🔬 Summarise reusable text blocks with Google Gemini from any workflow
⚡ 6 views · 🔬 Document Extraction & Analysis
Description
Quick Overview
This reusable sub-workflow is called from other n8n workflows to summarise provided text using Google Gemini, returning a consistent JSON response with a plain-language summary, key bullet points, tone, confidence, and error handling.
How it works
- Receives input from another workflow with text and optional language, audience, and maxWords parameters.
- Applies defaults for missing inputs and calculates basic metadata like character count.
- Stops early and returns a structured error response if no text is provided.
- Sends the text and summarisation instructions to Google Gemini to generate a summary, 3–5 bullets, tone, and confidence.
- Parses and normalises the model output into a consistent response object, including bulletText and metadata for the calling workflow.
Setup
- Add a Google Gemini (PaLM) API credential for the Google Gemini Chat Model node.
- Save and activate this workflow so other workflows can call it.
- In your calling workflow, use an Execute Workflow node to run this sub-workflow and map text (and optionally language, audience, and maxWords) to the workflow inputs.
🔗 Nodes Used
Execute Workflow Trigger, Basic LLM Chain, Structured Output Parser, Google Gemini Chat Model
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File