Recipe Recommendations with Qdrant and Mistral — Workflow n8n

Wysoka złożoność⚡ Wyzwalacz24 węzłów🏷️ Miscellaneous👁 6,207 wyświetleńautor: Jimleuk

Przegląd

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 weekly course and recipes for data. We'll scrape the website for this data. Each recipe is split, vectorised and inserted into a Qdrant Collection using Mistral Embeddings Additionally the whole recipe is stored in a SQLite database for l

Użyte węzły

HTTP RequestCodeHTMLAI AgentRecursive Character Text SplitterCall n8n Workflow ToolDefault Data LoaderEmbeddings Mistral CloudMistral Cloud Chat ModelQdrant Vector Store

Podgląd workflow

Step 1. Fetch Available Courses For the Curre
To populate our vectorstore, we'll scrape the weekly me
Step 2. Create Recipe Documents For VectorSto
To populate our vectorstore, we'll scrape the weekly me
Step 3. Vectorise Recipes For Recommendation
Read more about Qdrant node
We'll sto
Step 4. Save Original Document to Database
Read more about Code Node
Finally, let's have the original document stored in
5. Chat with Our HelloFresh Recommendation AI
Read more about AI Agents
This agent is designed
5. Using Qdrant's Recommend API & Grouping Fu
Read more about Qdrant's Recommend API
Unlike basic similarity search, Q
Try it out!
This workflow does the following:
* Fetches and stores this week's HelloFresh's menu
* Builds the foundation of a recommendation engine by s
🚨Ensure Qdrant collection exists!
You'll need to run the following command in Qdrant:
```
PUT collections/hello_fresh
{
"vectors": {
🚨Configure Your Qdrant Connection
* Be sure to enter your endpoint address
doctoolembedmodel
⚡
W
When clicking "Test work…
Get This Week's Menu
Extract Available Courses
Extract Server Data
G
Get Course Metadata
Get Recipe
Embeddings Mistral Cloud
Default Data Loader
M
Merge Course & Recipe
P
Prepare Documents
Recursive Character Text…
⚡
C
Chat Trigger
Extract Recipe Details
Qdrant Recommend API
⚡
E
Execute Workflow Trigger
Mistral Cloud Chat Model
G
Get Tool Response
W
Wait for Rate Limits
Get Mistral Embeddings
Use Qdrant Recommend API
Get Recipes From DB
Save Recipes to DB
AI Agent
Qdrant Vector Store
24 nodes22 edges

Jak to działa

  1. 1

    Wyzwalacz

    Workflow uruchamia się wyzwalaczem wyzwalacz.

  2. 2

    Przetwarzanie

    Dane przepływają przez 24 węzłów, connecting agent, chattrigger, code.

  3. 3

    Wyjście

    Workflow kończy automatyzację i dostarcza wynik do skonfigurowanego miejsca docelowego.

Szczegóły węzłów (24)

HT

HTTP Request

httpRequest

#1
CO

Code

code

#2
HT

HTML

html

#3
AI

AI Agent

n8n-nodes-langchain.agent

#4
RE

Recursive Character Text Splitter

n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter

#5
CA

Call n8n Workflow Tool

n8n-nodes-langchain.toolWorkflow

#6
DE

Default Data Loader

n8n-nodes-langchain.documentDefaultDataLoader

#7
EM

Embeddings Mistral Cloud

n8n-nodes-langchain.embeddingsMistralCloud

#8
MI

Mistral Cloud Chat Model

n8n-nodes-langchain.lmChatMistralCloud

#9
QD

Qdrant Vector Store

n8n-nodes-langchain.vectorStoreQdrant

#10

Jak zaimportować ten workflow

  1. 1Kliknij przycisk Pobierz JSON po prawej stronie, aby zapisać plik workflow.
  2. 2Otwórz swoją instancję n8n. Przejdź do Workflow → Nowy → Importuj z pliku.
  3. 3Wybierz pobrany plik recipe-recommendations-with-qdrant-and-mistral i kliknij Importuj.
  4. 4Skonfiguruj dane uwierzytelniające dla każdego węzła usługi (klucze API, OAuth itp.).
  5. 5Kliknij Testuj workflow, aby sprawdzić, czy wszystko działa, a następnie aktywuj go.

Lub wklej bezpośrednio w n8n → Importuj z JSON:

{ "name": "Recipe Recommendations with Qdrant and Mistral", "nodes": [...], ...}

Integracje

agentchattriggercodedocumentdefaultdataloaderembeddingsmistralcloudexecuteworkflowtriggerhtmlhttprequestlmchatmistralcloudmanualtriggermergesettextsplitterrecursivecharactertextsplittertoolworkflowvectorstoreqdrantwait

Pobierz ten workflow

Pobierz i zaimportuj jednym kliknięciem

Pobierz JSONZobacz na n8n.io
Węzły24
Złożonośćhigh
Wyzwalacztrigger
Wyświetlenia6,207
KategoriaMiscellaneous

Autor

Jimleuk

Jimleuk

@jimleuk

Tagi

agentchattriggercodedocumentdefaultdataloaderembeddingsmistralcloudexecuteworkflowtriggerhtmlhttprequestlmchatmistralcloudmanualtrigger
⚡

Nowy w n8n?

n8n to darmowe narzędzie open-source do automatyzacji workflow. Hostuj samodzielnie lub użyj wersji chmurowej.

Pobierz n8n za darmo →

Related Miscellaneous Workflows

COGMGOME+2
high

Automate Google Form Tracking & Gmail Alerts via n8n

Boost your administrative efficiency with this comprehensive n8n automation suite designed to bridge the gap between data collection and actionable insights. This workflow transforms standard Google Form submissions into a high-performance management ecosystem. Instead of manually checking spreadsheets, the system triggers instantly upon form submission, updating a centralized Google Sheets dashboard with real-time statistics while simultaneously executing conditional logic via the Code node. The automation intelligently distinguishes between new registrants and follow-ups, triggering personalized Gmail acknowledgments for immediate engagement. Furthermore, it incorporates a sophisticated reminder logic to ensure no student or lead falls through the cracks. By leveraging Webhook and Respond to Webhook nodes, the suite maintains a low-latency connection between your front-end forms and back-end database. This setup eliminates manual data entry errors, reduces response times by up to 90%, and provides stakeholders with a live visual overview of registration trends. It is an essential toolkit for any organization looking to scale their intake process without increasing headcount. **Common Use Cases:** - Educational Workshop & Course Enrollment Management - Automated Event Registration with Instant Attendee Confirmation - Customer Inquiry Routing and Lead Nurturing Pipeline

🔗 Webhook·20 nodes