Connectors

AI, LLM & Vector Stores

Google Vertex AI

Managed ML platform: model predictions, tuning jobs, and endpoint management
Google Vertex AI API reference
Signs in with
API token
Runs on
Cloud or On-Prem Worker
Operations
4
Ready-made triggers
0

Connect Google Vertex AI

  1. In Neblex open Connect › Connections and click New Connection.
  2. Search for Google Vertex AI and give the connection a clear name.
  3. Fill in the fields. Secret values are encrypted and never shown again.
  4. Click Test, then Create Connection.
FieldWhat to enter
Access tokenRequiredSecret

Use it in a flow

  1. Open a flow, open the node library and search for Google Vertex AI.
  2. Drag it onto the canvas and choose an Operation and your connection.
  3. Map the operation's fields from earlier steps, or click Map with Matt.
  4. Use Test this step to see what it returns, then save.

To start a flow from Google Vertex AI without a ready-made trigger: a Poll for changes trigger can check one of its list operations on a schedule and pass on only what is new; if Google Vertex AI can send webhooks, a Webhook trigger receives them at its own URL.

Operations

4 operations in 3 groups. Each one is a step you can add to a flow.

Content2
Count tokenscountTokensPOSTCount tokens a request would use.
Generate contentgenerateContentPOSTGenerate from a Gemini model on Vertex (contents JSON array).
Embeddings1
Create embeddingsembeddingsPOSTCreate text embeddings (instances JSON array).
Prediction1
PredictpredictPOSTRun online prediction on a model (instances JSON array).