Observability for Ollama with Highlight

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 Honeycomb. 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

Route traces to Highlights’s OTLP endpoint and set the Highlight project ID in the headers.

TRACELOOP_BASE_URL=https://otel.highlight.io:4318
TRACELOOP_HEADERS="x-highlight-project=<YOUR_HIGHLIGHT_PROJECT_ID>"

Docs

Observability for Ollama with Highlight

Step 1

Step 2

Discover use cases

More things you can connect to {platform}

Chroma

OpenAI

Cohere

Gemini

Watsonx

Bedrock

Anthropic

LangChain

LlamaIndex

Mistral AI

together.ai