Phoenix
TypeScript APIPython APICommunityGitHubPhoenix Cloud
  • Documentation
  • Self-Hosting
  • Cookbooks
  • Learn
  • Integrations
  • SDK and API Reference
  • Release Notes
  • Overview
  • LLM Providers
    • Amazon Bedrock
      • Amazon Bedrock Tracing
      • Amazon Bedrock Evals
      • Amazon Bedrock Agents Tracing
    • Anthropic
      • Anthropic Tracing
      • Anthropic Evals
    • Google Gen AI
      • Google GenAI Tracing
      • Gemini Evals
    • LiteLLM
      • LiteLLM Tracing
      • LiteLLM Evals
    • MistralAI
      • MistralAI Tracing
      • MistralAI Evals
    • Groq
      • Groq Tracing
    • OpenAI
      • OpenAI Tracing
      • OpenAI Evals
      • OpenAI Agents SDK Tracing
      • OpenAI Node.js SDK
    • VertexAI
      • VertexAI Tracing
      • VertexAI Evals
  • Frameworks
    • Agno
      • Agno Tracing
    • AutoGen
      • AutoGen Tracing
    • BeeAI
      • BeeAI Tracing (JS)
    • CrewAI
      • CrewAI Tracing
    • DSPy
      • DSPy Tracing
    • Flowise
      • Flowise Tracing
    • Guardrails AI
      • Guardrails AI Tracing
    • Haystack
      • Haystack Tracing
    • Hugging Face smolagents
      • smolagents Tracing
    • Instructor
      • Instructor Tracing
    • LlamaIndex
      • LlamaIndex Tracing
      • LlamaIndex Workflows Tracing
    • LangChain
      • LangChain Tracing
      • LangChain.js
    • LangGraph
      • LangGraph Tracing
  • LangFlow
    • LangFlow Tracing
  • Model Context Protocol
    • Phoenix MCP Server
    • MCP Tracing
  • Prompt Flow
    • Prompt Flow Tracing
  • Vercel
    • Vercel AI SDK Tracing (JS)
  • Evaluation Libraries
    • Cleanlab
    • Ragas
  • Vector Databases
    • MongoDB
    • Pinecone
    • Qdrant
    • Weaviate
    • Zilliz / Milvus
Powered by GitBook

Platform

  • Tracing
  • Prompts
  • Datasets and Experiments
  • Evals

Software

  • Python Client
  • TypeScript Client
  • Phoenix Evals
  • Phoenix Otel

Resources

  • Container Images
  • X
  • Blue Sky
  • Blog

Integrations

  • OpenTelemetry
  • AI Providers

© 2025 Arize AI

On this page

Was this helpful?

  1. LLM Providers
  2. VertexAI

VertexAI Evals

Configure and run VertexAI for evals

VertexAI

Need to install the extra dependencygoogle-cloud-aiplatform>=1.33.0

class VertexAIModel:
    project: Optional[str] = None
    location: Optional[str] = None
    credentials: Optional["Credentials"] = None
    model: str = "text-bison"
    tuned_model: Optional[str] = None
    temperature: float = 0.0
    max_tokens: int = 256
    top_p: float = 0.95
    top_k: int = 40

To authenticate with VertexAI, you must pass either your credentials or a project, location pair. In the following example, we quickly instantiate the VertexAI model as follows:

project = "my-project-id"
location = "us-central1" # as an example
model = VertexAIModel(project=project, location=location)
model("Hello there, this is a tesst if you are working?")
# Output: "Hello world, I am working!"
PreviousVertexAI TracingNextAgno

Last updated 14 days ago

Was this helpful?