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 and database, to retrieve multiple points from a specified collection. This operation is useful when you want to fetch detailed information about specific data points stored in Qdrant by their IDs. It supports options to include additional data such as payloads and vectors, control read consistency, specify shards for the query, and set request timeouts.
Practical examples:
- Retrieving user profile vectors and metadata by their unique IDs for personalized recommendations.
- Fetching product embeddings along with associated attributes for similarity searches or analytics.
- Querying specific sensor data points with payload details for monitoring or alerting systems.
Properties
| Name | Meaning |
|---|---|
| Collection Name | The name of the collection in Qdrant from which to retrieve points. |
| IDs | A JSON array listing the unique point IDs to retrieve from the collection. |
| With Payload | Boolean flag indicating whether to include the payload (metadata) of each point in the output. |
| With Vector | Boolean flag indicating whether to include the vector data of each point in the output. |
| Shard Key | JSON value specifying particular shards to search within; if omitted, all shards are searched. |
| Consistency | Read consistency level for the operation; options are Majority, Quorum, or All. |
| Timeout | Number specifying the timeout for this request in seconds, overriding the global timeout. |
Output
The node outputs JSON data containing the retrieved points. Each point includes its ID and, depending on input properties, may also contain:
- Payload: Additional metadata or attributes associated with the point.
- Vector: The vector representation stored in Qdrant.
If binary data were involved, it would be summarized here, but this node focuses on JSON structured data representing points.
Dependencies
- Requires an API key credential to authenticate with the Qdrant service.
- Needs the base URL of the Qdrant instance configured in credentials.
- No other external dependencies are indicated.
Troubleshooting
Common issues:
- Providing invalid or empty point IDs will result in no data returned or errors.
- Incorrect collection names will cause the node to fail to find the collection.
- Setting inconsistent shard keys that do not exist may lead to empty results.
- Network or authentication failures due to incorrect API credentials or URL.
Error messages:
- Errors related to missing or invalid credentials indicate misconfiguration of the API key or URL.
- Timeout errors suggest increasing the timeout property or checking network connectivity.
- Consistency-related errors may require adjusting the consistency level based on cluster state.