Email assistant: convert natural language to SQL queries with Phi4-mini and PostgreSQL
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What to replace before upgrading
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (12)
- Edit Fields (Set)
n8n-nodes-base.set - Convert to File
n8n-nodes-base.convertToFile - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Extract from File
n8n-nodes-base.extractFromFile - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Manual Trigger
n8n-nodes-base.manualTrigger - If
n8n-nodes-base.if - Merge
n8n-nodes-base.merge - Postgres
n8n-nodes-base.postgres - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent
What it does
Who is this for? 🧑🏻🫱🏻🫲🏻🤖 Humans and Robots alike. This workflow can be used as a Chat Trigger, as well as a Workflow Trigger. It will take a natural language request, and then generate a SQL query. The resulting query parameter will contain the query, and a sqloutput parameter will contain the results of executing such query. What's the use case? This template is most useful paired with other workflows that extract e-mail information and store it in a structured Postgres table, and use LLMs to understand inquiries about information contained in an e-mail inbox and formulate questions that needs answering. Plus, the prompt can be easily adapted to formulate SQL queries over any kind of structured database. Privacy and Economics As LLM provider I'm using Ollama locally, as I consider my e-mail extremely sensitive information. As model, phi4-mini does an excellent job balancing quality and efficiency. Setup Upon running for the first time, this workflow will automatically trigger a sub-section to read all tables and extract their schema into a local file. Then, either by chatting with the workflow in n8n's interface or by using it as a sub-workflow, you will get a query and a sqloutput response. Customizations If you want to work with just one particular table yet keep edits at bay, append a condition to the List all tables in a database step, like so: sql WHERE tableschema='public' AND tablename='myemailstablename' To repurpose this workflow to work with any other data corpus in a structured database, inspect the AI Agent user and system prompts and edit them accordingly.