Google Vertex AI

SideSeat automatically extracts model information, token usage, and costs from Google Vertex AI API calls.

Prerequisites

• SideSeat running locally (sideseat)
• SDK installed (pip install sideseat / uv add sideseat or npm install @sideseat/sdk)
• Google Cloud credentials configured

Usage with Vertex AI SDK

from sideseat import SideSeat
SideSeat()

import vertexai
from vertexai.generative_models import GenerativeModel

vertexai.init(project="your-project", location="us-central1")

model = GenerativeModel("gemini-2.5-flash")
response = model.generate_content("Hello!")
print(response.text)

Usage with Google GenAI SDK

from sideseat import SideSeat
SideSeat()

import google.generativeai as genai

genai.configure(api_key="your-api-key")

model = genai.GenerativeModel("gemini-2.5-flash")
response = model.generate_content("Hello!")
print(response.text)

Extracted Attributes

Attribute	Source
gen_ai.system	vertex_ai or google_ai
gen_ai.request.model	Model name
gen_ai.response.model	Response model field
gen_ai.usage.input_tokens	Usage metadata
gen_ai.usage.output_tokens	Usage metadata
cloud.provider	gcp
cloud.region	Vertex AI location

Streaming

Streaming responses are captured:

model = GenerativeModel("gemini-2.5-flash")

for chunk in model.generate_content("Tell me a story", stream=True):
    print(chunk.text, end="")

Chat Sessions

Multi-turn conversations are traced:

model = GenerativeModel("gemini-2.5-flash")
chat = model.start_chat()

response1 = chat.send_message("Hello!")
response2 = chat.send_message("Tell me more")

Function Calling

Tool use is captured:

from vertexai.generative_models import FunctionDeclaration, Tool

get_weather = FunctionDeclaration(
    name="get_weather",
    description="Get weather for a location",
    parameters={
        "type": "object",
        "properties": {
            "location": {"type": "string"}
        }
    }
)

tool = Tool(function_declarations=[get_weather])
model = GenerativeModel("gemini-2.5-flash", tools=[tool])

response = model.generate_content("What's the weather in Paris?")

Authentication

Vertex AI uses Google Cloud credentials:

# Application Default Credentials
gcloud auth application-default login

# Or service account
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json

Next Steps

• First Run — get started with SideSeat
• Python SDK — SDK reference