Qdrant Query
CertifiedQuery points in a Qdrant collection
Qdrant Query
Query points in a Qdrant collection
Searches for nearest neighbors in a Qdrant collection using a vector or the vector of an existing point ID. Supports filters and score threshold.
type: io.kestra.plugin.qdrant.QueryExamples
Search for nearest vectors and return inline rows
id: qdrant_query
namespace: company.team
tasks:
- id: search_points
type: io.kestra.plugin.qdrant.Query
host: "{{ secret('QDRANT_HOST') }}"
apiKey: "{{ secret('QDRANT_API_KEY') }}"
tlsEnabled: true
collectionName: docs
vector: [0.05, 0.61, 0.76, 0.74]
topK: 5
withPayload: true
fetchType: FETCH
Search using an existing point ID and store results to Kestra storage
id: qdrant_query_by_id
namespace: company.team
tasks:
- id: search_by_id
type: io.kestra.plugin.qdrant.Query
host: "{{ secret('QDRANT_HOST') }}"
apiKey: "{{ secret('QDRANT_API_KEY') }}"
tlsEnabled: true
collectionName: docs
vectorId: 1
topK: 10
fetchType: STORE
Properties
collectionName *string
Collection name
The name of the collection to search in.
host *string
The host of the Qdrant instance
The hostname or IP address of the Qdrant gRPC endpoint.
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.
limit integerstring
Limit results
Maximum number of nearest points to return (default: 10, min: 1, max: 1000). Takes precedence if 'topK' is also set.
port integerstring
6334The port of the Qdrant instance
The gRPC port of the Qdrant instance (default 6334).
scoreThreshold numberstring
Score threshold
Optional minimal similarity score threshold for returning points.
tlsEnabled booleanstring
falseEnable TLS
Whether to use TLS/SSL for secure gRPC connection.
topK integerstring
Top K results
Maximum number of nearest points to return (default: 10, min: 1, max: 1000). Alias for 'limit'; overridden if 'limit' is also specified.
vector array
Query vector
Dense vector to search for nearest neighbors. Mutually exclusive with 'vectorId'.
vectorId object
Point ID to use as query vector
Existing point ID whose vector should be used for searching. Mutually exclusive with 'vector'.
vectorName string
Vector name
Name of the vector space to target when querying a collection configured with named vectors.
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.
