Actions26
- Collection Actions
- Payload Actions
- Point Actions
- Search Actions
- Vector Actions
Overview
The node provides an interface to interact with the "Payload Facets" operation of a Qdrant collection. This operation allows users to retrieve facet counts for a specified payload key within a collection, optionally filtered by conditions and limited in result size. Faceting is useful for summarizing or aggregating data values, such as counting how many points have certain attribute values.
Common scenarios include:
- Analyzing distribution of categorical metadata stored in payloads.
- Quickly getting counts of distinct values for a given key.
- Filtering points based on criteria and then understanding the value spread of a specific field.
For example, if you have a collection of documents with a payload key "category", you can use this node to get counts of how many documents belong to each category, optionally filtering only documents created after a certain date.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The target collection to query facets from. Can be selected from a list of collections or specified by name. |
| Key | The payload key whose values will be faceted (counted). |
| Filter | JSON object defining conditions to filter points before faceting. Only points satisfying these are considered. |
| Limit | Maximum number of facet results to return. |
| Exact | Boolean flag indicating whether to perform an exact count for each facet value (more expensive). |
| Shard Key | JSON specifying which shards to search in; if omitted, all shards are searched. |
| Consistency | Read consistency level for the operation. Options: Majority, Quorum, All. |
| Timeout | Request timeout in seconds, overriding global timeout if set. |
Output
The node outputs JSON data representing the facet counts for the specified payload key. The structure typically includes keys corresponding to distinct values found under the payload key, along with their respective counts. If the "Exact" option is enabled, counts reflect precise numbers rather than estimates.
If binary data output is supported by other operations, it is not relevant here since this operation deals with JSON facet summaries.
Dependencies
- Requires connection to a Qdrant vector database instance.
- Needs an API authentication token configured in n8n credentials to authorize requests.
- The base URL of the Qdrant REST API must be provided in the credentials.
- No additional external services are required.
Troubleshooting
Common issues:
- Incorrect collection name or non-existent collection will cause errors.
- Malformed JSON in the Filter property may lead to request failures.
- Setting an excessively high Limit may impact performance or cause timeouts.
- Using "Exact" counts on very large datasets can be slow or resource-intensive.
Error messages:
- "Collection not found": Verify the collection name is correct and exists.
- "Invalid filter format": Ensure the filter JSON is valid and matches expected schema.
- "Timeout exceeded": Increase the Timeout property or optimize the filter/limit.
- Authentication errors: Check that the API key credential is correctly configured.