aws-sdk-java-v2-bedrock

Name: aws-sdk-java-v2-bedrock
Author: giuseppe-trisciuoglio

1.6kinstalls36forks

How to install aws-sdk-java-v2-bedrock?

giuseppe-trisciuoglio/developer-kit/aws-sdk-java-v2-bedrock

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill aws-sdk-java-v2-bedrock

Installs into the current project.

Summary

Provides Amazon Bedrock patterns using AWS SDK for Java 2.x. Invokes foundation models (Claude, Llama, Titan), generates text and images, creates embeddings for RAG, streams real-time responses, and configures Spring Boot integration. Use when asking about Bedrock integration, Ja

Files · 1

View on GitHub

SKILL.md

1	# AWS SDK for Java 2.x - Amazon Bedrock
2
3	## Overview
4
5	Invokes foundation models through AWS SDK for Java 2.x. Configures clients, builds model-specific JSON payloads, handles streaming responses with error recovery, creates embeddings for RAG, integrates generative AI into Spring Boot applications, and implements exponential backoff for resilience.
6
7	## When to Use
8
9	- Invoke Claude, Llama, Titan, or Stable Diffusion for text/image generation
10	- Configure BedrockClient and BedrockRuntimeClient instances
11	- Build and parse model-specific payloads (Claude, Titan, Llama formats)
12	- Stream real-time AI responses with async handlers and error recovery
13	- Create embeddings for retrieval-augmented generation
14	- Integrate generative AI into Spring Boot microservices
15	- Handle throttling with exponential backoff retry logic
16
17	## Quick Start
18
19	### Dependencies
20
21	```xml
22	<!-- Bedrock (model management) -->
23	<dependency>
24	<groupId>software.amazon.awssdk</groupId>
25	<artifactId>bedrock</artifactId>
26	</dependency>
27
28	<!-- Bedrock Runtime (model invocation) -->
29	<dependency>
30	<groupId>software.amazon.awssdk</groupId>
31	<artifactId>bedrockruntime</artifactId>
32	</dependency>
33
34	<!-- For JSON processing -->
35	<dependency>
36	<groupId>org.json</groupId>
37	<artifactId>json</artifactId>
38	<version>20231013</version>
39	</dependency>
40	```
41
42	### Client Setup
43
44	```java
45	import software.amazon.awssdk.regions.Region;
46	import software.amazon.awssdk.services.bedrock.BedrockClient;
47	import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
48
49	// Model management client
50	BedrockClient bedrockClient = BedrockClient.builder()
51	.region(Region.US_EAST_1)
52	.build();
53
54	// Model invocation client
55	BedrockRuntimeClient bedrockRuntimeClient = BedrockRuntimeClient.builder()
56	.region(Region.US_EAST_1)
57	.build();
58	```
59
60	## Instructions
61
62	Follow these steps for production-ready Bedrock integration:
63
64	1. Configure AWS Credentials - Set up IAM roles with Bedrock permissions (avoid access keys)
65	2. Enable Model Access - Request access to specific foundation models in AWS Console
66	3. Initialize Clients - Create reusable `BedrockClient` and `BedrockRuntimeClient` instances
67	4. Validate Model Availability - Test with a simple invocation before production use
68	5. Build Payloads - Create model-specific JSON payloads with proper format
69	6. Handle Responses - Parse response structure and extract content
70	7. Implement Streaming - Use response stream handlers for real-time generation
71	8. Add Error Handling - Implement retry logic with exponential backoff
72
73	Validation Checkpoint: Always test with a simple prompt (e.g., "Hello") before production use to verify model access and response parsing.
74
75	## Examples
76
77	### Text Generation with Claude
78
79	```java
80	public String generateWithClaude(BedrockRuntimeClient client, String prompt) {
81	JSONObject payload = new JSONObject()
82	.put("anthropic_version", "bedrock-2023-05-31")
83	.put("max_tokens", 1000)
84	.put("messages", new JSONObject[]{
85	new JSONObject().put("role", "user").put("content", prompt)
86	});
87
88	InvokeModelResponse response = client.invokeModel(InvokeModelRequest.builder()
89	.modelId("anthropic.claude-sonnet-4-5-20250929-v1:0")
90	.body(SdkBytes.fromUtf8String(payload.toString()))
91	.build());
92
93	JSONObject responseBody = new JSONObject(response.body().asUtf8String());
94	return responseBody.getJSONArray("content")
95	.getJSONObject(0)
96	.getString("text");
97	}
98	```
99
100	### Model Discovery
101
102	```java
103	import software.amazon.awssdk.services.bedrock.model.*;
104
105	public List<FoundationModelSummary> listFoundationModels(BedrockClient bedrockClient) {
106	return bedrockClient.listFoundationModels().modelSummaries();
107	}
108	```
109
110	### Multi-Model Invocation
111
112	```java
113	public String invokeModel(BedrockRuntimeClient client, String modelId, String prompt) {
114	JSONObject payload = createPayload(modelId, prompt);
115
116	InvokeModelResponse response = client.invokeModel(request -> request
117	.modelId(modelId)
118	.body(SdkBytes.fromUtf8String(payload.toString())));
119
120	return extractTextFromResponse(modelId, response.body().asUtf8String());
121	}
122
123	private JSONObject createPayload(String modelId, String prompt) {
124	if (modelId.startsWith("anthropic.claude")) {
125	return new JSONObject()
126	.put("anthropic_version", "bedrock-2023-05-31")
127	.put("max_tokens", 1000)
128	.put("messages", new JSONObject[]{
129	new

