Library / AI Agents & Assistants
AI Agents & Assistants
Query BigQuery with an OpenAI agent via a generated and cleaned SQL pipeline
Called by another workflow, it lets an OpenAI chat model agent write SQL, clean it, and run it against BigQuery instead of using the built-in BigQuery tool.
What it does
### 2. AI Agent equipped with the query tool In order to have more control on the input of the BigQuery node, we don't use the BigQuery tool. Instead we have a set of nodes to retrieve the SQL query, clean it and send it to a BigQuery Node. #### How to setup? - AI Agent with the Chat Model: 1. Add a chat model with the required credentials *(Example: Open AI 4o-mini)* 2. Adapt the name of your BigQuery table in the system prompt *(Example: transports.shipments)* 3. Adapt the tables fields explanation in the system prompt [Learn more about the AI Agent Node]({{ $env.WEBHOOK_URL }} - Copy and past the nodes in the yellow sticker in another workflow. Point the query tool to this workflow. [Learn more about the Custom n8n Workflow Tool node]({{ $env.WEBHOOK_URL }}
The steps
- OpenAI Chat Model
- AI Control Tower Agent
- Call Query Tool
- Query Database
- Trigger Executed by the AI Tool
- Sanitising the Query
- Chat Memory
- Chat with the User
- Error Handler
Similar automations