aws-cloudformation-bedrock

Name: aws-cloudformation-bedrock
Author: giuseppe-trisciuoglio

71installs36forks

How to install aws-cloudformation-bedrock?

giuseppe-trisciuoglio/developer-kit/aws-cloudformation-bedrock

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill aws-cloudformation-bedrock

Installs into the current project.

Summary

Provides AWS CloudFormation patterns for Amazon Bedrock resources including agents, knowledge bases, data sources, guardrails, prompts, flows, and inference profiles. Use when creating Bedrock agents with action groups, implementing RAG with knowledge bases, configuring vector st

Files · 1

View on GitHub

SKILL.md

1	# AWS CloudFormation Amazon Bedrock
2
3	## Overview
4
5	Creates production-ready AI infrastructure using AWS CloudFormation templates for Amazon Bedrock. Covers Bedrock agents, knowledge bases for RAG implementations, data source connectors, guardrails for content moderation, prompt management, workflow orchestration with flows, and inference profiles for optimized model access.
6
7	## When to Use
8
9	- Creating Bedrock agents with action groups
10	- Implementing RAG with knowledge bases
11	- Configuring S3 or web crawl data sources
12	- Setting up content moderation guardrails
13	- Managing prompt templates
14	- Orchestrating AI workflows with Bedrock Flows
15	- Configuring inference profiles for multi-model access
16	- Organizing templates with Parameters and cross-stack references
17
18	## Instructions
19
20	### 1. Define Parameters
21
22	```yaml
23	Parameters:
24	FoundationModel:
25	Type: String
26	Default: anthropic.claude-3-sonnet-20240229-v1:0
27	AllowedValues:
28	- anthropic.claude-3-sonnet-20240229-v1:0
29	- anthropic.claude-3-haiku-20240307-v1:0
30	- amazon.titan-text-express-v1
31	Description: Foundation model for agent
32	```
33
34	### 2. Create Agent Role
35
36	```yaml
37	Resources:
38	AgentRole:
39	Type: AWS::IAM::Role
40	Properties:
41	AssumeRolePolicyDocument:
42	Version: "2012-10-17"
43	Statement:
44	- Effect: Allow
45	Principal:
46	Service: bedrock.amazonaws.com
47	Action: sts:AssumeRole
48	Policies:
49	- PolicyName: BedrockPermissions
50	PolicyDocument:
51	Version: "2012-10-17"
52	Statement:
53	- Effect: Allow
54	Action:
55	- bedrock:InvokeModel
56	Resource: !Sub "arn:aws:bedrock:${AWS::Region}:${AWS::AccountId}:foundation-model/${FoundationModel}"
57	```
58
59	### 3. Create Agent
60
61	```yaml
62	BedrockAgent:
63	Type: AWS::Bedrock::Agent
64	Properties:
65	AgentName: !Sub "${AWS::StackName}-agent"
66	AgentResourceRoleArn: !GetAtt AgentRole.Arn
67	FoundationModelArn: !Sub "arn:aws:bedrock:${AWS::Region}::foundation-model/${FoundationModel}"
68	AutoPrepare: true
69	Instruction: \|
70	You are a helpful assistant. Use the knowledge base to answer questions.
71	```
72
73	### 4. Create Knowledge Base
74
75	```yaml
76	KnowledgeBaseRole:
77	Type: AWS::IAM::Role
78	Properties:
79	AssumeRolePolicyDocument:
80	Version: "2012-10-17"
81	Statement:
82	- Effect: Allow
83	Principal:
84	Service: bedrock.amazonaws.com
85	Action: sts:AssumeRole
86
87	KnowledgeBase:
88	Type: AWS::Bedrock::KnowledgeBase
89	Properties:
90	Name: !Sub "${AWS::StackName}-kb"
91	RoleArn: !GetAtt KnowledgeBaseRole.Arn
92	KnowledgeBaseConfiguration:
93	Type: VECTOR
94	VectorKnowledgeBaseConfiguration:
95	EmbeddingModelArn: !Sub "arn:aws:bedrock:${AWS::Region}::embedding-model/amazon.titan-embed-text-v1"
96	```
97
98	### 5. Create Data Source
99
100	```yaml
101	DataBucket:
102	Type: AWS::S3::Bucket
103
104	S3DataSource:
105	Type: AWS::Bedrock::DataSource
106	Properties:
107	KnowledgeBaseId: !Ref KnowledgeBase
108	Name: s3-data-source
109	Type: S3
110	DataSourceConfiguration:
111	S3Configuration:
112	BucketArn: !GetAtt DataBucket.Arn
113	InclusionPrefixes:
114	- documents/
115	```
116
117	### 6. Add Guardrail
118
119	```yaml
120	Guardrail:
121	Type: AWS::Bedrock::Guardrail
122	Properties:
123	Name: !Sub "${AWS::StackName}-guardrail"
124	BlockedInputMessaging: "I cannot help with that request."
125	ContentPolicyConfig:
126	filtersConfig:
127	- type: PROFANITY
128	- type: MISCONDUCT
129	```
130
131	### 7. Create Action Group
132
133	```yaml
134	ActionLambdaFunction:
135	Type: AWS::Lambda::Function
136	Properties:
137	Runtime: python3.12
138	Handler: index.handler
139	Role: !GetAtt ActionLambdaRole.Arn
140	Code:
141	ZipFile: \|
142	def handler(event, context):
143	return {"statusCode": 200, "body": "{\"result\": \"success\"}"}
144
145	ActionGroup:
146	Type: AWS::Bedrock::AgentActionGroup
147	Properties:
148	ActionGroupName: api-operations
149	ActionGroupState: ENABLED
150	AgentId: !GetAtt BedrockAgent.AgentId
151	ActionGroupExecutor:
152	Lambda: !Ref ActionLambdaFunction
153	FunctionSchema:
154	functionConfigurations:
155	- function: \|
156	{ "name": "get_inventory", "description": "Get current inventory status", "parameters": { "type": "object", "properties": { "sku": { "type": "string" } }, "required": [] } }
157	```
158
159	### 8. V