People who liked this also viewed

6 picks

Type

aws-sdk-java-v2-bedrock

1.6kinstalls36forks

View on GitHub

How to install aws-sdk-java-v2-bedrock?

giuseppe-trisciuoglio/developer-kit/aws-sdk-java-v2-bedrock

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill aws-sdk-java-v2-bedrock

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# AWS SDK for Java 2.x - Amazon Bedrock
2
3	## Overview
4
5	Invokes foundation models through AWS SDK for Java 2.x. Configures clients, builds model-specific JSON payloads, handles streaming responses with error recovery, creates embeddings for RAG, integrates generative AI into Spring Boot applications, and implements exponential backoff for resilience.
6
7	## When to Use
8
9	- Invoke Claude, Llama, Titan, or Stable Diffusion for text/image generation
10	- Configure BedrockClient and BedrockRuntimeClient instances
11	- Build and parse model-specific payloads (Claude, Titan, Llama formats)
12	- Stream real-time AI responses with async handlers and error recovery
13	- Create embeddings for retrieval-augmented generation
14	- Integrate generative AI into Spring Boot microservices
15	- Handle throttling with exponential backoff retry logic
16
17	## Quick Start
18
19	### Dependencies
20
21	```xml
22	<!-- Bedrock (model management) -->
23	<dependency>
24	<groupId>software.amazon.awssdk</groupId>
25	<artifactId>bedrock</artifactId>
26	</dependency>
27
28	<!-- Bedrock Runtime (model invocation) -->
29	<dependency>
30	<groupId>software.amazon.awssdk</groupId>
31	<artifactId>bedrockruntime</artifactId>
32	</dependency>
33
34	<!-- For JSON processing -->
35	<dependency>
36	<groupId>org.json</groupId>
37	<artifactId>json</artifactId>
38	<version>20231013</version>
39	</dependency>
40	```
41
42	### Client Setup
43
44	```java
45	import software.amazon.awssdk.regions.Region;
46	import software.amazon.awssdk.services.bedrock.BedrockClient;
47	import software.amazon.awssdk.services.bedrockruntime.BedrockRuntimeClient;
48
49	// Model management client
50	BedrockClient bedrockClient = BedrockClient.builder()
51	.region(Region.US_EAST_1)
52	.build();
53
54	// Model invocation client
55	BedrockRuntimeClient bedrockRuntimeClient = BedrockRuntimeClient.builder()
56	.region(Region.US_EAST_1)
57	.build();
58	```
59
60	## Instructions
61
62	Follow these steps for production-ready Bedrock integration:
63
64	1. Configure AWS Credentials - Set up IAM roles with Bedrock permissions (avoid access keys)
65	2. Enable Model Access - Request access to specific foundation models in AWS Console
66	3. Initialize Clients - Create reusable `BedrockClient` and `BedrockRuntimeClient` instances
67	4. Validate Model Availability - Test with a simple invocation before production use
68	5. Build Payloads - Create model-specific JSON payloads with proper format
69	6. Handle Responses - Parse response structure and extract content
70	7. Implement Streaming - Use response stream handlers for real-time generation
71	8. Add Error Handling - Implement retry logic with exponential backoff
72
73	Validation Checkpoint: Always test with a simple prompt (e.g., "Hello") before production use to verify model access and response parsing.
74
75	## Examples
76
77	### Text Generation with Claude
78
79	```java
80	public String generateWithClaude(BedrockRuntimeClient client, String prompt) {
81	JSONObject payload = new JSONObject()
82	.put("anthropic_version", "bedrock-2023-05-31")
83	.put("max_tokens", 1000)
84	.put("messages", new JSONObject[]{
85	new JSONObject().put("role", "user").put("content", prompt)
86	});
87
88	InvokeModelResponse response = client.invokeModel(InvokeModelRequest.builder()
89	.modelId("anthropic.claude-sonnet-4-5-20250929-v1:0")
90	.body(SdkBytes.fromUtf8String(payload.toString()))
91	.build());
92
93	JSONObject responseBody = new JSONObject(response.body().asUtf8String());
94	return responseBody.getJSONArray("content")
95	.getJSONObject(0)
96	.getString("text");
97	}
98	```
99
100	### Model Discovery
101
102	```java
103	import software.amazon.awssdk.services.bedrock.model.*;
104
105	public List<FoundationModelSummary> listFoundationModels(BedrockClient bedrockClient) {
106	return bedrockClient.listFoundationModels().modelSummaries();
107	}
108	```
109
110	### Multi-Model Invocation
111
112	```java
113	public String invokeModel(BedrockRuntimeClient client, String modelId, String prompt) {
114	JSONObject payload = createPayload(modelId, prompt);
115
116	InvokeModelResponse response = client.invokeModel(request -> request
117	.modelId(modelId)
118	.body(SdkBytes.fromUtf8String(payload.toString())));
119
120	return extractTextFromResponse(modelId, response.body().asUtf8String());
121	}
122
123	private JSONObject createPayload(String modelId, String prompt) {
124	if (modelId.startsWith("anthropic.claude")) {
125	return new JSONObject()
126	.put("anthropic_version", "bedrock-2023-05-31")
127	.put("max_tokens", 1000)
128	.put("messages", new JSONObject[]{
129	new

People who liked this also viewed

6 picks

Type