🎫 Triage emails and build a morning digest with a local Ollama LLM
⚡ 34 views · 🎫 Ticket Management & Triage
Description
Quick overview
This workflow triages emails with a local Ollama LLM (gemma4:e4b), flags urgent messages for immediate alerting, and compiles a morning digest grouped by urgency categories.
How it works
- Runs manually and generates a sample set of incoming emails.
- Sends each email to Ollama (gemma4:e4b) with a prompt that classifies it as URGENT, REPLY_TODAY, FYI, or JUNK and returns structured JSON.
- Parses the LLM output into JSON and falls back to a safe default classification if the response is malformed.
- Separates emails marked URGENT and formats an urgent alert message for each one.
- Aggregates all classified emails into a single morning digest text grouped by category with suggested actions and totals.
- If the workflow errors, captures the failure details and outputs a structured error record.
Setup
- Set up an Ollama API credential in n8n that points to your Ollama server (for example, http://host.docker.internal:11434).
- Ensure the specified Ollama model (gemma4:e4b) is available locally, or update the model name in the Ollama Chat Model configuration.
- Replace the sample email generator with your real email source (for example, Gmail or Microsoft Outlook) and add a delivery step for urgent alerts and the digest (for example, Slack or email).
Requirements
- n8n 1.19.4 or later (LangChain nodes required)
- Ollama running locally with a chat model (tested with gemma4:e4b)
Customization
- Edit the classification prompt in the Classify Email node to add or change urgency categories
- Swap the Ollama Chat Model for OpenAI or Anthropic by replacing the LLM sub-node
- Connect Slack, Telegram, or email after the Format Urgent Alert node for instant notifications
🔗 Nodes Used
Basic LLM Chain, Ollama Chat Model
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File