You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+29-27Lines changed: 29 additions & 27 deletions
Original file line number
Diff line number
Diff line change
@@ -28,35 +28,37 @@
28
28
-[Roadmap](#roadmap)
29
29
-[Legal Disclaimer](#legal-disclaimer)
30
30
31
-
# Introduction
31
+
##Introduction
32
32
33
33
The AWS Generative AI Constructs Library is an open-source extension of the [AWS Cloud Development Kit (AWS CDK)](https://docs.aws.amazon.com/cdk/v2/guide/home.html) that provides multi-service, well-architected patterns for quickly defining solutions in code to create predictable and repeatable infrastructure, called [constructs](https://docs.aws.amazon.com/cdk/v2/guide/constructs.html). The goal of AWS Generative AI CDK Constructs is to help developers build generative AI solutions using pattern-based definitions for their architecture.
34
34
35
35
The patterns defined in AWS Generative AI CDK Constructs are high level, multi-service abstractions of AWS CDK constructs that have default configurations based on well-architected best practices. The library is organized into logical modules using object-oriented techniques to create each architectural pattern model.
36
36
37
-
# CDK Versions
37
+
##CDK Versions
38
38
39
39
AWS Generative AI CDK Constructs and the AWS CDK are independent teams and have different release schedules. Each release of AWS Generative AI CDK Constructs is built against a specific version of the AWS CDK. The [CHANGELOG.md](./CHANGELOG.md) file lists the CDK version associated with each AWS Generative AI Constructs release. For instance, AWS Generative AI CDK Constructs v0.0.0 was built against AWS CDK v2.96.2. This means that to use AWS Generative AI CDK Constructs v0.0.0, your application must include AWS CDK v2.96.2 or later. You can continue to use the latest AWS CDK versions and upgrade the your AWS Generative AI CDK Constructs version when new releases become available.
40
40
41
-
# Contributing
41
+
##Contributing
42
42
43
43
Contributions of all kinds are welcome! Check out our [contributor guide](./CONTRIBUTING.md)
44
44
45
-
# Design guidelines and Development guide
45
+
##Design guidelines and Development guide
46
46
47
47
If you want to add a new construct to the library, check out our [design guidelines](./DESIGN_GUIDELINES.md), then follow the [development guide](./DEVELOPER_GUIDE.md)
48
48
49
-
# Getting Started
49
+
## Getting Started
50
+
51
+
### For TypeScript
50
52
51
-
#### For TypeScript:
52
53
- Create or use an existing CDK application in TypeScript.
53
54
-`cdk init app --language typescript`
54
55
- Run `npm install @cdklabs/generative-ai-cdk-constructs`
55
56
- The package should be added to your package.json.
56
-
- Import the library:
57
+
- Import the library:
57
58
-`import * as genai from '@cdklabs/generative-ai-cdk-constructs';`
58
59
59
-
#### For Python:
60
+
### For Python
61
+
60
62
- Create or use an existing CDK application in Python
61
63
-`cdk init app --language python`
62
64
- Install the package:
@@ -66,38 +68,38 @@ If you want to add a new construct to the library, check out our [design guideli
66
68
67
69
Refer to the documentation for additional guidance on a particular construct: [Catalog](#catalog)
68
70
69
-
# Catalog
71
+
##Catalog
70
72
71
73
The following constructs are available in the library:
72
74
73
-
**L3 constructs**
75
+
### L3 constructs
74
76
75
77
|**Construct**|Description| AWS Services used |
76
78
|:-------------|:-------------|:-------------|
77
-
|[Data ingestion pipeline - OpenSearch](./src/patterns/gen-ai/aws-rag-appsync-stepfn-opensearch/)| Ingestion pipeline providing a RAG (retrieval augmented generation) source for storing documents in a knowledge base. | Amazon OpenSearch, AWS Step Functions, Amazon Bedrock, AWS AppSync, AWS Lambda |
