Build a RAG system by uploading PDFs to the Google Gemini File Search Store

by Davide Boizza ✓ · 4,242 views · created 2025-11-24 · Internal Wiki, AI RAG

What this workflow does

This AI workflow has 14 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects Google Gemini Chat Model and HTTP Request. It also calls generativelanguage.googleapis.com over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).

1. Create Store (HTTP Request): calls generativelanguage.googleapis.com (POST)
2. Merge: merges the data from its input branches
3. Get Store (Edit Fields (Set)): sets 1 field: Search Store
4. Get Store (Edit Fields (Set)): sets 1 field: Search Store
5. Merge: merges the data from its input branches
6. Upload File (HTTP Request): calls generativelanguage.googleapis.com (POST)
7. Rag Agent (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; 1 tool (SearchStore); memory: Simple Memory
8. Import to Store (HTTP Request): calls an HTTP API (POST)

Services it uses

Google Gemini Chat ModelHTTP Request

HTTP calls to: generativelanguage.googleapis.com

Before you upgrade to n8n 3.0

Nodes used (10)

• Manual Triggern8n-nodes-base.manualTrigger
• n8n Form Triggern8n-nodes-base.formTrigger
• Mergen8n-nodes-base.merge
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• Http Request Tooln8n-nodes-base.httpRequestTool
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• HTTP Requestn8n-nodes-base.httpRequest
• Edit Fields (Set)n8n-nodes-base.set
• AI Agent@n8n/n8n-nodes-langchain.agent

From the author

This workflow implements a Retrieval-Augmented Generation (RAG) system using Google Gemini's File Search API. It allows users to upload files to a dedicated search store and then ask questions about their content in a chat interface. The system automatically…

View the original on n8n.io → Check your own copy