Observability for Anthropic with Datadog

Step 1

Install the Traceloop SDK and initialize it. It will automatically log all calls to Anthropic, with prompts and completions as separate spans.

import boto3
import json

from traceloop.sdk import Traceloop
from traceloop.sdk.decorators import task, workflow

Traceloop.init(app_name="joke_generation_service")
client = Anthropic()

import * as traceloop from "@traceloop/node-server-sdk";
import Anthropic from "@anthropic-ai/sdk";

traceloop.initialize({
  appName: "sample_anthropic",
  apiKey: process.env.TRACELOOP_API_KEY,
  disableBatch: true,
});
const anthropic = new Anthropic({});

async function main() {
  const completion = await anthropic.messages.create({
    max_tokens: 1024,
    model: "claude-3-opus-20240229",
    messages: [
      {
        role: "user",
        content: "How does a court case get to the Supreme Court?",
      },
    ],
  });
  console.log(completion.content);
}

main();

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

Discover use cases

Trace prompts and completions in Anthropic

Call any Claude model by Anthropic and see prompts, completions, and token usage for your call. Both Claude Instant and Claude 2 are supported.

See Code Example

Observability for Anthropic with Datadog

Step 1

Step 2

Discover use cases

Trace prompts and completions in Anthropic

More things you can connect to {platform}

Mistral AI

Gemini

Chroma

together.ai

Ollama

LlamaIndex

OpenAI

Watsonx

Cohere

LangChain

Bedrock