Keyword Retriever

Node catalog Artificial intelligence

On this page

Retrieve chunks by keywords

Usage and specifics

Supply chunksSource and query. Retrieval uses keyword matching and topK limits results; no model key is required.

Technical type : ai_keyword_retriever. Runtime : nodulz.

Credentials and prerequisites

This node defines no dedicated external credential. Remote sources or execution targets may still need their own access credentials.

See the credentials guide if a remote source or execution target requires access.

Parameters

Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.

Parameter	Type	Default	Values / limits
`query`	`string`	`""`	-
`topK`	`number`	`4`	-; ≥ 1, ≤ 1000
`searchMode`	`enum`	`"vector"`	`vector`, `hybrid`
`candidateK`	`number`	`20`	-; ≥ 1, ≤ 1000
`rerank`	`boolean`	`false`	-
`chunksSource`	`string`	`""`	-
`vectorsSource`	`string`	`""`	-
`documentsSource`	`string`	`""`	-
`credentialId`	`string`	-	-
`model`	`string`	`""`	-
`workflowId`	`string`	`""`	-

Initial configuration

Initial catalog configuration example, to adapt before running. Keep secrets in credentials.

json

{
  "query": "",
  "topK": 4,
  "searchMode": "vector",
  "candidateK": 20,
  "rerank": false,
  "chunksSource": "",
  "vectorsSource": "",
  "documentsSource": "",
  "model": "",
  "workflowId": ""
}

Verification

Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.