Model-Inference
4 guides available
Showing 4 of 4 guides
AI App Infrastructure
Deploy a minimal HTTP AI application endpoint with cloud-native compute, logs, secret/config wiring, and least-privilege model invocation permissions.
AI
Cloud-Run
Functions
Model-Inference
Serverless
Deploy AI app infrastructure on AWS Bedrock with Pulumi
Provision a minimal HTTP endpoint, cloud logs, secure config, and least-privilege Amazon Bedrock invocation for an AI app on AWS Bedrock.
AI
AWS
Bedrock
Cloud-Run
CloudWatch
Functions
Lambda
Model-Inference
Python
Serverless
TypeScript
Deploy AI app infrastructure on Azure OpenAI with Pulumi
Provision a minimal HTTP endpoint, cloud logs, secure config, and least-privilege Azure OpenAI invocation for an AI app on Azure OpenAI.
AI
Application-Insights
Azure
Azure-Functions
Cloud-Run
Functions
Key-Vault
Model-Inference
Python
Serverless
TypeScript
Deploy AI app infrastructure on GCP Vertex AI with Pulumi
Provision a minimal HTTP endpoint, cloud logs, secure config, and least-privilege Vertex AI invocation for an AI app on GCP Vertex AI.
AI
Cloud-Run
Functions
GCP
Model-Inference
Python
Serverless
TypeScript
Vertex-Ai