RAG: Index (vector)

rag_ingest · action · Utility · Available · v1.0.0

Description

Index content into the TENANT vector knowledge base: embeds the text (BYOK provider) and upserts into the vector DB, creating the collection on first use. Idempotent — without an explicit id a deterministic one is derived from content, so re-runs never duplicate.

⚙️ Configuration parameters

Fields shown in the editor when configuring the node. Generated directly from the NodeDefconfigFields.

FieldTypeRequiredDefaultDescription
databaseId
Vector DB
db-pickeryesUn database con engine vettoriale (embedded o pgvector).
collection
Collezione
stringyesNome della collezione (creata se non esiste).
content
Contenuto da indicizzare
stringnoTesto da embeddizzare. Vuoto = usa l'input del nodo precedente (stringa o {content}/{text}).
id
ID record
stringnoVuoto = id deterministico dal contenuto (idempotenza). Fornisci un id stabile (es. {{input.docId}}) per aggiornare lo stesso record.
provider
Provider embedding
enum
openaivoyageollama
noopenai
model
Modello embedding
stringnotext-embedding-3-smallLe dimensioni della collezione derivano da questo modello — non cambiarlo dopo il primo ingest.
apiKey
API key (BYOK)
stringno
distance
Distanza
enum
cosineeuclideandot
nocosine
payloadJson
Metadati (payload)
key-valuenoCoppie chiave-valore salvate col chunk (es. source, lang). Il contenuto viene sempre incluso automaticamente.

💡 Configuration example

JSON snippet of the node as it appears in the workflow. Values are derived fromdefaultValue and from required parameters.

{
  "id": "node-rag_ingest-1",
  "defId": "rag_ingest",
  "label": "RAG: Index (vector)",
  "config": {
    "databaseId": "<databaseId>",
    "collection": "<collection>",
    "provider": "openai",
    "model": "text-embedding-3-small",
    "distance": "cosine"
  }
}

🔗 Related nodes in the same category

Ready to use RAG: Index (vector)?

Available now on all FlowForge plans. Try it free without a credit card.

Start freeBrowse all nodes