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
This node integrates with Qdrant, a vector search engine, to perform various operations on collections of points. Specifically, the "Count Points" operation counts the number of points in a specified collection that match given criteria. This is useful for quickly determining the size of subsets within large vector datasets, such as counting how many vectors meet certain filter conditions or reside in specific shards.
Practical examples include:
- Counting how many vectors in an image feature collection correspond to a particular category.
- Estimating the number of points matching a complex filter without retrieving all data.
- Monitoring collection sizes or subsets dynamically during data processing workflows.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The name of the collection in Qdrant where points are stored and counted. |
| Filter | JSON object specifying conditions to select only points that satisfy these criteria (e.g., payload filters). |
| Exact | Boolean flag indicating whether to count the exact number of points (true) or an approximate count (false). Approximate counts are faster but may be unreliable during indexing. |
| Shard Key | JSON array or value specifying which shards to search within. If not set, all shards are searched. |
| Timeout | Number specifying the timeout for this request in seconds, overriding any global timeout settings. |
Output
The output contains a JSON field with the count result of points matching the query. It typically includes a numeric value representing the total number of points found according to the filter and shard constraints.
If binary data were involved, it would represent raw data associated with points, but this operation focuses solely on counting and thus outputs only JSON numeric results.
Dependencies
- Requires connection to a Qdrant instance, configured via an API key credential and base URL.
- The node expects proper authentication credentials to access the Qdrant API.
- Network connectivity to the Qdrant service endpoint must be available.
Troubleshooting
- Timeouts: If the count operation takes too long, consider increasing the timeout property or using approximate counting by setting
Exactto false. - Incorrect Counts: Using approximate counting during active indexing might yield unreliable results; switch to exact counting if accuracy is critical.
- Filter Syntax Errors: Ensure the JSON filter is correctly formatted and valid according to Qdrant's filtering schema.
- Shard Key Issues: Specifying invalid shard keys may result in zero counts or errors; verify shard keys exist in the collection.
- Authentication Failures: Check that the API key credential is correctly configured and has sufficient permissions.