Run a WhatsApp customer support chatbot with OpenWA, OpenAI and Qdrant
UnknownWhat this workflow does
This AI workflow has 26 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects OpenAI Chat Model, DebugHelper, Qdrant Vector Store and Embeddings OpenAI and 4 more. It also calls qdranturl over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Create collection (HTTP Request): calls qdranturl (POST)
- Refresh collection (HTTP Request): calls an HTTP API (POST)
- Switch: routes items into 2 branches
- Get folder (Google Drive): work with file folder
- Edit Fields (Edit Fields (Set)): sets 8 fields: from, to, chat_id…
- Send Text (Open Wa): uses Open Wa
- Download Files (Google Drive): download
- Customer Support Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 3 tools (Calculator, rag_search, get_human_support); memory: Window Buffer Memory
- DebugHelper: uses DebugHelper
- Qdrant Vector Store: stores documents in the Qdrant vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
…plus 3 more steps. See the full node list below.
Services it uses
HTTP calls to: qdranturl
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 @rmyndharis/n8n-nodes-openwa is verified or supports 3.0 (used in OpenWA Trigger).
- Check that @rmyndharis/n8n-nodes-openwa is verified or supports 3.0 (used in Send Text, Send Text1).
Nodes used (19)
- Switch
n8n-nodes-base.switch - Open Wa Trigger
@rmyndharis/n8n-nodes-openwa.openWaTrigger - Open Wa
@rmyndharis/n8n-nodes-openwa.openWa - Edit Fields (Set)
n8n-nodes-base.set - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - DebugHelper
n8n-nodes-base.debugHelper - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Gmail Tool
n8n-nodes-base.gmailTool - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Manual Trigger
n8n-nodes-base.manualTrigger - HTTP Request
n8n-nodes-base.httpRequest - Google Drive
n8n-nodes-base.googleDrive - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Token Splitter
@n8n/n8n-nodes-langchain.textSplitterTokenSplitter
From the author
Quick overview This workflow builds a WhatsApp customer-support chatbot using OpenWA and OpenAI, enriched with Qdrant RAG knowledge and optional Gmail escalation to a human agent, plus a manual knowledge-base ingestion flow that loads documents from Google…