📖 Chat with a research assistant using Google Gemini, Wikipedia, and Sheets
⚡ 17 views · 📖 Internal Wiki & Knowledge Base
Description
Quick Overview
This workflow provides a chat-based research assistant powered by Google Gemini that can look up facts on Wikipedia, do calculations, and remember context, while also tagging each user question and logging it to a Google Sheets spreadsheet.
How it works
- Receives a user message through the built-in n8n chat webhook trigger.
- Sends the message to a Google Gemini agent that can consult Wikipedia for factual lookups and use a Calculator tool for arithmetic.
- Uses a buffer memory window to keep recent conversation context so follow-up questions stay coherent.
- Streams the agent’s plain-language, cited response back to the chat.
- In parallel, uses Google Gemini to generate a short 1–3 word topic label for the question.
- Appends the original question and its topic label to a Google Sheets tab for tracking what users ask.
Setup
- Add Google Gemini (PaLM) API credentials for the agent model and the topic-tagging model.
- Add a Google Sheets OAuth2 connection and select the target spreadsheet and the “Questions” sheet in the logging step.
- Open the chat URL for the workflow’s public chat trigger and share it with users who should be able to ask questions.
🔗 Nodes Used
Google Sheets, AI Agent, Basic LLM Chain, Simple Memory, Calculator, Wikipedia
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File