Run an English website chatbot with OpenAI GPT-5 and Qdrant
Ready for 3.0What this workflow does
This AI workflow has 17 nodes and runs when an HTTP GET request hits its webhook URL. Along the way it connects OpenAI, Qdrant Vector Store, OpenAI Chat Model and Embeddings OpenAI and 1 more.
How it runs
Trigger: When an HTTP GET request hits its webhook URL.
- Normalize Webhook Payload (Code): runs custom JavaScript code
- OpenAI: uses OpenAI
- Route by Intent and Language (Switch): routes items into branches
- Format Safety Message (Code): runs custom JavaScript code
- OpenAI: uses OpenAI
- Search Qdrant Knowledge Base (Qdrant Vector Store): uses the Qdrant vector store, with embeddings: Generate Query Embeddings with OpenAI
- Return Chatbot Webhook Response (Respond to Webhook): sends the response back to the webhook caller
- Format Smalltalk Output (Code): runs custom JavaScript code
- Build Answer Context (Code): runs custom JavaScript code
- Answer Generator Agent (AI Agent): runs an AI agent, with model: OpenAI GPT; output parser: Define Answer JSON Schema
…plus 2 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (11)
- Code
n8n-nodes-base.code - OpenAI
@n8n/n8n-nodes-langchain.openAi - AI Agent
@n8n/n8n-nodes-langchain.agent - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Reranker Cohere
@n8n/n8n-nodes-langchain.rerankerCohere - Switch
n8n-nodes-base.switch - Webhook
n8n-nodes-base.webhook - Respond to Webhook
n8n-nodes-base.respondToWebhook
From the author
Quick Overview This workflow exposes a secured webhook that powers an English website chatbot, using OpenAI for intent detection and responses and Qdrant (with optional Cohere reranking) to retrieve relevant website content and return structured JSON search…