AWS Bedrock Agent Sink
Provided by: "Apache Software Foundation"
Support Level for this Kamelet is: "Preview"
Starts, lists or looks up the ingestion jobs of an Amazon Bedrock knowledge base, which load the documents of a data source, such as an S3 bucket, into the knowledge base.
Use it to refresh a knowledge base after its documents changed, for example to start an ingestion job when new files arrive in the bucket of the data source, or every night from timer-source, and to check how the job went. To ask questions of the knowledge base, use aws-bedrock-agent-runtime-sink.
Input: the body is not used. For getIngestionJob, the CamelAwsBedrockAgentIngestionJobId header is the ID of the job to look up, and is required.
Output: when it is used inside a route, the body afterwards depends on the operation: for startIngestionJob the ID of the new job, as text; for listIngestionJobs a List of job summaries; for getIngestionJob the job, an object of the AWS SDK for Java, with its status, such as IN_PROGRESS, COMPLETE or FAILED, also in the CamelAwsBedrockAgentIngestionJobStatus header.
Good to know: an ingestion job runs in the background, and startIngestionJob returns at once; to follow it, copy the ID from the body into the CamelAwsBedrockAgentIngestionJobId header and use getIngestionJob. The operation, the knowledge base and the data source come only from the options; headers cannot change them. To reach AWS through an HTTP proxy, set proxyHost and proxyPort, and set proxyProtocol to HTTP for a proxy that takes plain HTTP, such as Squid.
Configuration Options
The following table summarizes the configuration options available for the aws-bedrock-agent-sink Kamelet:
| Property | Name | Description | Type | Default | Example |
|---|---|---|---|---|---|
Data Source ID | Required The ID of the data source of the knowledge base whose documents are loaded, a code of 10 letters and digits shown in the Bedrock console. Needed by all three operations. | string | GH56IJ78KL | ||
Knowledge Base ID | Required The ID of the knowledge base, a code of 10 letters and digits shown in the Bedrock console. | string | AB12CD34EF | ||
AWS Region | Required The AWS region of the knowledge base, such as Enum values: * us-east-1 * us-east-2 * us-west-2 * us-gov-west-1 * ap-northeast-1 * ap-northeast-2 * ap-south-1 * ap-southeast-1 * ap-southeast-2 * ca-central-1 * eu-central-1 * eu-central-2 * eu-west-1 * eu-west-2 * eu-west-3 * sa-east-1 | string | eu-west-1 | ||
Access Key | The access key ID of an IAM user, which AWS gives when you create an access key for the user (in the AWS console: IAM, Users, Security credentials). Use it together with | string | |||
Operation | What to do: Enum values: * startIngestionJob * listIngestionJobs * getIngestionJob | string | startIngestionJob | ||
Endpoint Overwrite | If true, the requests go to the address in | boolean | false | ||
Profile Credentials Name | The name of the profile to use from the AWS credentials file. Only used when | string | |||
Proxy Host | The host name or IP address of an HTTP proxy to send the calls to AWS through, such as the proxy of a company network. Used only together with | string | proxy.example.com | ||
Proxy Port | The port of the proxy in | integer | 3128 | ||
Proxy Protocol | How to talk to the proxy itself: Enum values: * HTTP * HTTPS | string | HTTP | ||
Secret Key | The secret access key that goes with | string | |||
Session Token | The session token of temporary credentials, which AWS gives together with their access key and secret key. Only used when | string | |||
Overwrite Endpoint URI | The address to send the requests to instead of the usual AWS address, such as | string | http://localhost:4566 | ||
Default Credentials Provider | If true, the credentials are found the way the AWS SDK finds them: from the | boolean | false | ||
Profile Credentials Provider | If true, the credentials are read from a profile of the AWS credentials file ( | boolean | false | ||
Session Credentials | If true, it logs in with temporary credentials, such as those of an assumed IAM role: | boolean | false |
Dependencies
At runtime, the aws-bedrock-agent-sink Kamelet relies upon the presence of the following dependencies:
-
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:aws-bedrock-agent-sink" You can now run it directly through the following command
camel run route.yaml AWS Bedrock Agent Sink Kamelet Description
Operations
This Kamelet manages the data source ingestion jobs of a knowledge base. The operation property selects which one runs:
-
startIngestionJob- kick off an ingestion of the configured data source -
listIngestionJobs- list the ingestion jobs of the knowledge base -
getIngestionJob- look up a single job
Job Id
For the getIngestionJob operation the job id is taken from the CamelAwsBedrockAgentIngestionJobId header, which is the one input this Kamelet deliberately reads from the message. Every other CamelAwsBedrockAgent* header is removed before the call, so an inbound message cannot change the operation, the knowledge base or the data source.
Through an HTTP Proxy
Where AWS can be reached only through an HTTP proxy, as in many company networks, set proxyHost and proxyPort to the proxy. proxyProtocol is how the Kamelet talks to the proxy itself, not to AWS: it is HTTPS when it is not set, so set it to HTTP for a proxy that takes plain HTTP, such as Squid. The calls to AWS stay encrypted, as the proxy only passes them on. The Kamelet has no option for a proxy user or password.
The step that sends to the Kamelet, in a route:
- to:
uri: "kamelet:aws-bedrock-agent-sink"
parameters:
knowledgeBaseId: "AB12CD34EF"
dataSourceId: "GH56IJ78KL"
region: "eu-west-1"
useDefaultCredentialsProvider: true
proxyHost: "proxy.example.com"
proxyPort: 3128
proxyProtocol: "HTTP"