AI-Powered Hello Fresh Recipe Recommender with Qdrant and Mistral
detail.loadingPreview
This n8n workflow powers an intelligent recipe recommendation chatbot for Hello Fresh, leveraging AI to understand user preferences and suggest meals from the current week's menu. It automates data ingestion, creates a searchable knowledge base, and delivers personalized meal ideas.
About This Workflow
This comprehensive n8n workflow creates a dynamic AI-driven recipe recommendation system tailored for Hello Fresh. It begins by extracting the latest weekly menu data, including detailed recipe instructions, using advanced web scraping. This information is then processed, split, and converted into vector embeddings via Mistral AI. These embeddings are stored and efficiently searched within a Qdrant vector database, enabling lightning-fast similarity comparisons. A Mistral Large language model acts as the conversational interface, empowered by a custom tool that queries Qdrant based on user inputs (desired ingredients, cooking preferences, or dietary restrictions). The system ensures recommendations are always from the current week's offerings, providing a seamless and personalized experience for users seeking their next Hello Fresh meal.
Key Features
- Intelligent AI Chatbot: Interact with users using Mistral Large to understand complex recipe preferences and constraints.
- Personalized Recipe Recommendations: Leverage Qdrant vector search to find the most relevant recipes based on user "positives" and "negatives."
- Automated Menu Ingestion: Automatically scrape and process Hello Fresh's weekly menu, including detailed instructions.
- Local Data Persistence: Store recipe metadata in a local SQLite database for quick access and historical tracking.
- Real-time Contextual Recommendations: Ensure recommendations are always relevant to the current week's available menu.
How To Use
- Configure Qdrant Connection: Update the
Qdrant Recommend APInode with your Qdrant endpoint URL (e.g.,http://qdrant:6333). Ensure thehello_freshcollection exists or is created. - Set Up Mistral AI Credentials: Provide your Mistral Cloud API key in the
Mistral Cloud Chat ModelandEmbeddings Mistral Cloudnodes' credentials section. - Adjust Web Scraping (Optional): If Hello Fresh's website structure changes, modify the CSS selectors in the
Extract Recipe DetailsandExtract Available Coursesnodes to accurately capture recipe information. - Database Initialization: The Python script in the
Get Recipes From DBnode will automatically create ansqlite3database file (hello_fresh_1.db). Ensure n8n has write permissions in the execution directory. - Trigger Workflow: The workflow is designed to be triggered by a chat interface (
Chat Trigger) but can also be adapted for manual testing or scheduled runs.
Apps Used
Workflow JSON
{
"id": "4248ab3f-0f3b-4ed3-8dc8-b853541f908b",
"name": "AI-Powered Hello Fresh Recipe Recommender with Qdrant and Mistral",
"nodes": 5,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: 4248ab3f-0f3b...
About the Author
SaaS_Connector
Integration Guru
Connecting CRM, Notion, and Slack to automate your life.
Statistics
Related Workflows
Discover more workflows you might like
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.
Automate Getty Images Editorial Search & CMS Integration
This n8n workflow automates searching for editorial images on Getty Images, extracts key details and embed codes, and prepares them for seamless integration into your Content Management System (CMS), streamlining your content creation process.