CHATBOTS

Ask a question. Every answer comes with receipts.

It searches, matches, and cites. Every answer traced to the source.

Copper Kettle Coffee RAG-powered

Welcome to Copper Kettle Coffee! I can help with our menu, locations, ordering, and company info. What would you like to know?

Retrieval Inspector

🔍

Ask a question to see how the RAG pipeline retrieves and ranks source documents.

                Behind the Build
                ▼
              

Stack

RAG pipeline bge-base-en-v1.5 embeddings Cosine similarity Cloudflare Workers AI Vectorize

Architecture

User question submitted
  → query embedded (768-dim vector)
  → top-k retrieval via cosine similarity
  → source passage extracted + scored
  → LLM generates grounded answer
  → response returned with citation

Knowledge Base

19 articles across 5 categories (Menu, Locations, Orders, Orders & Loyalty, About) for a fictional specialty coffee roaster. Articles cover espresso drinks, seasonal specials, allergens, sourcing, brewing guides, loyalty programs, catering, and more.

You just chatted with a bot that cited its sources. In production, this replaces your FAQ page and handles 80%+ of support tickets.

Try RAG & Knowledge Base to see how this scales to thousands of documents.

More where that came from.

Back to all demos →