added new aws rag prototyping template

Author: greg-the-coder

templates/awshp-k8s-rag-with-claude-code/README.md

@@ -0,0 +1,50 @@
+# AWS RAG Application Prototyping with Coder CDE
+
+A Kubernetes-based Coder template that provides a complete development environment for AWS RAG (Retrieval-Augmented Generation) application prototyping with Claude Code integration.
+
+## Architecture
+
+This template creates:
+- **Kubernetes workspace** with configurable CPU/memory resources
+- **Aurora PostgreSQL Serverless v2** cluster with pgvector extension for vector storage
+- **Claude Code integration** with AWS Bedrock for AI-assisted development
+- **Pre-configured development environment** with AWS CLI, CDK, and Python tooling
+
+## Key Components
+
+### Infrastructure (`main.tf`)
+- Kubernetes deployment with Coder agent
+- Configurable compute resources (2-8 CPU cores, 2-8GB RAM)
+- Git repository cloning (defaults to aws-rag-prototyping repo)
+- Code-server and Claude Code modules
+- Streamlit app preview on port 8501
+
+### Database (`aws-aurora/aurora-pgvector.tf`)
+- Aurora PostgreSQL 16.6 Serverless v2 cluster
+- pgvector extension for vector embeddings
+- Configurable scaling (0.5-1.0 ACU)
+- Security group allowing PostgreSQL access
+
+## Environment Variables
+
+```bash
+CLAUDE_CODE_USE_BEDROCK=1
+ANTHROPIC_MODEL=us.anthropic.claude-3-7-sonnet-20250219-v1:0
+PGVECTOR_HOST=<aurora-endpoint>
+PGVECTOR_DATABASE=mydb1
+PGVECTOR_USER=dbadmin
+```
+
+## Usage
+
+1. Deploy template to Coder instance
+2. Create workspace with desired CPU/memory configuration
+3. Claude Code automatically sets up Python environment and installs dependencies
+4. Access Streamlit preview at the provided URL
+5. Use integrated development tools for RAG application prototyping
+
+## Prerequisites
+
+- Kubernetes cluster with Coder deployment
+- AWS VPC with private subnets
+- Appropriate IAM permissions for Aurora and Bedrock services

templates/awshp-k8s-rag-with-claude-code/aws-aurora/aurora-pgvector.tf

@@ -0,0 +1,124 @@
+# variables for Coder Workspace Reference
+variable "workspace_name" {
+  type = string
+  default = "awsragproto"
+}
+
+variable "eks_cluster_name" {
+  description = "Name of the EKS cluster"
+  type        = string
+  default     = "coder-aws-cluster"
+}
+
+#Variables for Aurora PostgreSQL Serverless v2
+
+variable "database_name" {
+  description = "Name of the database to be created"
+  type        = string
+  default     = "mydb"
+}
+variable "db_master_username" {
+  description = "Master username for the database"
+  type        = string
+  default     = "dbadmin"
+}
+variable "db_master_password" {
+  description = "Master password for the database"
+  type        = string
+  default     = "YourStrongPasswordHere1"  # Consider using AWS Secrets Manager for production
+}
+
+# Get EKS cluster info
+data "aws_eks_cluster" "current" {
+  name = var.eks_cluster_name  # Add this variable
+}
+
+# Use EKS VPC
+data "aws_vpc" "existing_vpc" {
+  id = data.aws_eks_cluster.current.vpc_config[0].vpc_id
+}
+
+# Get private subnets from EKS
+data "aws_subnets" "private" {
+  filter {
+    name   = "vpc-id"
+    values = [data.aws_vpc.existing_vpc.id]
+  }
+  
+  tags = {
+    "kubernetes.io/role/internal-elb" = "1"
+  }
+}
+
+# Create a subnet group for Aurora instances using existing subnets
+resource "aws_db_subnet_group" "awsrag_aurora_subnet_group" {
+  name       = "${var.workspace_name}-sgrp"
+  subnet_ids = data.aws_subnets.private.ids
+
+  tags = {
+    Name = "${var.workspace_name}-sgrp"
+  }
+}
+
+# Create security group for Aurora instances
+resource "aws_security_group" "awsrag_aurora_sg" {
+  name        = "${var.workspace_name}-sg"
+  description = "Security group for Aurora PostgreSQL instances"
+  vpc_id      = data.aws_vpc.existing_vpc.id
+
+  ingress {
+    from_port   = 5432
+    to_port     = 5432
+    protocol    = "tcp"
+    cidr_blocks = ["0.0.0.0/0"]  # Allow public access not restricted to the VPC
+  }
+
+  egress {
+    from_port   = 0
+    to_port     = 0
+    protocol    = "-1"
+    cidr_blocks = ["0.0.0.0/0"]
+  }
+
+  tags = {
+    Name = "${var.workspace_name}-sg"
+  }
+}
+
+# First Aurora PostgreSQL Serverless v2 instance
+resource "aws_rds_cluster" "awsrag_aurora_postgres_1" {
+  cluster_identifier      = "${var.workspace_name}-pgvector01"
+  engine                  = "aurora-postgresql"
+  engine_mode             = "provisioned"
+  engine_version          = "16.6"
+  database_name           = var.database_name
+  master_username         = var.db_master_username
+  master_password         = var.db_master_password  # Use AWS Secrets Manager in production
+  db_subnet_group_name    = aws_db_subnet_group.awsrag_aurora_subnet_group.name
+  vpc_security_group_ids  = [aws_security_group.awsrag_aurora_sg.id]
+  skip_final_snapshot     = true
+  
+  serverlessv2_scaling_configuration {
+    min_capacity = 0.5
+    max_capacity = 1.0
+  }
+}
+
+# Primary DB instance for the Aurora PostgreSQL cluster
+resource "aws_rds_cluster_instance" "awsrag_aurora_primary" {
+  cluster_identifier   = aws_rds_cluster.awsrag_aurora_postgres_1.id
+  instance_class       = "db.serverless"
+  engine               = "aurora-postgresql"
+  engine_version       = "16.6"
+  db_subnet_group_name = aws_db_subnet_group.awsrag_aurora_subnet_group.name
+  identifier           = "${var.workspace_name}-primary"
+}
+
+# Outputs
+output "aurora_postgres_1_endpoint" {
+  value = aws_rds_cluster.awsrag_aurora_postgres_1.endpoint
+}
+
+output "aurora_postgres_1_reader_endpoint" {
+  value = aws_rds_cluster.awsrag_aurora_postgres_1.reader_endpoint
+}