78
-
|[Data ingestion pipeline - Kendra](./src/patterns/gen-ai/aws-rag-appsync-stepfn-kendra/)| Ingestion pipeline providing a RAG (retrieval augmented generation) source for storing documents in a knowledge base. | Amazon Kendra, AWS Step Functions, AWS AppSync, AWS Lambda |
79
-
|[Question answering](./src/patterns/gen-ai/aws-qa-appsync-opensearch/)| Utilizing Large Language Models (Anthropic Claude V2.1.) for Question Answering on PDF documents with RAG (retrieval augmented generation) source and/or long context. Additionally, leveraging Anthropic Claude 3 for visual question answering on images.| Amazon OpenSearch, AWS Lambda, Amazon Bedrock, AWS AppSync |
80
-
|[Summarization](./src/patterns/gen-ai/aws-summarization-appsync-stepfn/)| Document summarization with a large language model (Anthropic Claude V2.1). | AWS Lambda, Amazon Bedrock, AWS AppSync and Amazon ElastiCache for Redis. |
81
-
|[SageMaker model deployment (JumpStart)](./src/patterns/gen-ai/aws-model-deployment-sagemaker/README_jumpstart.md)| Deploy a foundation model from Amazon SageMaker JumpStart to an Amazon SageMaker endpoint. | Amazon SageMaker |
82
-
|[SageMaker model deployment (Hugging Face)](./src/patterns/gen-ai/aws-model-deployment-sagemaker/README_hugging_face.md)| Deploy a foundation model from Hugging Face to an Amazon SageMaker endpoint. | Amazon SageMaker |
79
+
|[Data ingestion pipeline - OpenSearch](./src/patterns/gen-ai/aws-rag-appsync-stepfn-opensearch/README.md)| Ingestion pipeline providing a RAG (retrieval augmented generation) source for storing documents in a knowledge base. | Amazon OpenSearch, AWS Step Functions, Amazon Bedrock, AWS AppSync, AWS Lambda |
80
+
|[Data ingestion pipeline - Kendra](./src/patterns/gen-ai/aws-rag-appsync-stepfn-kendra/README.md)| Ingestion pipeline providing a RAG (retrieval augmented generation) source for storing documents in a knowledge base. | Amazon Kendra, AWS Step Functions, AWS AppSync, AWS Lambda |
81
+
|[Question answering](./src/patterns/gen-ai/aws-qa-appsync-opensearch/README.md)| Utilizing Large Language Models (Anthropic Claude V2.1.) for Question Answering on PDF documents with RAG (retrieval augmented generation) source and/or long context. Additionally, leveraging Anthropic Claude 3 for visual question answering on images.| Amazon OpenSearch, AWS Lambda, Amazon Bedrock, AWS AppSync |
82
+
|[Summarization](./src/patterns/gen-ai/aws-summarization-appsync-stepfn/README.md)| Document summarization with a large language model (Anthropic Claude V2.1). | AWS Lambda, Amazon Bedrock, AWS AppSync and Amazon ElastiCache for Redis. |
83
+
|[SageMaker model deployment (JumpStart)](./src/patterns/gen-ai/aws-model-deployment-sagemaker/README_jumpstart.md)| Deploy a foundation model from Amazon SageMaker JumpStart to an Amazon SageMaker endpoint. | Amazon SageMaker |
84
+
|[SageMaker model deployment (Hugging Face)](./src/patterns/gen-ai/aws-model-deployment-sagemaker/README_hugging_face.md)| Deploy a foundation model from Hugging Face to an Amazon SageMaker endpoint. | Amazon SageMaker |
83
85
|[SageMaker model deployment (Custom)](./src/patterns/gen-ai/aws-model-deployment-sagemaker/README_custom_sagemaker_endpoint.md)| Deploy a foundation model from an S3 location to an Amazon SageMaker endpoint. | Amazon SageMaker |
84
-
|[Content Generation](./src/patterns/gen-ai/aws-contentgen-appsync-lambda/)| Generate images from text using Amazon titan-image-generator-v1 or stability.stable-diffusion-xl model. | AWS Lambda, Amazon Bedrock, AWS AppSync |
85
-
|[Web crawler](./src/patterns/gen-ai/aws-web-crawler/)| Crawl websites and RSS feeds on a schedule and store changeset data in an Amazon Simple Storage Service bucket. | AWS Lambda, AWS Batch, AWS Fargate, Amazon DynamoDB |
86
+
