Vertex AI | Respan Docs

Vertex AI is Google Cloud’s managed platform for foundation models including Gemini, PaLM, and third-party models. Respan gives you full observability over every Vertex AI call, streamed response, and tool invocation — and gateway routing through the Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai opentelemetry-instrumentation-vertexai google-cloud-aiplatform

Set environment variables

$ export GOOGLE_APPLICATION_CREDENTIALS="path/to/your/gcp-key.json"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

GOOGLE_APPLICATION_CREDENTIALS is used for Vertex AI auth. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import vertexai
2 from vertexai.generative_models import GenerativeModel
3 from respan import Respan
4 from opentelemetry.instrumentation.vertexai import VertexAIInstrumentor
5 
6 respan = Respan(instrumentations=[VertexAIInstrumentor()])
7 
8 vertexai.init(project="your-gcp-project", location="us-central1")
9 
10 model = GenerativeModel("gemini-2.0-flash")
11 response = model.generate_content("Say hello in three languages.")
12 print(response.text)
13 respan.flush()

View your trace

Open the Traces page to see your auto-instrumented Vertex AI spans with prompts, tokens, and cost.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `VertexAIInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from opentelemetry.instrumentation.vertexai import VertexAIInstrumentor
3 
4 respan = Respan(
5     instrumentations=[VertexAIInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "vertex-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from respan import Respan, propagate_attributes
2 from opentelemetry.instrumentation.vertexai import VertexAIInstrumentor
3 
4 respan = Respan(instrumentations=[VertexAIInstrumentor()])
5 
6 def handle_request(user_id: str, question: str):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         response = model.generate_content(question)
13         print(response.text)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.