
Qdrant SparseQuery
CertifiedQuery a Qdrant collection with a sparse vector
Qdrant SparseQuery
Query a Qdrant collection with a sparse vector
Runs one sparse-only query against a named sparse vector space and returns the nearest points with their sparse similarity score.
This is the sparse counterpart of Query and the third leg of a retrieval comparison next to Query (dense) and HybridQuery (fused): running the same labelled queries through all three shows whether fusion improves your workload. The collection must already expose the sparse vector space, which CreateCollection can create and Upsert can fill.
type: io.kestra.plugin.qdrant.SparseQueryExamples
Search a sparse vector space for exact identifiers or lexical matches
id: qdrant_sparse_query
namespace: company.team
tasks:
- id: sparse_search
type: io.kestra.plugin.qdrant.SparseQuery
host: "{{ secret('QDRANT_HOST') }}"
apiKey: "{{ secret('QDRANT_API_KEY') }}"
tlsEnabled: true
collectionName: docs
vectorName: text_sparse
indices: [12, 104, 982]
values: [0.84, 1.23, 0.41]
limit: 10
filter:
tenant_id: acme
fetchType: FETCH
Installation
Our standard Docker images already include this plugin. If you use a -slim image or another setup, install it with the following command:
kestractl plugins get io.kestra.plugin:plugin-qdrant --compatible-for $KESTRA_VERSION For kestractl, use your Kestra version with --compatible-for, or specify an exact plugin version.
Properties
collectionName *string
Collection name
The name of the collection to search in. It must expose the sparse vector space named below.
host *string
The host of the Qdrant instance
The hostname or IP address of the Qdrant gRPC endpoint.
indices *array
Sparse query indices
Indices of the non-zero dimensions of the sparse query vector, as a list of distinct non-negative whole numbers. Must have the same number of elements as 'values'.
values *array
Sparse query values
Weights of the non-zero dimensions of the sparse query vector, as a list of finite numbers positionally paired with 'indices'.
vectorName *string
Sparse vector space name
Name of the sparse vector space to search, as configured on the collection.
apiKey string
API key
The API key for authentication with Qdrant.
assets
Assets this task consumes as inputs or produces as outputs, for lineage tracking and the asset graph (Enterprise Edition). A flow declaring this property on a task is rejected in the open-source edition.
io.kestra.core.models.assets.AssetsDeclaration
IGNOREFAILWARNAsset failure behavior
Behavior applied to the task state when a declared asset fails to render, emit, or be persisted (e.g. a lock conflict): FAIL escalates it to FAILED, WARN (default) warns it if it would otherwise succeed, IGNORE leaves the state untouched.
Whether to auto-register assets referenced dynamically at runtime that are not statically declared in inputs or outputs.
The assets consumed as inputs.
io.kestra.core.models.assets.AssetIdentifier
1The assets produced as outputs.
io.kestra.plugin.ee.assets.Dataset
1150{}1150io.kestra.plugin.ee.assets.File
1150{}1150io.kestra.plugin.ee.assets.Table
1150{}1150io.kestra.plugin.ee.assets.VM
1150{}1150io.kestra.core.models.assets.External
1150{}1150io.kestra.core.models.assets.Custom
11501Custom asset type
{}1150fetchType string
STORESTOREFETCHFETCH_ONENONESelect fetch behavior
Output mode for query results: FETCH returns all rows inline, FETCH_ONE returns the first row, and STORE writes all rows to Kestra storage as an ION file and returns the URI (default: STORE).
filter object
Filter criteria
Filter map to restrict the search space before ranking. Accepts the same filter shapes as the 'Query' task.
limit integerstring
10Limit results
Maximum number of points to return (default: 10, min: 1, max: 1000).
port integerstring
6334The port of the Qdrant instance
The gRPC port of the Qdrant instance (default 6334).
queryTimeout string
PT30SQuery timeout
Server-side and client-side bound for the query, truncated to whole seconds (default: PT30S, min: 1 second). The same value is sent as the Qdrant request timeout and used as the gRPC call deadline.
scoreThreshold numberstring
Score threshold
Optional minimal sparse similarity score for returning points.
tlsEnabled booleanstring
falseEnable TLS
Whether to use TLS/SSL for secure gRPC connection.
withPayload booleanstring
trueInclude payload
Whether to include point payload metadata in the result (default: true).
withVectors booleanstring
falseInclude vectors
Whether to include vector embeddings in the result (default: false).
Outputs
row object
Map containing the first row of fetched data.
Only populated if using fetchType=FETCH_ONE.
rows array
List containing the fetched data.
Only populated if using fetchType=FETCH.
size integer
The number of fetched rows.
uri string
uriKestra's internal storage URI of the stored data.
Only populated if using fetchType=STORE.