People who liked this also viewed

6 picks

Type

aws-cloudformation-bedrock

71installs36forks

View on GitHub

How to install aws-cloudformation-bedrock?

giuseppe-trisciuoglio/developer-kit/aws-cloudformation-bedrock

$npx -y skills add giuseppe-trisciuoglio/developer-kit --skill aws-cloudformation-bedrock

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# AWS CloudFormation Amazon Bedrock
2
3	## Overview
4
5	Creates production-ready AI infrastructure using AWS CloudFormation templates for Amazon Bedrock. Covers Bedrock agents, knowledge bases for RAG implementations, data source connectors, guardrails for content moderation, prompt management, workflow orchestration with flows, and inference profiles for optimized model access.
6
7	## When to Use
8
9	- Creating Bedrock agents with action groups
10	- Implementing RAG with knowledge bases
11	- Configuring S3 or web crawl data sources
12	- Setting up content moderation guardrails
13	- Managing prompt templates
14	- Orchestrating AI workflows with Bedrock Flows
15	- Configuring inference profiles for multi-model access
16	- Organizing templates with Parameters and cross-stack references
17
18	## Instructions
19
20	### 1. Define Parameters
21
22	```yaml
23	Parameters:
24	FoundationModel:
25	Type: String
26	Default: anthropic.claude-3-sonnet-20240229-v1:0
27	AllowedValues:
28	- anthropic.claude-3-sonnet-20240229-v1:0
29	- anthropic.claude-3-haiku-20240307-v1:0
30	- amazon.titan-text-express-v1
31	Description: Foundation model for agent
32	```
33
34	### 2. Create Agent Role
35
36	```yaml
37	Resources:
38	AgentRole:
39	Type: AWS::IAM::Role
40	Properties:
41	AssumeRolePolicyDocument:
42	Version: "2012-10-17"
43	Statement:
44	- Effect: Allow
45	Principal:
46	Service: bedrock.amazonaws.com
47	Action: sts:AssumeRole
48	Policies:
49	- PolicyName: BedrockPermissions
50	PolicyDocument:
51	Version: "2012-10-17"
52	Statement:
53	- Effect: Allow
54	Action:
55	- bedrock:InvokeModel
56	Resource: !Sub "arn:aws:bedrock:${AWS::Region}:${AWS::AccountId}:foundation-model/${FoundationModel}"
57	```
58
59	### 3. Create Agent
60
61	```yaml
62	BedrockAgent:
63	Type: AWS::Bedrock::Agent
64	Properties:
65	AgentName: !Sub "${AWS::StackName}-agent"
66	AgentResourceRoleArn: !GetAtt AgentRole.Arn
67	FoundationModelArn: !Sub "arn:aws:bedrock:${AWS::Region}::foundation-model/${FoundationModel}"
68	AutoPrepare: true
69	Instruction: \|
70	You are a helpful assistant. Use the knowledge base to answer questions.
71	```
72
73	### 4. Create Knowledge Base
74
75	```yaml
76	KnowledgeBaseRole:
77	Type: AWS::IAM::Role
78	Properties:
79	AssumeRolePolicyDocument:
80	Version: "2012-10-17"
81	Statement:
82	- Effect: Allow
83	Principal:
84	Service: bedrock.amazonaws.com
85	Action: sts:AssumeRole
86
87	KnowledgeBase:
88	Type: AWS::Bedrock::KnowledgeBase
89	Properties:
90	Name: !Sub "${AWS::StackName}-kb"
91	RoleArn: !GetAtt KnowledgeBaseRole.Arn
92	KnowledgeBaseConfiguration:
93	Type: VECTOR
94	VectorKnowledgeBaseConfiguration:
95	EmbeddingModelArn: !Sub "arn:aws:bedrock:${AWS::Region}::embedding-model/amazon.titan-embed-text-v1"
96	```
97
98	### 5. Create Data Source
99
100	```yaml
101	DataBucket:
102	Type: AWS::S3::Bucket
103
104	S3DataSource:
105	Type: AWS::Bedrock::DataSource
106	Properties:
107	KnowledgeBaseId: !Ref KnowledgeBase
108	Name: s3-data-source
109	Type: S3
110	DataSourceConfiguration:
111	S3Configuration:
112	BucketArn: !GetAtt DataBucket.Arn
113	InclusionPrefixes:
114	- documents/
115	```
116
117	### 6. Add Guardrail
118
119	```yaml
120	Guardrail:
121	Type: AWS::Bedrock::Guardrail
122	Properties:
123	Name: !Sub "${AWS::StackName}-guardrail"
124	BlockedInputMessaging: "I cannot help with that request."
125	ContentPolicyConfig:
126	filtersConfig:
127	- type: PROFANITY
128	- type: MISCONDUCT
129	```
130
131	### 7. Create Action Group
132
133	```yaml
134	ActionLambdaFunction:
135	Type: AWS::Lambda::Function
136	Properties:
137	Runtime: python3.12
138	Handler: index.handler
139	Role: !GetAtt ActionLambdaRole.Arn
140	Code:
141	ZipFile: \|
142	def handler(event, context):
143	return {"statusCode": 200, "body": "{\"result\": \"success\"}"}
144
145	ActionGroup:
146	Type: AWS::Bedrock::AgentActionGroup
147	Properties:
148	ActionGroupName: api-operations
149	ActionGroupState: ENABLED
150	AgentId: !GetAtt BedrockAgent.AgentId
151	ActionGroupExecutor:
152	Lambda: !Ref ActionLambdaFunction
153	FunctionSchema:
154	functionConfigurations:
155	- function: \|
156	{ "name": "get_inventory", "description": "Get current inventory status", "parameters": { "type": "object", "properties": { "sku": { "type": "string" } }, "required": [] } }
157	```
158
159	### 8. V

People who liked this also viewed

6 picks

Type