mistral-reference-architecture

# Mistral AI Reference Architecture ## Overview Production-ready architecture patterns for Mistral AI integrations: layered project structure, singleton client, Zod-validated config, custom error classes, service layer with caching, health checks, prompt templates, and model routing. ## Prerequisites - TypeScript/Node.js project (ESM) - `@mistralai/mistralai` SDK - `zod` for config validation - Testing framework (Vitest) ## Layer Architecture ``` API Layer (Routes, Controllers, Middleware) | Service Layer (Business Logic, Orchestration) | Mistral Layer (Client, Config, Errors, Prompts) | Infrastructure Layer (Cache, Queue, Monitoring) ``` ## Instructions ### Step 1: Directory Structure ``` src/ ├── mistral/ │ ├── client.ts # Singleton client factory │ ├── config.ts # Zod-validated config │ ├── errors.ts # Custom error classes │ ├── types.ts # Shared types │ └── prompts.ts # Prompt templates ├── services/ │ ├── chat.service.ts # Chat with caching + retry │ ├── embed.service.ts # Embeddings + search │ └── rag.service.ts # RAG pipeline ├── api/ │ ├── chat.route.ts # HTTP endpoints │ └── health.route.ts # Health check └── config/ ├── base.ts # Shared config ├── development.ts # Dev overrides └── production.ts # Prod overrides ``` ### Step 2: Config with Zod Validation ```typescript // src/mistral/config.ts import { z } from 'zod'; const MistralConfigSchema = ...