Manage Gemini File Search RAG stores and documents with n8n forms

by KPendic ✓ · 7 views · created 2026-09-18 · Document Extraction, AI RAG

What this workflow does

This workflow has 42 nodes and runs when someone submits an n8n form (“Gemini RAG — ingest documents”) (plus 1 other trigger). It uses only n8n's built-in nodes. It also calls generativelanguage.googleapis.com over HTTP.

How it runs

Trigger: When someone submits an n8n form (“Gemini RAG — ingest documents”) (plus 1 other trigger).

1. If: checks a condition and branches into true / false
2. Normalize Tool Input (Code): runs custom JavaScript code
3. switch (Code): runs custom JavaScript code
4. FS (HTTP Request): calls generativelanguage.googleapis.com (POST)
5. Route Action (Switch): routes items into 7 branches
6. loop (Loop Over Items (Split in Batches)): loops over the items in batches
7. sn (Edit Fields (Set)): sets 2 fields: sname, displayName
8. List RAG Stores (HTTP Request): calls generativelanguage.googleapis.com
9. Create RAG Store (HTTP Request): calls generativelanguage.googleapis.com (POST)
10. Get RAG Store (HTTP Request): calls an HTTP API

…plus 30 more steps. See the full node list below.

HTTP calls to: generativelanguage.googleapis.com

Before you upgrade to n8n 3.0

Nodes used (9)

• HTTP Requestn8n-nodes-base.httpRequest
• Ifn8n-nodes-base.if
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• n8n Formn8n-nodes-base.form
• Switchn8n-nodes-base.switch
• Execute Workflow Triggern8n-nodes-base.executeWorkflowTrigger
• n8n Form Triggern8n-nodes-base.formTrigger

From the author

Quick Overview This workflow creates and manages Gemini File Search RAG stores via an Agents tool, and ingests documents through an n8n Form that uploads files to Google’s Generative Language API for indexing. How it works 1. Receives tool calls from an n8n…

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