Qdrant integration

Vector database

18 operationsVector Databases

Qdrant is an open-source vector database built for fast similarity search over embeddings. The NoClick Qdrant node covers the full lifecycle of a collection: create and update collections, upsert points, run vector queries and recommendations, retrieve or scroll through results, and manage the payload metadata and indexes attached to each point. It can also take a document, embed it, and index it in a single step with Upload and Index Document. Drop it into a workflow to keep a semantic search index in sync without writing client code.

What you can automate with Qdrant

Qdrant operations

Points8

Collection5

Payload3

Index2

Questions

Yes. The node upserts points, uploads and indexes documents, and updates collection settings, so any trigger can push fresh embeddings into Qdrant. You can also delete points or clear payloads to keep a collection current as records change.

It authenticates with an API key and your cluster URL, whether that is Qdrant Cloud or a self-hosted server. Once the credential is saved, every operation in the workflow reuses the same connection, so you set it up once.

Yes. Use Query / Search to find the nearest vectors to a given embedding, or Recommend Points to surface items similar to a set of examples. Retrieve Points and Scroll Points let you pull specific records by ID or page through the whole collection.

It can. Set Payload writes metadata onto points, while Clear Payload and Delete Payload Keys remove it, and Create Payload Index and Delete Payload Index control which fields are indexed for filtering. That lets one workflow keep both the vectors and their attached metadata in order.

The Qdrant node is request and response, so it does not fire on its own. You trigger it from another node, a schedule, a form, or an inbound webhook, then use List Collections, Count Points, or Get Collection Info to check the state of a collection as part of that run.

Give Qdrant to an agent

All integrations

Free to start.