feat(inference): Add examples and terratest for inference module

infrastructure/ai-inference/opentofu/modules/inference/examples/README.md

@@ -0,0 +1,3 @@
+# Examples
+
+This directory contains examples of how to use the inference module.

infrastructure/ai-inference/opentofu/modules/inference/examples/gpt-oss-20b/data.tf

@@ -0,0 +1,31 @@
+# Data source for the latest Ubuntu 24.04 AI Inference AMI
+data "aws_ami" "ai_inference" {
+  most_recent = true
+  owners      = ["self"]
+
+  filter {
+    name   = "name"
+    values = ["${var.ami_name_prefix}*"]
+  }
+
+  filter {
+    name   = "state"
+    values = ["available"]
+  }
+}
+
+# Security group for the AI inference server
+data "aws_vpc" "default" {
+  default = true
+}
+
+data "aws_subnets" "default" {
+  filter {
+    name   = "vpc-id"
+    values = [data.aws_vpc.default.id]
+  }
+}
+
+data "aws_iam_instance_profile" "ai_inference_profile" {
+  name = "ai-inference-profile"
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/gpt-oss-20b/main.tf

@@ -0,0 +1,16 @@
+module "gpt_oss_20b" {
+  source = "../../"
+
+  ami_id               = data.aws_ami.ai_inference.id
+  instance_type        = "g6.xlarge"
+  vpc_id               = data.aws_vpc.default.id
+  subnet_id            = data.aws_subnets.default.ids[0]
+  iam_instance_profile = data.aws_iam_instance_profile.ai_inference_profile.name
+  key_name             = "gpt_oss_20b_key"
+
+  allowed_ip_addresses = var.allowed_ip_addresses
+  hugging_face_token   = var.hugging_face_token
+  model                = "openai/gpt-oss-20b"
+  vllm_timeout         = 600
+  vllm_version         = "v0.10.1"
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/gpt-oss-20b/outputs.tf

@@ -0,0 +1,4 @@
+output "public_ip" {
+  description = "Public IP address of the AI inference server"
+  value       = module.gpt_oss_20b.public_ip
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/gpt-oss-20b/providers.tf

@@ -0,0 +1,12 @@
+terraform {
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+  }
+}
+
+provider "aws" {
+  region = "us-east-1"
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/gpt-oss-20b/variables.tf

@@ -0,0 +1,16 @@
+variable "ami_name_prefix" {
+  description = "Prefix for the AMI name"
+  type        = string
+  default     = "ubuntu-24.04-ai-inference"
+}
+
+variable "allowed_ip_addresses" {
+  description = "List of IP addresses (CIDR blocks) allowed to access the server"
+  type        = list(string)
+}
+
+variable "hugging_face_token" {
+  description = "Hugging Face token"
+  type        = string
+  sensitive   = true
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/qwen3-0.6b/data.tf

@@ -0,0 +1,31 @@
+# Data source for the latest Ubuntu 24.04 AI Inference AMI
+data "aws_ami" "ai_inference" {
+  most_recent = true
+  owners      = ["self"]
+
+  filter {
+    name   = "name"
+    values = ["${var.ami_name_prefix}*"]
+  }
+
+  filter {
+    name   = "state"
+    values = ["available"]
+  }
+}
+
+# Security group for the AI inference server
+data "aws_vpc" "default" {
+  default = true
+}
+
+data "aws_subnets" "default" {
+  filter {
+    name   = "vpc-id"
+    values = [data.aws_vpc.default.id]
+  }
+}
+
+data "aws_iam_instance_profile" "ai_inference_profile" {
+  name = "ai-inference-profile"
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/qwen3-0.6b/main.tf

@@ -0,0 +1,15 @@
+module "qwen3_0_6b" {
+  source = "../../"
+
+  ami_id               = data.aws_ami.ai_inference.id
+  vpc_id               = data.aws_vpc.default.id
+  subnet_id            = data.aws_subnets.default.ids[0]
+  iam_instance_profile = data.aws_iam_instance_profile.ai_inference_profile.name
+  key_name             = "qwen3_0_6b_key"
+
+  allowed_ip_addresses = var.allowed_ip_addresses
+  hugging_face_token   = var.hugging_face_token
+  model                = "Qwen/Qwen3-0.6B"
+  vllm_timeout         = 360
+  vllm_version         = "latest"
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/qwen3-0.6b/outputs.tf

@@ -0,0 +1,4 @@
+output "public_ip" {
+  description = "Public IP address of the AI inference server"
+  value       = module.qwen3_0_6b.public_ip
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/qwen3-0.6b/providers.tf