|[Content Generation](./src/patterns/gen-ai/aws-contentgen-appsync-lambda/README.md)| Generate images from text using Amazon titan-image-generator-v1 or stability.stable-diffusion-xl model. | AWS Lambda, Amazon Bedrock, AWS AppSync |
87
+
|[Web crawler](./src/patterns/gen-ai/aws-web-crawler/README.md)| Crawl websites and RSS feeds on a schedule and store changeset data in an Amazon Simple Storage Service bucket. | AWS Lambda, AWS Batch, AWS Fargate, Amazon DynamoDB |
86
88
87
-
**L2 Constructs**
89
+
### L2 Constructs
88
90
89
91
|**Construct**|Description| AWS Services used |
90
92
|:-------------|:-------------|:-------------|
91
-
|[Lambda layer](./src/patterns/gen-ai/aws-langchain-common-layer/)| Python Lambda layer providing dependencies and utilities to develop generative AI applications on AWS. | AWS Lambda, Amazon Bedrock, Amazon SageMaker |
93
+
|[Lambda layer](./src/patterns/gen-ai/aws-langchain-common-layer/README.md)| Python Lambda layer providing dependencies and utilities to develop generative AI applications on AWS. | AWS Lambda, Amazon Bedrock, Amazon SageMaker |
|[Amazon OpenSearch Serverless Vector Collection](./src/cdk-lib/opensearchserverless/README.md)| CDK L2 Constructs to create a vector collection. | Amazon OpenSearch Vector Index |
94
96
|[Amazon OpenSearch Vector Index](./src/cdk-lib/opensearch-vectorindex/README.md)| CDK L1 Custom Resource to create a vector index. | Amazon OpenSearch Serverless, AWS Lambda |
95
97
96
-
# Sample Use Cases
98
+
##Sample Use Cases
97
99
98
100
The official samples repository https://github.com/aws-samples/generative-ai-cdk-constructs-samples includes a collection of functional use case implementations to demonstrate the usage of AWS Generative AI CDK Constructs. These can be used in the same way as architectural patterns, and can be conceptualized as an additional "higher-level" abstraction of those patterns. Those patterns (constructs) are composed together into [stacks](https://docs.aws.amazon.com/cdk/latest/guide/stacks.html), forming a "CDK app".
99
101
100
-
# Additional Resources
102
+
##Additional Resources
101
103
102
104
| Resource |Description|
103
105
|:-------------|:-------------|
@@ -115,21 +117,21 @@ The official samples repository https://github.com/aws-samples/generative-ai-cdk
115
117
|[Agents for Amazon Bedrock - Powertools for AWS Lambda (Python)](https://docs.powertools.aws.dev/lambda/python/latest/core/event_handler/bedrock_agents/#using-aws-cloud-developer-kit-cdk)| Create Agents for Amazon Bedrock using event handlers and auto generation of OpenAPI schemas. |
116
118
|[Text to SQL Bedrock Agent](https://github.com/aws-samples/amazon-bedrock-samples/tree/main/agents-for-bedrock/use-case-examples/text-2-sql-agent-cdk-enhanced)| Harnessing the power of natural language processing, the "Text to SQL Bedrock Agent" facilitates the automatic transformation of natural language questions into executable SQL queries. |
Generative AI CDK Constructs may collect anonymous operational metrics, including: the region a construct is deployed, the name and version of the construct deployed, and related information. We may use the metrics to maintain, provide, develop, and improve the constructs and AWS services.
125
127
126
-
# Roadmap
128
+
##Roadmap
127
129
128
130
Roadmap is available through the [GitHub Project](https://github.com/orgs/awslabs/projects/136)
129
131
130
-
# Legal Disclaimer
132
+
##Legal Disclaimer
131
133
132
134
You should consider doing your own independent assessment before using the content in this library for production purposes. This may include (amongst other things) testing, securing, and optimizing the CDK constructs and other content, provided in this library, based on your specific quality control practices and standards.
0 commit comments