Tech Stack
| Layer | Technology |
|---|---|
| Frontend | React 18, TypeScript, Vite, Tailwind CSS, Radix UI |
| Backend | Node.js, Express.js, TypeScript |
| Database | MySQL 8 (Drizzle ORM) |
| Caching | Redis (Upstash in production) |
| Auth | JWT access + refresh tokens, OAuth2 (Google, Twitter, Facebook) |
| AI / LLM | Google Gemini, LangChain, OpenAI (embeddings) |
| Vector DB | Qdrant (RAG / semantic search) |
| Cloud Storage | AWS S3 |
| Payments | Stripe, Cashfree |
| Gupshup (primary), Wasimple, Facebook Meta | |
| Real-time | WebSockets |
| Job Scheduling | node-cron |
High-Level Architecture
Browser / WhatsApp / Telegram / Gmail / Twitter
│
▼
Express.js Server (port 5001)
├── REST API (~160+ endpoints) ←── JWT Auth middleware
├── WebSocket Server ←── Real-time inbox updates
├── Webhook handlers ←── Gupshup / Wasimple / Meta / Stripe
└── Static file server ←── Vite-built React app
│
├── MySQL 8 (Drizzle ORM)
├── Redis (session cache, job queue)
├── AWS S3 (media + training files)
├── Qdrant (vector store for RAG)
└── AI Agent Process (port 5555)
└── LangChain + Gemini / OpenAI
Project Structure
sahyogi/
├── client/src/ # React frontend
│ ├── pages/ # Route-level components
│ ├── components/ # Shared UI components
│ ├── hooks/ # Custom React hooks
│ └── lib/ # API clients, utilities
│
├── server/ # Express backend
│ ├── routes.ts # All API routes (160+ endpoints)
│ ├── db.ts # MySQL connection pool
│ ├── jwt-auth.ts # JWT middleware
│ ├── storage.ts # DB query/mutation layer
│ ├── stripe.ts # Stripe client + webhooks
│ ├── websocket.ts # WebSocket server
│ ├── cron.ts # Scheduled jobs
│ └── utils/ # vectorSearch, encryption, events
│
├── shared/
│ ├── schema.ts # Drizzle schema + Zod types (source of truth)
│ ├── gupshup.ts # Gupshup API client
│ └── wasimple.ts # Wasimple API client
│
├── agent/ # Standalone AI agent (port 5555)
└── db/ # Migrations + seed
Key Flows
Message Flow (WhatsApp → Bot → User)
WhatsApp user sends message
│
▼
Gupshup/Wasimple/Meta webhook → POST /api/webhooks/...
│
▼
Bot lookup (channel → bot mapping)
│
▼
AI Agent (LangChain + Gemini)
├── Tool calls (Airtable, webhooks, API tools)
└── RAG: Qdrant vector search → context injection
│
▼
Response sent back via WhatsApp provider API
│
▼
Message stored in MySQL → WebSocket push to inbox
RAG (Knowledge Base) Flow
User uploads PDF / URL
│
▼
File stored in AWS S3 / URL scraped
│
▼
processTrainingFiles.ts / processTrainingUrls.ts
→ Text chunked → Embeddings via Gemini/OpenAI
→ Stored in Qdrant vector collection
│
▼
On bot message → vectorSearch.ts queries Qdrant
→ Top-k chunks injected into LLM prompt
Channels
| Channel | Provider | Auth method |
|---|---|---|
| Gupshup (primary) | API Key | |
| Wasimple | API Key | |
| Facebook/Meta | OAuth2 | |
| Gmail | OAuth2 | |
| OAuth2 | ||
| Web | Built-in | Bot ID |
| Telegram, Slack, Discord | On request | — |
AI & Integrations
| Service | Role |
|---|---|
| Google Gemini | LLM for bot responses + embeddings |
| OpenAI | Embedding fallback |
| Qdrant | Vector search for knowledge-base RAG |
| LangChain | Agent orchestration, tool use, RAG pipeline |
| Airtable | Bot tool — read/write CRM data |
| AWS S3 | Media and training file storage |
| Stripe | Subscription billing |
| Cashfree | Alternative billing (India) |
| Redis | Session caching, queue |