Actions26
- Collection Actions
- Payload Actions
- Point Actions
- Search Actions
- Vector Actions
Overview
The node provides an interface to retrieve multiple points from a specified collection in Qdrant, a vector search engine. It allows users to fetch detailed information about points by their IDs, optionally including payload data and vector embeddings. This operation is useful when you want to access stored vectors and their metadata for further processing, analysis, or integration with other workflows.
Common scenarios:
- Fetching specific points by their IDs to analyze or visualize their payload.
- Retrieving vectors along with payloads for similarity comparison or downstream machine learning tasks.
- Selectively querying shards to optimize performance in distributed setups.
Practical example:
You have a collection of image feature vectors indexed in Qdrant. You want to retrieve the payload (e.g., image metadata) and optionally the vector embeddings for a subset of images identified by their point IDs to display them in a dashboard or feed into another system.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The target collection from which to retrieve points. Can be selected from a list or entered by name. |
| Point IDs | JSON array specifying the list of point IDs to retrieve. |
| With Payload | Boolean flag indicating whether to include the payload (metadata) of each point in the response. |
| With Vector | Boolean flag indicating whether to include the vector embeddings of each point in the response. |
| Shard Key | JSON value specifying particular shards to query. If omitted, all shards are searched. |
| Consistency | Read consistency level for the operation; options are Majority, Quorum, or All. |
| Timeout | Request timeout in seconds, overriding the global default for this operation. |
Output
The output contains a JSON array of points matching the requested IDs. Each point object may include:
id: The unique identifier of the point.payload: The associated metadata if "With Payload" is true.vector: The vector embedding if "With Vector" is true.
If binary data were involved, it would be summarized here, but this operation deals primarily with JSON data representing points.
Dependencies
- Requires connection to a Qdrant instance via its REST API.
- Needs an API key or authentication token configured in n8n credentials to authorize requests.
- The base URL of the Qdrant service must be set in the node credentials.
Troubleshooting
- Empty results: Ensure that the point IDs provided exist in the specified collection and that the collection name is correct.
- Timeout errors: Increase the timeout property if the request takes longer than expected, especially for large queries or slow networks.
- Consistency issues: If data appears stale or inconsistent, try adjusting the consistency level (e.g., from Majority to All).
- Authentication failures: Verify that the API key or authentication token is valid and has sufficient permissions.
- Shard key misconfiguration: If specifying shard keys, ensure they match the shards configured in your Qdrant deployment.