ProjectBuild an AI-Powered Digital Bank with RAG: the explanation · Module 16: The frontend and running it locally · part 18 of 20
Part 18 · Module 16: The frontend and running it locally

Module 16: The frontend and running it locally

24 min read·
About 45 minutes · Needs: Module 4 (high-level design) and Module 6 (auth and RBAC); Module 10 helps for the approval card · Code: frontend/src/lib/api.ts, frontend/src/lib/auth.tsx, frontend/src/pages/Assistant.tsx, docker-compose.yml, Makefile

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
The parts this module covers (blue): the React app for both roles, the proxy in front of the API, and the data stores it runs with.

Every earlier module lives behind the API. This one covers what a person touches, the React app, and how to run the whole stack on one laptop, with Docker or with hot reload. Read it to demo the project or change a page. Module 17 then opens the containers line by line, and Module 18 deploys them to Google Cloud.

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