How to build an AI assistant for an online store with open-source RagLeap Core

Short answer: run RagLeap Core, load your product pages, shipping and returns policy and FAQ, and combine the built-in support, sales and returns_refunds_agent roles. It answers from the documents you load. The steps are in the general setup guide.

Which roles apply?

Among the 46 built-in roles: support, sales, returns_refunds_agent, warranty_claims_agent, inventory_agent, delivery_dispatch_agent and logistics_agent. Names are the identifiers in defaults.py at v0.11.0.

What would you upload?

Product pages and size guides, the shipping and returns policy, warranty terms and your FAQ, as PDF, Word, Excel or other files, or public web pages by address. The assistant cites the source and knows only what you load.

How do people reach it?

Through WhatsApp, Telegram, Discord or a voice line (Twilio). A website chat widget is planned, not built. Language detection runs across every channel; short messages in closely related languages can be misdetected.

What should you check first?

Connectors. The README lists Shopify and Stripe among its connectors, but its known limitations say sync runs only on demand and synced data is not yet injected into chat answers automatically, and the README is not consistent on this. Test it before relying on it.
Refunds and orders. Keep any action that changes an order or a refund at semi until you have read real conversations.
Autonomy is off by default; semi asks before acting; full is opt-in. Read real conversations before going live.
Your documents and each conversation go to the AI provider you configure. A local Ollama model keeps those steps on your machine, but local models on a CPU are slower and less accurate than Gemini.
Single-tenant: one deployment, one business, one document set. Named users and roles arrived in v0.12.0: four roles, personal keys and an audit log of who made each state-changing request (updated 2026-10-29: this page said “No named users or roles yet”). No single sign-on or multi-factor sign-in, and no independent security review yet.
No results for this field are claimed, and no compliance certification. Test with your own documents and questions.

Sources

The v0.11.0 README, defaults.py and the AI employees documentation.