Observability for Ollama with Datadog

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 Datadog. 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

Configure your Datadog agent to receive traces from OpenLLMetry

# In your values.yaml
otlp:
  receiver:
    protocols:
      http:
        enabled: true
        
# In the environment of your application
TRACELOOP_BASE_URL=http://datadog-agent-hostname:4318

Docs

Observability for Ollama with Datadog

Step 1

Step 2

Discover use cases

More things you can connect to {platform}

Mistral AI

Gemini

Chroma

Anthropic

together.ai

LlamaIndex

OpenAI

Watsonx

Cohere

LangChain

Bedrock