Automate Document Q&A with Multi-Agent RAG Orchestration using Contextual AI & Gemini
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 14 nodes and runs when someone submits an n8n form (“Create your AI Agent”) (plus 1 other trigger). Along the way it connects Google Gemini Chat Model and Contextualai (community).
How it runs
Trigger: When someone submits an n8n form (“Create your AI Agent”) (plus 1 other trigger).
- Preprocessing Step (Code): runs custom JavaScript code
- Agent Orchestrator (AI Agent): runs an AI agent, with model: Google Gemini Chat Model; 2 tools (List Agents Tool, Query Agent Tool); memory: Simple Memory
- Create Agent (Contextual Ai): uses Contextual Ai
- Split Out: splits a list into separate items
- Iterate over each files (Loop Over Items (Split in Batches)): loops over the items in batches
- Wait: waits 30 seconds
- Get Document Ingestion Status (Contextual Ai): get document metadata (datastore)
- If: checks a condition and branches into true / false
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 2 community packages, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-contextualai is verified or supports 3.0 (used in Create Agent, Get Document Ingestion Status).
- Check that n8n-nodes-contextualai is verified or supports 3.0 (used in Query Agent Tool, List Agents Tool).
Nodes used (12)
- Contextual Ai
n8n-nodes-contextualai.contextualAi - n8n Form Trigger
n8n-nodes-base.formTrigger - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Contextual Ai Tool
n8n-nodes-contextualai.contextualAiTool - Split Out
n8n-nodes-base.splitOut - Wait
n8n-nodes-base.wait - If
n8n-nodes-base.if - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches
From the author
PROBLEM Managing multiple RAG AI agents can be complex when each has its own purpose and vector database. - Manually tracking agents and deciding which one to query wastes time. - LLMs often struggle to determine which agent best fits a user’s request. This…