:
  name: aws-bedrock-agent-runtime-sink-pipe
spec:
  source:
    ref:
      kind: Channel
      apiVersion: messaging.knative.dev/v1
      name: mychannel
  sink:
    ref:
      kind: Kamelet
      apiVersion: camel.apache.org/v1
      name: aws-bedrock-agent-runtime-sink
    properties:
      knowledgeBaseId: The Knowledge Base Id
      modelId: The Model Id
      region: The AWS Region

Prerequisite

You have Camel K installed on the cluster.

Procedure for using the cluster CLI

  1. Save the aws-bedrock-agent-runtime-sink-pipe.yaml file to your local drive, and then edit it as needed for your configuration.

  2. Run the sink by using the following command:

    kubectl apply -f aws-bedrock-agent-runtime-sink-pipe.yaml

Procedure for using the Kamel CLI

Configure and run the sink by using the following command:

kamel bind channel:mychannel -p "sink.knowledgeBaseId=The Knowledge Base Id" -p "sink.modelId=The Model Id" -p "sink.region=The AWS Region" aws-bedrock-agent-runtime-sink

This command creates the Kamelet Pipe in the current namespace on the cluster.

Kafka sink

You can use the aws-bedrock-agent-runtime-sink Kamelet as a Kafka sink by binding it to a Kafka topic.

aws-bedrock-agent-runtime-sink-pipe.yaml
apiVersion: camel.apache.org/v1
kind: Pipe
metadata:
  name: aws-bedrock-agent-runtime-sink-pipe
spec:
  source:
    ref:
      kind: KafkaTopic
      apiVersion: kafka.strimzi.io/v1beta1
      name: my-topic
  sink:
    ref:
      kind: Kamelet
      apiVersion: camel.apache.org/v1
      name: aws-bedrock-agent-runtime-sink
    properties:
      knowledgeBaseId: The Knowledge Base Id
      modelId: The Model Id
      region: The AWS Region

Prerequisites

  • You’ve installed Strimzi.

  • You’ve created a topic named my-topic in the current namespace.

  • You have Camel K installed on the cluster.

Procedure for using the cluster CLI

  1. Save the aws-bedrock-agent-runtime-sink-pipe.yaml file to your local drive, and then edit it as needed for your configuration.

  2. Run the sink by using the following command:

    kubectl apply -f aws-bedrock-agent-runtime-sink-pipe.yaml

Procedure for using the Kamel CLI

Configure and run the sink by using the following command:

kamel bind kafka.strimzi.io/v1beta1:KafkaTopic:my-topic -p "sink.knowledgeBaseId=The Knowledge Base Id" -p "sink.modelId=The Model Id" -p "sink.region=The AWS Region" aws-bedrock-agent-runtime-sink

This command creates the Kamelet Pipe in the current namespace on the cluster.