Observability for Ollama with Traceloop

OpenLLMetry lets you trace any model running locally or remotely on Ollama. 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 Ollama, whether you're running a model locally or remotely, with prompts and completions as separate spans.

import ollama
from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import workflow

Traceloop.init(app_name="joke_generation_service")

@workflow(name="joke_creation")
def create_joke():
		response = ollama.chat(
        model="llama3",
        messages=[
            {
                "role": "user",
                "content": "Tell me a joke about OpenTelemetry",
            },
        ],
    )

    return response["message"]["content"]

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 Ollama with Traceloop

Step 1

Step 2

Discover use cases

More things you can connect to {platform}

Gemini

Cohere

LangChain

Chroma

Mistral AI

together.ai

Anthropic

Bedrock

OpenAI

Watsonx

LlamaIndex