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 query grouped points from a Qdrant collection. It allows users to perform advanced queries on vector search data, grouping the results by a specified payload field. This is useful for scenarios where you want to aggregate or categorize search results based on certain attributes, such as grouping similar items by category, user ID, or any other metadata field.
Practical examples include:
- Retrieving product recommendations grouped by brand or category.
- Grouping customer feedback points by sentiment or region.
- Aggregating sensor data points by device ID or location.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The name of the Qdrant collection to query. |
| Group By | The payload field (string or number) used to group the returned points. |
| Query | The query to perform; can be a vector, an ID, or a complex query object in JSON format. |
| Using | Specifies which vector name to use for querying. |
| Filter | Conditions to filter points before grouping, provided as a JSON object. |
| Params | Additional search parameters when no prefetch is used, in JSON format. |
| Score Threshold | Minimum score threshold; only points with scores better than this are returned. |
| With Vector | Boolean flag to include vectors in the response. |
| With Payload | Boolean flag to include payload data in the response. |
| Lookup From | JSON defining the location to use for IDs lookup. |
| Group Size | Maximum number of points to return per group. |
| Limit | Maximum number of groups to return. |
| With Lookup | JSON defining if points should be looked up in another collection using group IDs. |
| Prefetch | JSON defining sub-requests to perform first; query runs on these prefetch results. |
| Shard Key | JSON specifying shards to look for points; if omitted, all shards are searched. |
| Consistency | Read consistency level for the operation; options: Majority, Quorum, All. |
| Timeout | Request timeout in seconds; overrides global timeout if set. |
Output
The output contains grouped points from the queried collection. Each group corresponds to a unique value of the "Group By" field and includes up to the specified "Group Size" number of points. Each point may include:
- Its payload data (if
With Payloadis true). - Its vector representation (if
With Vectoris true). - Associated metadata such as scores or IDs.
This structured output enables downstream processing or visualization of grouped search results.
Dependencies
- Requires connection to a Qdrant vector search service.
- Needs an API key credential configured in n8n for authentication.
- The base URL of the Qdrant instance must be set in the credentials.
- No additional external dependencies beyond the Qdrant API.
Troubleshooting
Common issues:
- Incorrect collection name or non-existent collection will cause errors.
- Invalid JSON in query, filter, params, or other JSON fields may lead to parsing errors.
- Setting incompatible types for "Group By" (non-string/number) may cause unexpected behavior.
- Timeout errors if the request takes longer than the specified timeout.
- Insufficient permissions or invalid API key will result in authentication errors.
Error messages and resolutions:
- Collection not found: Verify the collection name exists in your Qdrant instance.
- Invalid query/filter JSON: Ensure JSON syntax is correct and matches expected schema.
- Timeout exceeded: Increase the timeout value or optimize the query.
- Authentication failed: Check that the API key credential is valid and properly configured.