Chroma Query
CertifiedQuery a Chroma collection
Chroma Query
Query a Chroma collection
Runs a nearest-neighbour search with a query vector, optionally filtered by metadata (where) and document text (whereDocument). Returns the matches as rows: inline, first-only, or written to Kestra storage.
type: io.kestra.plugin.chroma.QueryExamples
Search for the 5 nearest records and return them inline
id: chroma_query
namespace: company.team
tasks:
- id: search
type: io.kestra.plugin.chroma.Query
baseUrl: http://localhost:8000
collectionName: docs
vector: [0.05, 0.61, 0.76, 0.74]
maxResults: 5
where:
source: handbook
fetchType: FETCH
Properties
baseUrl *string
Base URL of the Chroma server
The base URL of the Chroma HTTP server, for example http://localhost: 8000.
collectionName *string
Collection name
The name of the collection to search.
vector *array
Query vector
The embedding to search with, as a list of numbers.
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
{}1150authToken string
Authentication token
Token sent in the X-Chroma-Token header. Used by token-authenticated self-hosted servers and by Chroma Cloud. Mutually exclusive with username/password.
database string
Database
The Chroma database that holds the collection (default: default_database).
fetchType string
STORESTOREFETCHFETCH_ONENONESelect fetch behavior
FETCH returns all rows inline, FETCH_ONE returns the first row, and STORE writes the rows to Kestra storage as an ION file and returns the URI (default: STORE).
include array
Fields to include
Which fields to return for each match (default: metadatas, documents, distances). Valid values: distances, documents, metadatas, embeddings, uris.
maxResults integerstring
10Maximum number of results
Maximum number of nearest records to return (default: 10, min: 1, max: 10000).
password string
Basic-auth password
Password for HTTP basic authentication. Requires username.
tenant string
Tenant
The Chroma tenant that holds the database (default: default_tenant).
username string
Basic-auth username
Username for HTTP basic authentication. Requires password.
where object
Metadata filter
A Chroma where filter on record metadata, e.g. {source: handbook} or {year: {$gte: 2020}}.
whereDocument object
Document filter
A Chroma where_document full-text filter, e.g. {$contains: "capital"}.
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.
