Automated email classification & response system with Groq AI and Pinecone
Ready for 3.0What this workflow does
This AI workflow has 34 nodes and runs when a new email arrives over IMAP (plus 1 other trigger). Along the way it connects Groq Chat Model, X (Formerly Twitter), Pinecone Vector Store and Embeddings Cohere. It also calls dropbox.com over HTTP.
How it runs
Trigger: When a new email arrives over IMAP (plus 1 other trigger).
- Code: runs custom JavaScript code
- HTTP Request: calls dropbox.com
- Switch: routes items into 7 branches
- Extract from File: extracts data from a file (pdf)
- Basic LLM Chain: sends a prompt to an LLM, with model: Groq Chat Model
- bill send to team (Send Email): sends an email over SMTP
- Send to customer (Send Email): sends an email over SMTP
- Sentiment Analysis: scores sentiment with AI, with model: Groq Chat Model
- RAG INQURY REPLY (AI Agent): runs an AI agent, with model: Groq Chat Model; 1 tool (Pinecone Vector Store)
- TO SALES TEAM (Send Email): sends an email over SMTP
…plus 13 more steps. See the full node list below.
Services it uses
HTTP calls to: dropbox.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (16)
- Email Trigger (IMAP)
n8n-nodes-base.emailReadImap - Switch
n8n-nodes-base.switch - Code
n8n-nodes-base.code - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq - X (Formerly Twitter)
n8n-nodes-base.twitter - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings Cohere
@n8n/n8n-nodes-langchain.embeddingsCohere - Manual Trigger
n8n-nodes-base.manualTrigger - HTTP Request
n8n-nodes-base.httpRequest - Extract from File
n8n-nodes-base.extractFromFile - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Send Email
n8n-nodes-base.emailSend - AI Agent
@n8n/n8n-nodes-langchain.agent - Sentiment Analysis
@n8n/n8n-nodes-langchain.sentimentAnalysis
From the author
📝 Description This workflow helps automatically classify incoming emails using a combination of conditional logic and minimal AI-based classification. The system checks email content, performs sentiment analysis, uses OpenAI for categorization, and routes…