Recipe recommendations with Qdrant and Mistral
Needs changesWhat this workflow does
This AI workflow has 24 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects Embeddings Mistral Cloud, Mistral Cloud Chat Model and Qdrant Vector Store. It also calls api.mistral.ai over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).
- Get This Week's Menu (HTTP Request): calls an HTTP API
- AI Agent: runs an AI agent, with model: Mistral Cloud Chat Model; 1 tool (Qdrant Recommend API)
- Wait: waits 1.1 seconds
- Extract Server Data (HTML): parses or builds HTML
- Get Mistral Embeddings (HTTP Request): calls api.mistral.ai (POST)
- Extract Available Courses (Code): runs custom JavaScript code
- Use Qdrant Recommend API (HTTP Request): calls an HTTP API (POST)
- Get Course Metadata (Edit Fields (Set)): sets 7 fields: name, cuisines, category…
- Get Recipe (HTTP Request): calls an HTTP API
- Get Recipes From DB (Code): runs custom Python code
…plus 6 more steps. See the full node list below.
Services it uses
HTTP calls to: api.mistral.ai
Scraping pages by hand? Firecrawl is a simpler option (10% off for new users).
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 AI Agent (v1.6): 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) AI Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (16)
- Manual Trigger
n8n-nodes-base.manualTrigger - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - HTML
n8n-nodes-base.html - Edit Fields (Set)
n8n-nodes-base.set - Embeddings Mistral Cloud
@n8n/n8n-nodes-langchain.embeddingsMistralCloud - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Merge
n8n-nodes-base.merge - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Mistral Cloud Chat Model
@n8n/n8n-nodes-langchain.lmChatMistralCloud - Wait
n8n-nodes-base.wait - AI Agent
@n8n/n8n-nodes-langchain.agent - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant
From the author
This n8n workflow demonstrates creating a recipe recommendation chatbot using the Qdrant vector store recommendation API. Use this example to build recommendation features in your AI Agents for your users. How it works For our recipes, we'll use HelloFresh's…