AWS
AI & ML
advanced
AI Chatbot with Retrieval — AWS Architecture Template
Authenticated chat API where a Lambda orchestrator augments a SageMaker-hosted LLM with document retrieval, history, and caching.
Why this architecture works
- Retrieval-augmented prompts ground responses in your S3 knowledge base, reducing hallucination
- The orchestrator pattern isolates prompt assembly and guardrails from the model, so either evolves independently
- Chat history in DynamoDB gives stateless Lambdas durable multi-turn context
- ElastiCache short-circuits repeated questions, cutting inference cost and latency
- Cognito authentication plus KMS-encrypted documents keep conversations and sources private per user
What's inside (9 resources)
Chat API
aws-api-gateway
User Auth
aws-cognito
Chat Orchestrator
aws-lambda
Knowledge Docs
aws-s3
Doc Encryption
aws-kms
LLM Endpoint
aws-sagemaker
Chat History
aws-dynamodb
Response Cache
aws-elasticache
Latency & Cost Metrics
aws-cloudwatch
From template to running infrastructure
- Open this template in the CloudForge visual designer (free account, no credit card).
- Customize resources, names, and connections on the drag-and-drop canvas — or ask Vani, the AI architect, to adapt it.
- Generate production-ready Terraform or CloudFormation in one click.
- Review the plan diff and security scan, then deploy with human approval.