Vertex AI Component

Drag & Drop LLM Component
Vertex AI Component

Overview

A drag-and-drop component for integrating Google Cloud's Vertex AI models into your workflow. Configure model parameters and connect inputs/outputs to other components.

Component Configuration

Basic Parameters

  • InputText input for the model
  • System MessageSystem prompt to guide model behavior
  • StreamToggle for streaming responses
  • Model Namee.g., gemini-1.5-pro

Project Settings

  • CredentialsGoogle Cloud credentials file
  • ProjectGoogle Cloud project ID
  • LocationRegion (e.g., us-central1)

Model Parameters

  • Max Output TokensMaximum number of tokens to generate
  • Max RetriesNumber of retry attempts (1 default)
  • TemperatureCreativity control (0 default)
  • Top KTop-k sampling parameter
  • Top PNucleus sampling parameter (0.95 default)
  • VerboseToggle detailed output logging

Output Connections

  • TextGenerated text output
  • Language ModelModel information and metadata

Usage Tips

  • Use service account credentials
  • Set appropriate region for lower latency
  • Enable streaming for real-time responses
  • Adjust temperature based on task needs

Best Practices

  • Secure credentials file handling
  • Monitor API quotas and usage
  • Implement proper error handling
  • Test with small token limits first