Documentation
Chat
- Getting Started
- Installation
- Core Concepts
- Escalation System
- Widget Keys
- Secret Keys (sk_)
- REST API
- Channels & Integrations
- Messaging Platform API
Voice
- Voice Agent
- Setup Guide
- Phone Numbers
- Outbound Campaigns
Platform
- Billing & Pricing
- Glossary
- FAQ
RAG (Retrieval-Augmented Generation)
A technique where the AI retrieves relevant documents from your knowledge base before generating a response, ensuring answers are grounded in your data.
Retrieval-Augmented Generation (RAG) is the technique that grounds your AI's responses in your actual data. Instead of making things up, the AI retrieves relevant information from your knowledge base before answering.
How RAG works
→
→
→
→
Without RAG
"I think the check-in time is around 2pm..." (hallucinated)
With RAG
"Check-in is at 3pm and check-out is at 11am." (from your docs)
Search methods
BM25 (voice) — Fast keyword search (~50-200ms). Used for voice calls where latency matters.
Hybrid (chat) — BM25 + vector similarity. More accurate but slower (~1-2s with embedding).
Knowledge base sources
File uploads (PDF, DOCX, TXT, Markdown)
Web page crawling (automatic scraping)
Manual content entry
