ProjectBuild an AI-Powered Digital Bank with RAG: the explanation · Module 18: Deploying to Google Cloud, with CI/CD · part 20 of 20
Part 20 · Module 18: Deploying to Google Cloud, with CI/CD

Module 18: Deploying to Google Cloud, with CI/CD

23 min read·
About 50 minutes · Needs: Module 16 (frontend and running locally) and Module 17 (Docker images); Module 14 helps for the eval gate · Code: deploy/gcp/terraform/cicd.tf, deploy/gcp/terraform/run.tf, .github/workflows/deploy.yml, deploy/gcp/deploy.sh

Where this fits

WHERE THIS FITS The Kestrel Bank system this module CLIENT API LAYER FastAPI SAFETY AGENT LangGraph MODELS RETRIEVAL DATA AND INGESTION Postgres, Redis QUALITY Langfuse Customer app React Admin app React FastAPI REST + streaming Auth + RBAC tokens, roles Document upload admin only, checked Guardrails injection, PII Router small or large Agent LangGraph Banking tools ledger, transfers LLMs Groq, Gemini Retrieval hybrid + rerank Ingestion parse, chunk, embed PostgreSQL + pgvector ledger, chunks, state Redis limits, queue Observability Langfuse, metrics, logs Evaluation golden set, release gate
Deployment moves the whole stack (blue) to Google Cloud; the evaluation gate decides whether a commit may go.

Every earlier module runs on one laptop. This one puts the same two images on Google Cloud and keeps them up to date automatically. Read it to put Kestrel online from an empty project.

The rest of this project is yours to keep

This project is bought on its own, once, and stays readable afterwards, including the parts added to it later.

Or open everything with a plan