Voice AI chatbot with OpenAI, RAG (Qdrant) & Guardrails for WordPress
Needs changesWhat this workflow does
This AI workflow has 27 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Qdrant Vector Store, Embeddings OpenAI and Guardrails and 3 more. It also calls collections over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Create collection (HTTP Request): calls collections (PUT)
- Clear collection (HTTP Request): calls an HTTP API (POST)
- Generate text (STT) (OpenAI): transcribe (audio)
- Search files (Google Drive): work with file folder
- Guardrails: uses Guardrails, with model: OpenAI Chat Model
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Voicebot AI Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (RAG, Calculator); memory: Window Buffer Memory
- Default response (TTS) (OpenAI): work with audio
- Get files (Google Drive): download
- Generate audio (TTS) (OpenAI): work with audio
…plus 4 more steps. See the full node list below.
Services it uses
HTTP calls to: collections
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Voicebot AI Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
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) Voicebot AI Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (18)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Respond to Webhook
n8n-nodes-base.respondToWebhook - Webhook
n8n-nodes-base.webhook - Guardrails
@n8n/n8n-nodes-langchain.guardrails - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Manual Trigger
n8n-nodes-base.manualTrigger - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - HTTP Request
n8n-nodes-base.httpRequest - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Google Drive
n8n-nodes-base.googleDrive - Wait
n8n-nodes-base.wait - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI
@n8n/n8n-nodes-langchain.openAi
From the author
This workflow implements a complete Voice AI Chatbot system for Wordress that integrates speech recognition, guardrails for safety, retrieval-augmented generation (RAG), Qdrant vector search, and audio responses. It is designed to be connected to a WordPress…