Count tokens
ReadCount the tokens a conversation would use with a model.
Permissions and limits
Account permissions
- Vertex AI User (roles/aiplatform.user) for the service account, with the Vertex AI API enabled
AI services · CONNECTIONGoogle Vertex AI + NodeHub
Generate content, count tokens and create embeddings with Gemini models on Vertex AI through a Google Cloud service account.
Explore 3 workflow actions for Google Vertex AI, including account permissions and operation limits.
3 read actions0 write actions
WORKFLOW ACTIONS
What you can configure.
Choose an action in the workflow builder, connect an account, and map its inputs. These actions are available in the catalog; your account access and a successful test determine whether they work for your setup.
Embed content
ReadTurn text into an embedding vector with a Vertex AI model that supports embedContent.
Permissions and limits
Account permissions
- Vertex AI User (roles/aiplatform.user) for the service account, with the Vertex AI API enabled
Generate content
ReadAsk a Gemini model on Vertex AI for a response to the conversation.
Permissions and limits
Account permissions
- Vertex AI User (roles/aiplatform.user) for the service account, with the Vertex AI API enabled
Operation limits
- Each call is billed to the Google Cloud project.
- Tools, function calling and streaming are not offered.
SETUP
Start with a controlled test.
01Connect the intended account
Use the account and permissions required for your process. Review the connection check before configuring a workflow action.
02Review inputs and access
Select a listed operation and map its required inputs. Use test records and add a human approval before writes that need review.
03Confirm the result
Inspect step outputs and confirm the result in Google Vertex AI. A saved workflow is not a completed provider action.
EXPLORE YOUR STACK