@@ -0,0 +1,12 @@
+terraform {
+  required_providers {
+    aws = {
+      source  = "hashicorp/aws"
+      version = "~> 5.0"
+    }
+  }
+}
+
+provider "aws" {
+  region = "us-east-1"
+}

infrastructure/ai-inference/opentofu/modules/inference/examples/qwen3-0.6b/variables.tf

@@ -0,0 +1,16 @@
+variable "ami_name_prefix" {
+  description = "Prefix for the AMI name"
+  type        = string
+  default     = "ubuntu-24.04-ai-inference"
+}
+
+variable "allowed_ip_addresses" {
+  description = "List of IP addresses (CIDR blocks) allowed to access the server"
+  type        = list(string)
+}
+
+variable "hugging_face_token" {
+  description = "Hugging Face token"
+  type        = string
+  sensitive   = true
+}

infrastructure/ai-inference/opentofu/modules/inference/test/README.md

@@ -0,0 +1,3 @@
+# Tests
+
+This directory contains Terratest-based tests for the inference module.

infrastructure/ai-inference/opentofu/modules/inference/test/go.mod

@@ -0,0 +1,47 @@
+module github.com/lukebrady/ai-engineering/infrastructure/ai-inference/opentofu/modules/inference/test
+
+go 1.24.3
+
+require (
+	github.com/gruntwork-io/terratest v0.50.0
+	github.com/joho/godotenv v1.5.1
+	github.com/openai/openai-go/v2 v2.4.1
+	github.com/stretchr/testify v1.11.1
+)
+
+require (
+	github.com/agext/levenshtein v1.2.3 // indirect
+	github.com/apparentlymart/go-textseg/v15 v15.0.0 // indirect
+	github.com/bgentry/go-netrc v0.0.0-20140422174119-9fd32a8b3d3d // indirect
+	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/hashicorp/errwrap v1.0.0 // indirect
+	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
+	github.com/hashicorp/go-getter/v2 v2.2.3 // indirect
+	github.com/hashicorp/go-multierror v1.1.1 // indirect
+	github.com/hashicorp/go-safetemp v1.0.0 // indirect
+	github.com/hashicorp/go-version v1.7.0 // indirect
+	github.com/hashicorp/hcl/v2 v2.22.0 // indirect
+	github.com/hashicorp/terraform-json v0.23.0 // indirect
+	github.com/jinzhu/copier v0.0.0-20190924061706-b57f9002281a // indirect
+	github.com/klauspost/compress v1.16.5 // indirect
+	github.com/mattn/go-zglob v0.0.2-0.20190814121620-e3c945676326 // indirect
+	github.com/mitchellh/go-homedir v1.1.0 // indirect
+	github.com/mitchellh/go-testing-interface v1.14.1 // indirect
+	github.com/mitchellh/go-wordwrap v1.0.1 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/tidwall/gjson v1.14.4 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.1 // indirect
+	github.com/tidwall/sjson v1.2.5 // indirect
+	github.com/tmccombs/hcl2json v0.6.4 // indirect
+	github.com/ulikunitz/xz v0.5.10 // indirect
+	github.com/zclconf/go-cty v1.15.0 // indirect
+	golang.org/x/crypto v0.36.0 // indirect
+	golang.org/x/mod v0.18.0 // indirect
+	golang.org/x/net v0.38.0 // indirect
+	golang.org/x/sync v0.12.0 // indirect
+	golang.org/x/sys v0.31.0 // indirect
+	golang.org/x/text v0.23.0 // indirect
+	golang.org/x/tools v0.22.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

