Observability for Gemini with Traceloop

OpenLLMetry lets you trace models running on VertexAI. With 5 minutes of work you can get complete view of your system directly into Traceloop. See how below.

Step 1

Install the Traceloop SDK and initialize it. It will automatically log all calls to Gemini or any other VertexAI models, with prompts and completions as separate spans.

import google.generativeai as genai
from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import workflow

Traceloop.init(app_name="joke_generation_service")

genai.configure(api_key=os.environ.get("GENAI_API_KEY"))

@workflow(name="joke_creation")
def create_joke():
    model = genai.GenerativeModel("gemini-1.0-pro-latest")
    response = model.generate_content(
        "Give me ten interview questions for the role of program manager.",
    )

    return response.text

Step 2

On Traceloop, API keys can be generated from the Traceloop Dashboard, for each of the three supported environments (Development, Staging, Production).

TRACELOOP_API_KEY=<Your API Key>

Docs

Observability for Gemini with Traceloop

Step 1

Step 2

Discover use cases

More things you can connect to {platform}

Cohere

Ollama

LangChain

Chroma

Mistral AI

together.ai

Anthropic

Bedrock

OpenAI

Watsonx

LlamaIndex