Qdrant
Vector search — collections and points via the Qdrant REST API.
OCNORA ships 5 typed Qdrant operations. Each node has a schema-driven form, input and output tables beside its settings, and is pre-flighted by Workflow Health before your first real run.
Before you connect Qdrant
- Authentication
- API key
- Credential
- the api-key (optional for open instances), or {"api_key": "…"}
- Connection test
- Available: the stored credential can be checked against the provider when you add it. This is not a record that a test was run or passed.
What you can do with Qdrant
Operations, grouped by what they do to your data.
Create and send 2
Read and search 2
Delete and cancel 1
Nodes that use your Qdrant connection
Beyond its own nodes, these generic nodes accept your Qdrant credential. Each chooses the provider from the connection you select, so the same node also works with the other providers shown.
- Vector: Create Collectionvector.create_collectionCreate a collection (index / class / table) sized for one embedding model.
- Vector: Deletevector.deleteDelete records from a vector store by id, by metadata filter, or all of them.
- Vector: Describe Collectionvector.describe_collectionRead one collection's width, metric and record count.
- Vector: List Collectionsvector.list_collectionsList the collections a vector store holds.
- Vector: Queryvector.queryFind the records nearest to a query text or vector, with metadata filtering.
- Vector: Upsertvector.upsertWrite documents and their vectors into a vector store, with metadata.
A sample Qdrant workflow
- 1A core triggerStart the run from a chat, form, manual, schedule, webhook, workflow trigger — no Qdrant trigger is needed.
- 2List Collectionsqdrant.list_collectionsList the collections.
- 3Create Collectionqdrant.create_collectionCreate a collection with a vector size and distance.
An outline built from this provider’s node contracts, not a recorded run. Each step’s output fields are available to the next in the field picker.
Every node below has a reference page: what it does, the connection it needs, its config fields with types, constraints and examples, and the shapes it emits.
Operations 5
- Create CollectionCreate a collection with a vector size and distance.qdrant.create_collection
- Delete PointsDelete points by id.qdrant.delete_points
- List CollectionsList the collections.qdrant.list_collections
- SearchNearest-neighbour search with an optional filter.qdrant.search_points
- Upsert PointsInsert or update points (id, vector, payload).qdrant.upsert_points
Qdrant questions
- How does OCNORA authenticate with Qdrant?
- With a stored API key credential, shaped the api-key (optional for open instances), or {"api_key": "…"}. A connection test can check it when you add it.
- What can I automate with Qdrant?
- 5 typed operations, each with a reference page listing its config fields and the shapes it emits. The credential also drives 6 generic nodes.
- What if the Qdrant operation I need is not listed?
- Where Qdrant has an HTTP API, call it from the HTTP node with the same credential, or describe the step to the AI builder, which asks our team for a typed node when one is missing.
- Are there templates that use Qdrant?
- Not yet. Start from a blank workflow, or describe the workflow to Build with AI.
- How are Qdrant calls controlled?
- Every call and every run step is audited, runs count against the execution budget, and Workflow Health pre-flights the workflow when you save it.
More in Databases & warehouses
See your first Qdrant workflow run.
Book a technical demo. We add the connection, pick a template or describe the workflow to Build with AI, and Workflow Health checks it before it runs.