AI-Powered Maintenance Ticket Router with RAG
detail.loadingPreview
Automate and intelligently route incoming maintenance tickets using advanced AI. This workflow leverages large language models and a vector knowledge base to understand ticket context, retrieve relevant solutions, and log decisions seamlessly.
About This Workflow
Streamline your maintenance operations with this robust AI-powered ticket router. Upon receiving a new maintenance request via a webhook, the system intelligently processes the ticket content. It utilizes Cohere embeddings to transform the text into searchable vectors, which are then stored and queried within a Supabase vector database. A Langchain Agent, powered by a Hugging Face chat model, uses this retrieved context alongside its conversational memory to analyze the ticket. This Retrieval Augmented Generation (RAG) approach ensures accurate classification and routing, ultimately logging the agent's decision to Google Sheets for seamless tracking and action.
Key Features
- Intelligent Ticket Classification: AI-powered analysis to understand the nature and urgency of maintenance requests.
- Contextual RAG (Retrieval Augmented Generation): Integrates with a Supabase vector store to pull relevant information (e.g., past solutions, FAQs, responsible teams) for informed decision-making.
- Conversational Memory: The AI agent maintains context to handle complex or multi-step requests effectively.
- Automated Logging: Automatically records all routed tickets and agent decisions into Google Sheets for auditing and reporting.
- Scalable & Customizable AI: Leverages powerful LLMs (Hugging Face) and embedding models (Cohere) with flexible configuration.
How To Use
- Set up Credentials:
- Configure your
CohereAPI credentials for text embeddings. - Set up
SupabaseAPI credentials for your vector store. Ensure your Supabase instance has thepgvectorextension enabled. - Provide
HuggingFaceAPI credentials for the Large Language Model. - Authenticate your
Google SheetsAPI credentials.
- Configure your
- Configure the Webhook:
- Define the
pathfor your incoming maintenance ticket requests (e.g.,/maintenance_ticket_router). - Ensure your external systems send POST requests to this endpoint with ticket data.
- Define the
- Customize the Agent:
- Modify the
Agentnode's prompt to guide its decision-making process for ticket routing and classification.
- Modify the
- Populate Supabase Vector Store:
- Use the 'Insert' path (Webhook -> Splitter -> Embeddings -> Insert) to initially populate your
maintenance_ticket_routerindex with historical tickets, solutions, or knowledge base articles. This builds the RAG knowledge base.
- Use the 'Insert' path (Webhook -> Splitter -> Embeddings -> Insert) to initially populate your
- Google Sheets Integration:
- Specify the
SHEET_IDandsheetNamein theSheetnode where the agent's output should be logged.
- Specify the
Apps Used
Workflow JSON
{
"id": "7ccf7105-0b2f-43a1-9288-a6cb978a1804",
"name": "AI-Powered Maintenance Ticket Router with RAG",
"nodes": 29,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 7ccf7105-0b2f...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Related Workflows
Discover more workflows you might like
Google Sheets to Icypeas: Automated Bulk Domain Scanning
This workflow streamlines the process of performing bulk domain scans by integrating your Google Sheets data directly with the Icypeas platform. Automate the submission of company names from your spreadsheet to Icypeas for comprehensive domain information, saving valuable time and effort.
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.