Simple Vector Store

Node catalog Artificial intelligence
On this page

In-memory vector store for RAG

Usage and specifics

For insert, supply documentsSource and vectorsSource, with one equal-dimension vector per document. For query, supply queryVectorSource; for delete, supply a nonempty idsSource list. Results are in matches. The simple store stays in execution data and storeSource reuses its output; external storage retains an index across runs.

Technical type : ai_simple_vector_store. 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
operation enum "insert" insert, query, delete
credentialId string - -
serviceInstanceId string - -
connectionSource enum "credential" credential, service
indexName string "" -
namespace string "" -
documentsSource string "" -
vectorsSource string "" -
query string "" -
queryVectorSource string "" -
idsSource string "" -
topK number 4 -; ≥ 1, ≤ 1000
storeSource string "" -

Initial configuration

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

json
{
  "operation": "insert",
  "connectionSource": "credential",
  "indexName": "",
  "namespace": "",
  "documentsSource": "",
  "vectorsSource": "",
  "query": "",
  "queryVectorSource": "",
  "idsSource": "",
  "topK": 4,
  "storeSource": ""
}

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.

See also : Expressions and data, Executions, Node catalog.