generative-ai-cdk-constructs
View on GitHubAWS Generative AI CDK Constructs are sample implementations of AWS CDK for common generative AI patterns.
AWS CDK construct library providing multi-service, well-architected patterns for generative AI on AWS: Bedrock, SageMaker model deployment, RAG knowledge bases, OpenSearch vector stores, agents, and batch inference. Use it to define repeatable GenAI infrastructure in TypeScript, Python, Java, Go, or C#. Experimental, n
Use Cases
Define well-architected generative AI infrastructure as CDK codeDeploy RAG question-answering systems with Bedrock Knowledge BasesDeploy foundation models to SageMaker endpoints from JumpStart, Hugging Face, or S3Monitor Amazon Bedrock model usage with CloudWatch dashboardsRun Bedrock batch inference jobs via Step FunctionsBuild intelligent document processing and multimodal data automation with Bedrock Data AutomationCreate OpenSearch Serverless vector collections and indexesBuild multi-agent systems on AWSSummarization and content generation pipelinesAdd RAG to applications using LangChain
Built With
- Language
- TypeScript
- Frameworks
- AWS CDK · projen · jsii · LangChain · Amazon Bedrock · Amazon SageMaker · Amazon OpenSearch Serverless · AWS AppSync · AWS Step Functions · AWS Lambda · Amazon Aurora DSQL · Amazon S3 Vectors
Tags
aws-cdk · infrastructure-as-code · amazon-bedrock · generative-ai · rag · knowledge-base · sagemaker · opensearch · agents · langchain · step-functions · vector-index · content-generation · summarization · question-answering · typescript