Actions26
- Delete Collection
- Get Collection
- Check Collection Exists
- Create Collection
- Update Collection
- Retrieve Point
- Retrieve Points
- Upsert Points
- Delete Points
- Update Vectors
- Delete Vectors
- Set Payload
- Overwrite Payload
- Delete Payload
- Clear Payload
- Batch Update Points
- Scroll Points
- Count Points
- Query Points
- Query Batch Points
- Query Points Groups
- Matrix Pairs
- Matrix Offsets
- Payload Facets
- Create Payload Index
- Delete Payload Index
Overview
The node provides an interface to Qdrant, a vector search engine. Specifically, the "Upsert Points" operation allows users to insert or update multiple points in a specified collection within Qdrant. Each point consists of an identifier, a vector (numerical array), and optional metadata payload.
This operation is useful when you want to add new data points or update existing ones in your vector database for similarity search, recommendation systems, or machine learning applications. For example, you might upsert user embedding vectors with associated profile information to enable personalized content retrieval.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The name of the target collection in Qdrant where points will be upserted. |
| Points | A JSON array of points to upsert. Each point must have: - id: unique identifier - vector: numerical array representing the point - Optional payload: additional metadata as key-value pairs (e.g., color, age) |
| Wait | Boolean flag indicating whether to wait for the operation to complete before proceeding. |
| Ordering | Defines ordering guarantees for the operation. Options are: - Weak - Medium - Strong |
Output
The node outputs JSON data representing the result of the upsert operation. This typically includes confirmation of successful insertion or update of the points. The exact structure depends on the Qdrant API response but generally confirms which points were processed.
No binary data output is involved in this operation.
Dependencies
- Requires connection to a Qdrant instance via an API URL.
- Needs an API authentication token or key configured in n8n credentials to authorize requests.
- The node uses HTTP requests to communicate with the Qdrant REST API.
Troubleshooting
Common issues:
- Invalid collection name or collection does not exist: ensure the collection is created beforehand.
- Malformed points JSON: verify that each point has a valid
idandvectorarray. - Authentication errors: check that the API key/token is correctly set in credentials.
- Network connectivity problems to the Qdrant server.
Error messages:
- "Collection not found": create the collection before upserting points.
- "Invalid vector format": ensure vectors are arrays of numbers matching the collection's dimension.
- "Unauthorized": verify API credentials.
- Timeout or network errors: confirm Qdrant server availability and network settings.