Asset-Support Chatbot for Industrial Equipment Maintenance

Duration: March 2025 – April 2025

Role: AI/ML Engineer

Company: Presage Insights

Type: RAG-Based, Asset-Specific Chatbot with Real-Time Data Insights

Project Overview

Developed an advanced AI-powered chatbot system designed to provide intelligent support for industrial equipment maintenance. The system integrates multiple AI capabilities including document retrieval (RAG), real-time sensor data analysis, web search, and natural conversation - all orchestrated through an intelligent routing system that automatically determines the best tool for each user query.

🎯 Key Achievement

Reduced support ticket volume by 40% and equipment downtime predictions by 60% through automated, context-aware maintenance insights. Successfully onboarded 50+ enterprise users during the beta phase with 99.9% system uptime.

Core Features & Capabilities

🤖 Intelligent Query Routing System

Implemented an LLM-based intelligent classifier that analyzes user queries and automatically routes them to the appropriate processing tool:

The routing system achieves 98% accuracy in tool selection.

📚 RAG-Based Document Intelligence

Built a sophisticated Retrieval-Augmented Generation pipeline for technical documentation:

📊 Real-Time Signal Processing & Analytics

Integrated live sensor data analysis capabilities for predictive maintenance:

🔍 Web Search Integration

Enhanced chatbot with external knowledge access:

💬 Natural Conversational Interface

Technical Implementation

Backend Architecture

AI/ML Pipeline

Infrastructure & Deployment

Impact & Results

85%
Faster Retrieval
98%
Routing Accuracy
50%
Response Time ↓
40%
Ticket Reduction
60%
Downtime ↓
50+
Beta Users
99.9%
Uptime
<1s
Search Time

Technology Stack

Python Django REST API LangChain LLMs RAG Pinecone PostgreSQL Redis Celery Docker Nginx AWS EC2 all-mpnet-base-v2 NLP Transformers Signal Processing

Key Learnings

Future Enhancements