🛠️ Auto workflow positioning
Needs changesNeeds changes. This template uses 2 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes), HTTP Request Tool (legacy). 2 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 31 nodes and runs when an HTTP POST request hits its webhook URL (plus 2 other triggers). Along the way it connects OpenAI Chat Model, Embeddings OpenAI and HTTP Request. It also calls api.ia2s.app over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 2 other triggers).
- Get n8n Workflow (n8n): get
- If: checks a condition and branches into true / false
- Magic Positioning IA2S (HTTP Request): calls api.ia2s.app (POST)
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Dummy Tool, Dummy Tool (1)); memory: Window Buffer Memory
- Update n8n Workflow (n8n): update
- Simple Webhook Response (Respond to Webhook): sends the response back to the webhook caller
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Switch: routes items into 5 branches
- Question and Answer Chain: answers questions over your documents (RAG), with model: OpenAI Chat Model; retriever: Vector Store Retriever
- Magic Positioning (HTTP Request): calls an HTTP API (POST)
Services it uses
HTTP calls to: api.ia2s.app
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.2): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- HTTP Request Tool (legacy) in Dummy Tool, Dummy Tool (1): replace with HTTP Request node connected to the AI Agent's Tool input.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.2) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
| HTTP Request Tool (legacy) Dummy Tool, Dummy Tool (1) | HTTP Request node connected to the AI Agent's Tool input |
Nodes used (18)
- Manual Trigger
n8n-nodes-base.manualTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Vector Store Retriever
@n8n/n8n-nodes-langchain.retrieverVectorStore - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Question and Answer Chain
@n8n/n8n-nodes-langchain.chainRetrievalQa - Switch
n8n-nodes-base.switch - If
n8n-nodes-base.if - No Operation, do nothing
n8n-nodes-base.noOp - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - n8n
n8n-nodes-base.n8n - HTTP Request
n8n-nodes-base.httpRequest - Webhook
n8n-nodes-base.webhook - Respond to Webhook
n8n-nodes-base.respondToWebhook - Schedule Trigger
n8n-nodes-base.scheduleTrigger
From the author
Check Online Version ! https://n8n-tools.streamlit.app/ Who is it for? This workflow is perfect for n8n users who want to maintain clean and organized workflows without manually repositioning nodes. Whether you're building complex workflows or sharing them…