Automated Customer Auto-tagging with Webhooks and RAG
detail.loadingPreview
This workflow automatically tags customers by processing incoming webhook data through a RAG (Retrieval-Augmented Generation) system. It leverages Text Splitter, Embeddings, Pinecone, and an OpenAI Chat Model to dynamically categorize and log customer information.
🚀Ready to Deploy This Workflow?
About This Workflow
Overview
This n8n workflow automates the process of customer auto-tagging. It's triggered via a webhook, allowing external systems to send customer data. The data is then processed using a Retrieval-Augmented Generation (RAG) approach, which combines the power of large language models with a vector database (Pinecone) for context-aware tagging. The workflow splits the incoming text, generates embeddings, stores them in Pinecone, queries for relevant information, and uses an OpenAI chat model to determine appropriate tags. Finally, the generated tags are appended to a Google Sheet for logging and an alert can be sent via Slack in case of errors.
Key Features
- Triggered by webhook for real-time data processing.
- Utilizes Text Splitter to segment incoming data.
- Generates embeddings using Cohere for semantic understanding.
- Leverages Pinecone as a vector database for efficient storage and retrieval.
- Employs OpenAI's Chat Model for intelligent tag generation.
- Implements a RAG Agent for contextually relevant tagging.
- Logs tagged data to a Google Sheet.
- Includes Slack alerting for error handling.
How To Use
- Set up the Webhook Trigger: Configure your external system to send POST requests to the n8n webhook URL with customer data in the request body.
- Configure Text Splitter: Adjust
chunkSizeandchunkOverlapparameters as needed for your data. - Set up Embeddings: Ensure your Cohere API credentials are correctly configured.
- Configure Pinecone: Set up your Pinecone index (
customer_auto-tagging) and provide your API credentials. - Configure OpenAI Chat Model: Provide your OpenAI API credentials and select a suitable model.
- Configure RAG Agent: Define the
textprompt for the RAG Agent, including how to incorporate the incoming data ({{ $json }}). Set thesystemMessagefor context. - Configure Append Sheet: Specify your Google Sheet ID and sheet name (
Log). Map the output from theRAG Agentto the desired column (e.g., 'Status'). Ensure Google Sheets API credentials are set up. - Configure Slack Alert: Set up your Slack API credentials and specify the channel for alerts.
Apps Used
Workflow JSON
{
"id": "7590eb81-a407-4417-8feb-6098b5e0a86b",
"name": "Automated Customer Auto-tagging with Webhooks and RAG",
"nodes": 0,
"category": "Automation",
"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: 7590eb81-a407...
About the Author
Free n8n Workflows Official
System Admin
The official repository for verified enterprise-grade workflows.
Statistics
Verification Info
Related Workflows
Discover more workflows you might like
Supply Chain Delay Monitor
Automated monitoring and logging of supply chain delays using a webhook, text processing, embeddings, and a vector store.
Inventory Slack Alert Workflow
Triggers an alert based on inventory changes, processes data using RAG, and logs results.
Dynamic Prompt Generation from GitHub with Language Model Integration
Fetches prompts from a GitHub repository, substitutes variables, and processes them with an AI agent.