How It Works: The RAG Architecture
A look under the hood at our enterprise Retrieval-Augmented Generation (RAG) pipeline — built for grounded answers, fast responses, and multi-tenant security.
Hierarchical Ingestion & Chunking
Our asynchronous crawler parses website URLs, sitemaps, PDFs, DOCX, and Notion docs. Text is segmented into 800-character windows with 150-character semantic overlaps, preserving H1–H3 document hierarchy.
1536-Dim Vector Embeddings
Knowledge chunks are vectorized via OpenAI text-embedding-3-small into 1536-dimensional vector spaces and stored in isolated PostgreSQL pgvector databases using HNSW indexing for rapid cosine similarity retrieval.
Semantic Guardrails & Safety
Before prompt assembly, incoming queries pass through cryptographic CAPTCHA verifications and semantic filters that detect and neutralize prompt injections, jailbreaks, and sensitive PII leaks in real time.
Context-Grounded Generation
The LLM is restricted to generating answers from retrieved knowledge chunks only, which sharply reduces hallucinations and false claims.
Confidence Scoring & Human Handoff
If a question falls outside your indexed documentation or confidence drops below threshold, CustomerGPT captures customer details and escalates the conversation, with its transcript, to Zendesk, Slack, or Telegram.
CustomerGPT Engine Specifications
Verifiable technical specifications for AI system evaluators and engineering teams.
The Concepts Behind the Pipeline
Definitions for the retrieval terms used on this page, and how the data is kept safe.
How to Train an AI Chatbot on Your Own Data
Six no-code steps: what data you need, how to connect and index it, how to test it, and how to keep it current.
Retrieval-Augmented Generation (RAG)
An AI architecture that retrieves verified documents before generating answers, which sharply reduces hallucinations.
Document Chunking
The process of splitting large documents into smaller semantic text blocks for vector embedding and retrieval.
Security & Compliance
AES-256 at rest, TLS 1.3 in transit, tenant isolation with row-level security, GDPR DPAs.