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 interfaces with Qdrant, a vector search engine, to perform various operations on collections of points. Specifically, the "Payload Facets" operation allows users to retrieve facet counts for a specified payload key within a collection. This is useful for summarizing or aggregating metadata values stored in the payloads of points, such as counting how many points have certain tags or categories.
Common scenarios include:
- Analyzing distribution of categorical metadata in a dataset.
- Quickly obtaining counts of different attribute values without retrieving all points.
- Filtering and faceting data based on complex conditions.
For example, you might use this node to get counts of documents by author or category in a large vector database, helping to understand the composition of your data.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The name of the collection in Qdrant where the points are stored. |
| Key | The payload key (attribute) to facet on, e.g., "category" or "tag". |
| Filter | JSON object specifying conditions to filter points before faceting. Only points matching these are counted. |
| Limit | Maximum number of facet values (hits) to return. |
| Exact | Boolean flag indicating whether to perform an exact count for each facet value (more computationally expensive). |
| Shard Key | JSON specifying which shards to query; if omitted, all shards are searched. |
| Consistency | Read consistency level for the operation: Majority, Quorum, or All. |
| Timeout | Request timeout in seconds, overriding global timeout settings. |
Output
The output json field contains the facet results for the specified payload key. It typically includes a list of facet values along with their respective counts, representing how many points have each value under the given key.
If binary data were involved, it would represent raw data blobs, but this operation focuses on JSON facet summaries.
Dependencies
- Requires connection to a Qdrant instance via an API URL and an API key credential.
- The node expects proper configuration of the Qdrant API credentials in n8n.
- Network access to the Qdrant service endpoint is necessary.
Troubleshooting
- Invalid Collection Name: If the collection does not exist, the node will fail. Verify the collection name is correct.
- Malformed Filter or Shard Key JSON: Ensure that the JSON provided in the Filter and Shard Key fields is valid and correctly formatted.
- Timeouts: If the request times out, consider increasing the Timeout property or checking network connectivity.
- Exact Count Performance: Setting Exact to true may cause slower responses due to more expensive computations.
- Consistency Errors: Using inappropriate consistency levels may lead to errors if the Qdrant cluster cannot satisfy the requested guarantees.