infrastructure/ai-inference/opentofu/modules/inference/test/go.sum

@@ -0,0 +1,88 @@
+github.com/agext/levenshtein v1.2.3 h1:YB2fHEn0UJagG8T1rrWknE3ZQzWM06O8AMAatNn7lmo=
+github.com/agext/levenshtein v1.2.3/go.mod h1:JEDfjyjHDjOF/1e4FlBE/PkbqA9OfWu2ki2W0IB5558=
+github.com/apparentlymart/go-textseg/v15 v15.0.0 h1:uYvfpb3DyLSCGWnctWKGj857c6ew1u1fNQOlOtuGxQY=
+github.com/apparentlymart/go-textseg/v15 v15.0.0/go.mod h1:K8XmNZdhEBkdlyDdvbmmsvpAG721bKi0joRfFdHIWJ4=
+github.com/bgentry/go-netrc v0.0.0-20140422174119-9fd32a8b3d3d h1:xDfNPAt8lFiC1UJrqV3uuy861HCTo708pDMbjHHdCas=
+github.com/bgentry/go-netrc v0.0.0-20140422174119-9fd32a8b3d3d/go.mod h1:6QX/PXZ00z/TKoufEY6K/a0k6AhaJrQKdFe6OfVXsa4=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/go-test/deep v1.0.7 h1:/VSMRlnY/JSyqxQUzQLKVMAskpY/NZKFA5j2P+0pP2M=
+github.com/go-test/deep v1.0.7/go.mod h1:QV8Hv/iy04NyLBxAdO9njL0iVPN1S4d/A3NVv1V36o8=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/gruntwork-io/terratest v0.50.0 h1:AbBJ7IRCpLZ9H4HBrjeoWESITv8nLjN6/f1riMNcAsw=
+github.com/gruntwork-io/terratest v0.50.0/go.mod h1:see0lbKvAqz6rvzvN2wyfuFQQG4PWcAb2yHulF6B2q4=
+github.com/hashicorp/errwrap v1.0.0 h1:hLrqtEDnRye3+sgx6z4qVLNuviH3MR5aQ0ykNJa/UYA=
+github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
+github.com/hashicorp/go-cleanhttp v0.5.2 h1:035FKYIWjmULyFRBKPs8TBQoi0x6d9G4xc9neXJWAZQ=
+github.com/hashicorp/go-cleanhttp v0.5.2/go.mod h1:kO/YDlP8L1346E6Sodw+PrpBSV4/SoxCXGY6BqNFT48=
+github.com/hashicorp/go-getter/v2 v2.2.3 h1:6CVzhT0KJQHqd9b0pK3xSP0CM/Cv+bVhk+jcaRJ2pGk=
+github.com/hashicorp/go-getter/v2 v2.2.3/go.mod h1:hp5Yy0GMQvwWVUmwLs3ygivz1JSLI323hdIE9J9m7TY=
+github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+lD48awMYo=
+github.com/hashicorp/go-multierror v1.1.1/go.mod h1:iw975J/qwKPdAO1clOe2L8331t/9/fmwbPZ6JB6eMoM=
+github.com/hashicorp/go-safetemp v1.0.0 h1:2HR189eFNrjHQyENnQMMpCiBAsRxzbTMIgBhEyExpmo=
+github.com/hashicorp/go-safetemp v1.0.0/go.mod h1:oaerMy3BhqiTbVye6QuFhFtIceqFoDHxNAB65b+Rj1I=
+github.com/hashicorp/go-version v1.7.0 h1:5tqGy27NaOTB8yJKUZELlFAS/LTKJkrmONwQKeRZfjY=
+github.com/hashicorp/go-version v1.7.0/go.mod h1:fltr4n8CU8Ke44wwGCBoEymUuxUHl09ZGVZPK5anwXA=
+github.com/hashicorp/hcl/v2 v2.22.0 h1:hkZ3nCtqeJsDhPRFz5EA9iwcG1hNWGePOTw6oyul12M=
+github.com/hashicorp/hcl/v2 v2.22.0/go.mod h1:62ZYHrXgPoX8xBnzl8QzbWq4dyDsDtfCRgIq1rbJEvA=
+github.com/hashicorp/terraform-json v0.23.0 h1:sniCkExU4iKtTADReHzACkk8fnpQXrdD2xoR+lppBkI=
+github.com/hashicorp/terraform-json v0.23.0/go.mod h1:MHdXbBAbSg0GvzuWazEGKAn/cyNfIB7mN6y7KJN6y2c=
+github.com/jinzhu/copier v0.0.0-20190924061706-b57f9002281a h1:zPPuIq2jAWWPTrGt70eK/BSch+gFAGrNzecsoENgu2o=
+github.com/jinzhu/copier v0.0.0-20190924061706-b57f9002281a/go.mod h1:yL958EeXv8Ylng6IfnvG4oflryUi3vgA3xPs9hmII1s=
+github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
+github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
+github.com/klauspost/compress v1.16.5 h1:IFV2oUNUzZaz+XyusxpLzpzS8Pt5rh0Z16For/djlyI=
+github.com/klauspost/compress v1.16.5/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
+github.com/mattn/go-zglob v0.0.2-0.20190814121620-e3c945676326 h1:ofNAzWCcyTALn2Zv40+8XitdzCgXY6e9qvXwN9W0YXg=
+github.com/mattn/go-zglob v0.0.2-0.20190814121620-e3c945676326/go.mod h1:9fxibJccNxU2cnpIKLRRFA7zX7qhkJIQWBb449FYHOo=
