Convert Email Questions into Database Queries and Execute Them
Workflow Description
An intelligent automation that accepts natural language questions about emails, converts them into SQL queries using a local language model, executes them against a PostgreSQL database, and returns results immediately to the user.
How it works
- 1.Receive the question through the interactive chat interface
- 2.Transform the natural language question into SQL using Ollama language model
- 3.Execute the query on the database and retrieve results
- 4.Display the answer and log the exchange to a file
Use cases
- Answer analytical questions about emails without writing SQL code
- Automate searching and filtering email archives using natural language
- Build an intelligent assistant that understands user email intent
Requirements
- PostgreSQL database containing email message tables
- Local language model installed via Ollama or compatible LLM server
- Read and write permissions on the file system
Service Value
Ready-made workflow template for automation delivery and service execution.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (26)
Add table name to output
Set
Convert data to binary
Convert To File
Save file locally
Read Write File
Extract data from file
Extract From File
Chat Trigger
Chat Trigger
Sticky Note
Sticky Note
When clicking "Test workflow"
Manual Trigger
Combine schema data and chat input
Set
Load the schema from the local file
Read Write File
Extract SQL query
Set
Check if query exists
If
Format query results
Set
Combine query result and chat answer
Merge
List all columns in a table
Postgres
List all tables in a database
Postgres
Ollama Chat Model
Lm Chat Ollama
Postgres
Postgres
Add trailing semicolon
Set
Check for trailing semicolon
If
WorkflowTrigger
Execute Workflow Trigger
If ran manually
If
If file exists or already retried generating it
If
Sticky Note1
Sticky Note
AI Agent
Agent
Format empty output
Set
Sticky Note2
Sticky Note