RAG-based chatbot

RAG-based chatbot on your own documents — accurate answers, cited sources.

Nortinia AI Assistant with RAG (Retrieval Augmented Generation): it answers accurately from your own documents, cites sources and minimises hallucination. Multi-tenant, on-premise option.

Citationevery answer references a source
Multi-docreasons across multiple docs
Re-ranktwo-stage retrieval + re-rank
What this means

What is RAG and why does it matter?

RAG (Retrieval Augmented Generation) is the latest generation of AI chatbots: before answering, the system retrieves relevant documents and the LLM generates from them.

Result: more accurate answers, cited sources, minimised hallucination. The Nortinia engine uses two-stage retrieval (semantic + keyword) and re-ranking for maximum precision.

RAG features

What sets Nortinia RAG apart?

01

Two-stage retrieval

Semantic + keyword search + re-rank. Higher precision on top-k documents.

02

Citation

Every answer references the source document — full traceability.

03

Multi-doc reasoning

Connects multiple documents in the answer — doesn't just copy one snippet.

04

Eval harness

Built-in eval framework: ground truth, retrieval@k, faithfulness, answer relevancy.

Rollout

RAG rollout in 4 steps

01

Document import

URLs, PDFs, Markdown, Notion, Confluence, SharePoint — bulk upload.

02

Chunking + indexing

Adaptive chunking, vector + keyword index, metadata tagging.

03

Pilot question set

Eval set to measure retrieval@k and faithfulness.

04

Go live

A/B-tested prompt fine-tuning, model pinning, monitoring.

Frequently asked questions

RAG chatbot — questions

What is the difference between a "plain" chatbot and RAG?

A plain chatbot answers from the model's trained knowledge (or hallucinates). RAG always retrieves from your documents and generates only from them.

Which formats are accepted?

PDF, DOCX, Markdown, HTML, URL, JSON, CSV, Notion, Confluence, SharePoint, Google Drive. Uploadable via API too.

How does it minimise hallucination?

Mandatory citation, re-rank on top-k, faithfulness scoring in eval, escalation on low confidence.

Does the knowledge base update automatically?

Yes — automatic crawl + diff-based re-indexing. Configurable interval (hourly to daily).

RAG on your own documents

We'll show the RAG chatbot on your own knowledge base.

30-minute demo, eval set, accuracy estimate at the end.