+github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y=
+github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
+github.com/mitchellh/go-testing-interface v1.14.1 h1:jrgshOhYAUVNMAJiKbEu7EqAwgJJ2JqpQmpLJOu07cU=
+github.com/mitchellh/go-testing-interface v1.14.1/go.mod h1:gfgS7OtZj6MA4U1UrDRp04twqAjfvlZyCfX3sDjEym8=
+github.com/mitchellh/go-wordwrap v1.0.1 h1:TLuKupo69TCn6TQSyGxwI1EblZZEsQ0vMlAFQflz0v0=
+github.com/mitchellh/go-wordwrap v1.0.1/go.mod h1:R62XHJLzvMFRBbcrT7m7WgmE1eOyTSsCt+hzestvNj0=
+github.com/openai/openai-go/v2 v2.4.1 h1:18RB0Qo21nzXfuFaMXy828Jlyho6cqNg1RLGWYBoXsk=
+github.com/openai/openai-go/v2 v2.4.1/go.mod h1:sIUkR+Cu/PMUVkSKhkk742PRURkQOCFhiwJ7eRSBqmk=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+github.com/tidwall/gjson v1.14.2/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/gjson v1.14.4 h1:uo0p8EbA09J7RQaflQ1aBRffTR7xedD2bcIVSYxLnkM=
+github.com/tidwall/gjson v1.14.4/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
+github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
+github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/pretty v1.2.1 h1:qjsOFOWWQl+N3RsoF5/ssm1pHmJJwhjlSbZ51I6wMl4=
+github.com/tidwall/pretty v1.2.1/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
+github.com/tidwall/sjson v1.2.5 h1:kLy8mja+1c9jlljvWTlSazM7cKDRfJuR/bOJhcY5NcY=
+github.com/tidwall/sjson v1.2.5/go.mod h1:Fvgq9kS/6ociJEDnK0Fk1cpYF4FIW6ZF7LAe+6jwd28=
+github.com/tmccombs/hcl2json v0.6.4 h1:/FWnzS9JCuyZ4MNwrG4vMrFrzRgsWEOVi+1AyYUVLGw=
+github.com/tmccombs/hcl2json v0.6.4/go.mod h1:+ppKlIW3H5nsAsZddXPy2iMyvld3SHxyjswOZhavRDk=
+github.com/ulikunitz/xz v0.5.10 h1:t92gobL9l3HE202wg3rlk19F6X+JOxl9BBrCCMYEYd8=
+github.com/ulikunitz/xz v0.5.10/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oWt/14=
+github.com/zclconf/go-cty v1.15.0 h1:tTCRWxsexYUmtt/wVxgDClUe+uQusuI443uL6e+5sXQ=
+github.com/zclconf/go-cty v1.15.0/go.mod h1:VvMs5i0vgZdhYawQNq5kePSpLAoz8u1xvZgrPIxfnZE=
+github.com/zclconf/go-cty-debug v0.0.0-20240509010212-0d6042c53940 h1:4r45xpDWB6ZMSMNJFMOjqrGHynW3DIBuR2H9j0ug+Mo=
+github.com/zclconf/go-cty-debug v0.0.0-20240509010212-0d6042c53940/go.mod h1:CmBdvvj3nqzfzJ6nTCIwDTPZ56aVGvDrmztiO5g3qrM=
+golang.org/x/crypto v0.36.0 h1:AnAEvhDddvBdpY+uR+MyHmuZzzNqXSe/GvuDeob5L34=
+golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc=
+golang.org/x/mod v0.18.0 h1:5+9lSbEzPSdWkH32vYPBwEpX8KwDbM52Ud9xBUvNlb0=
+golang.org/x/mod v0.18.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
+golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
+golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/sync v0.12.0 h1:MHc5BpPuC30uJk597Ri8TV3CNZcTLu6B6z4lJy+g6Jw=
+golang.org/x/sync v0.12.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
+golang.org/x/sys v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik=
+golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/term v0.30.0 h1:PQ39fJZ+mfadBm0y5WlL4vlM7Sx1Hgf13sMIY2+QS9Y=
+golang.org/x/term v0.30.0/go.mod h1:NYYFdzHoI5wRh/h5tDMdMqCqPJZEuNqVR5xJLd/n67g=
+golang.org/x/text v0.23.0 h1:D71I7dUrlY+VX0gQShAThNGHFxZ13dGLBHQLVl1mJlY=
+golang.org/x/text v0.23.0/go.mod h1:/BLNzu4aZCJ1+kcD0DNRotWKage4q2rGVAg4o22unh4=
+golang.org/x/tools v0.22.0 h1:gqSGLZqv+AI9lIQzniJ0nZDRG5GBPsSi+DRNHWNz6yA=
+golang.org/x/tools v0.22.0/go.mod h1:aCwcsjqvq7Yqt6TNyX7QMU2enbQ/Gt0bo6krSeEri+c=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=