SKF Incidents AI Assistant

How can I help you today?

Ask me for Incident Solution - follow-up questions are not supported.

Enter to send · Shift+Enter for a new line · AI responses may contain mistakes

Purpose

The SKF Incident Solution AI Assistant is a prototype conversational question-and-answer application built by DXC Technology for SKF. It demonstrates how a Retrieval Augmented Generation with basic features can answer questions in natural language based on context from Knowledge Articles with Large Language Models.

Key features

Conversational Q&A
RAG based answering (no fine-tuning required)
Session-based chat history with CSV export
Graceful error handling and health monitoring

Tech stack

Backend	Python 3 · Flask
AI model	Azure OpenAI (GPT-4o deployment)
AI approach	Prompt engineering with system prompt + conversation history
Frontend	HTML · CSS · vanilla JavaScript
API style	JSON REST endpoints (`/api/chat`, `/api/history`, `/api/export`)
Configuration	Environment variables via `.env` (python-dotenv)