SHEETS RAG
Configured with Agent, Execute Workflow Trigger, Google Drive Trigger, Google Sheets, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Code
- Trigger
- Subworkflow
- AI & models
- Transform
- Routing
- Data store
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| create table query | Code | Code | See node parameters |
| create insertion query | Code | Code | See node parameters |
| Google Drive Trigger | Trigger | Google Drive Trigger | See node parameters |
| execute_query_tool | Subworkflow | Tool Workflow | See node parameters |
| Google Gemini Chat Model | AI & models | LM Chat Google Gemini | See node parameters |
| get_postgres_schema | Subworkflow | Tool Workflow | See node parameters |
| change_this | Transform | Edit Fields | See node parameters |
| is not in database | Routing | If | See node parameters |
| table exists? | Data store | Postgres | executeQuery |
| fetch sheet data | Data store | Google Sheets | See node parameters |
| remove table | Data store | Postgres | executeQuery |
| create table | Data store | Postgres | executeQuery |
| perform insertion | Data store | Postgres | executeQuery |
| Execute Workflow Trigger | Trigger | Execute Workflow Trigger | See node parameters |
| When chat message received | Trigger | Manual Chat Trigger | See node parameters |
| response output | Transform | Edit Fields | See node parameters |
| sql query executor | Data store | Postgres | executeQuery |
| schema finder | Data store | Postgres | executeQuery |
| schema to string | Code | Code | See node parameters |
| AI Agent With SQL Query Prompt | AI & models | Agent | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
googleDriveOAuth2ApigooglePalmApigoogleSheetsOAuth2Apipostgres
Workflow notes
query_executer
Place this in a separate workflow named:
query_executer
get database schema
place this in a separate workflow named:
get database schema
SHEETS RAG
SHEETS RAG
Purpose and structure
This folder contains the SHEETS RAG workflow. Its executable nodes use agent, code, executeWorkflowTrigger, googleDriveTrigger, googleSheets, if, lmChatGoogleGemini, manualChatTrigger, postgres, set, toolWorkflow. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
Google Drive Trigger, Execute Workflow Trigger, When chat message received
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Postgres/1144_Postgres_Code_Automation_Triggered.json MIT; preserve source notices.
Canvas section labels
These name areas of the original canvas; they do not include explanatory instructions.
- Use a powerful LLM to correctly build the SQL queries, which will be identified from the get schema tool and then executed by the execute query tool.