Observability for together.ai with Datadog

OpenLLMetry lets you trace any model running on together.ai platform. 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 models served from together.ai, with prompts and completions as separate spans.

from together import Together
from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import workflow

Traceloop.init(app_name="joke_generation_service")

client = Together(api_key=os.environ.get("TOGETHER_API_KEY"))

@workflow(name="joke_creation")
def create_joke():
    response = client.chat.completions.create(
        model="mistralai/Mixtral-8x7B-Instruct-v0.1",
        messages=[{"role": "user", "content": "Tell me a joke about OpenTelemetry."}],
    )

    return response.choices[0].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 together.ai with Datadog

Step 1

Step 2

Discover use cases

More things you can connect to {platform}

Mistral AI

Gemini

Chroma

Anthropic

Ollama

LlamaIndex

OpenAI

Watsonx

Cohere

LangChain

Bedrock