Qdrant icon

Qdrant

Official n8n node to interface with Qdrant - https://qdrant.tech

Overview

The node provides an interface to perform a "Matrix Pairs" search operation on a vector database collection. This operation is used to find pairs of points within a specified collection that satisfy certain conditions and similarity criteria based on vector embeddings.

Typical use cases include:

  • Finding similar items in a dataset, such as recommending related products or documents.
  • Analyzing relationships between data points by comparing their vector representations.
  • Performing advanced similarity searches with filtering and sampling options.

For example, you might use this node to find pairs of images in a collection that are visually similar, or pairs of text documents that share semantic meaning, filtered by metadata conditions.

Properties

Name Meaning
Collection Name The target collection to search within. Can be selected from a list of collections or specified by name.
Filter JSON object defining conditions to filter points before searching for pairs.
Sample Number of points to randomly select and search within (sampling size).
Limit Maximum number of result pairs to return.
Using Name of the vector field to use for querying. If empty, the default vector is used.
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 the global timeout setting.

Output

The output contains a JSON array of point pairs that match the search criteria. Each pair includes information about the two points and their similarity metrics according to the vector embeddings.

If binary data is returned (not explicitly shown here), it would typically represent raw vector data or serialized payloads associated with the points.

Dependencies

  • Requires connection to a Qdrant vector database instance.
  • Needs an API key credential configured in n8n for authentication.
  • The base URL of the Qdrant service must be set in the node credentials.

Troubleshooting

  • Timeout errors: May occur if the query takes longer than the specified timeout. Increase the timeout property or optimize filters/sample size.
  • No results returned: Check that the collection name is correct and that the filter conditions are not too restrictive.
  • Invalid JSON in Filter or Shard Key: Ensure these fields contain valid JSON objects.
  • Authentication failures: Verify that the API key credential is correctly configured and has access to the Qdrant instance.

Links and References

Discussion