The flow
Starts it 1Model 4Logic 4Service 2
The steps in the order they run, from what starts it.
- 1Simple MemoryMemory Buffer WindowModel
- 2OpenAI Chat ModelLm Chat Open AiModel
- 3Structured Output ParserOutput Parser StructuredModel
- 4Embedable chat for users to ask questions of bigqueryChat triggerStarts it
- 5AI Agent - Write SQL QueryAgentModel
- 6Output all table, and column names in your schemaGoogle Big QueryService
- 7combine the table names with user questionMergeLogic
- 8Run query against schemaGoogle Big QueryService
- 9Combine into one fieldAggregateLogic
- 10Ask User to try another questionCodeLogic
- 11Convert table names and columns into single text for agentCodeLogic
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 11
- Size
- Medium: a working afternoon
- Connects to
- Nothing by connector; it calls services over plain HTTP
- Model
- OpenAI
- Retrieval
- Answers are drawn from documents you supply, not from the model alone
Questions
What does it need to run?
An n8n account, and a key for OpenAI. You connect your own accounts after importing it; none are included.
What starts it?
It starts on someone opening a chat with it.
Does it use AI?
Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 11 steps is enough that you should read each one before running it.
How do I import it?
Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.
Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 11 steps before you point it at anything that matters.