Google Vertex AI
Invoke Gemini foundation models on Google Vertex AI (Google OAuth2).
OCNORA ships 10 typed Google Vertex AI operations. Each node has a schema-driven form, input and output tables beside its settings, and is pre-flighted by Workflow Health before your first real run.
Before you connect Google Vertex AI
- Authentication
- OAuth 2.0
- Credential
- {"client_id", "client_secret", "refresh_token"}
- Connection test
- Available: the stored credential can be checked against the provider when you add it. This is not a record that a test was run or passed.
What you can do with Google Vertex AI
Operations, grouped by what they do to your data.
Create and send 3
Read and search 3
Update 1
Delete and cancel 1
Other operations 2
A sample Google Vertex AI workflow
- 1A core triggerStart the run from a chat, form, manual, schedule, webhook, workflow trigger — no Google Vertex AI trigger is needed.
- 2Count Tokensvertex_ai.count_tokensCount the tokens a Gemini model would consume for a prompt (no generation).
- 3Create Endpointvertex_ai.create_endpointCreates an Endpoint.
An outline built from this provider’s node contracts, not a recorded run. Each step’s output fields are available to the next in the field picker.
Every node below has a reference page: what it does, the connection it needs, its config fields with types, constraints and examples, and the shapes it emits.
Operations 10
- Count TokensCount the tokens a Gemini model would consume for a prompt (no generation).vertex_ai.count_tokens
- Create EndpointCreates an Endpoint.vertex_ai.create_endpoint
- Delete EndpointDeletes an Endpoint.vertex_ai.delete_endpoint
- Embed TextCreate vector embeddings for one or more texts with a Google embedding model.vertex_ai.embed_text
- GenerateInvoke a Gemini foundation model on Google Vertex AI.vertex_ai.generate_content
- Get EndpointGets an Endpoint.vertex_ai.get_endpoint
- List EndpointsLists Endpoints in a Location.vertex_ai.list_endpoints
- PredictSend instances to a deployed Vertex AI endpoint and return its predictions.vertex_ai.predict
- Replace EndpointUpdates an Endpoint with a long running operation.vertex_ai.replace_endpoint
- Update EndpointUpdates an Endpoint.vertex_ai.update_endpoint
Google Vertex AI questions
- How does OCNORA authenticate with Google Vertex AI?
- With a stored OAuth 2.0 credential, shaped {"client_id", "client_secret", "refresh_token"}. A connection test can check it when you add it.
- What can I automate with Google Vertex AI?
- 10 typed operations, each with a reference page listing its config fields and the shapes it emits.
- What if the Google Vertex AI operation I need is not listed?
- Where Google Vertex AI has an HTTP API, call it from the HTTP node with the same credential, or describe the step to the AI builder, which asks our team for a typed node when one is missing.
- Are there templates that use Google Vertex AI?
- Not yet. Start from a blank workflow, or describe the workflow to Build with AI.
- How are Google Vertex AI calls controlled?
- Every call and every run step is audited, runs count against the execution budget, and Workflow Health pre-flights the workflow when you save it.
See your first Google Vertex AI workflow run.
Book a technical demo. We add the connection, pick a template or describe the workflow to Build with AI, and Workflow Health checks it before it runs.