Skip to main content

​
Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses Ollama for local model inference.
You’ll keep calling Ollama exactly as you do today. Telemetry simply observes and enriches those calls.
Auto-instrumentation for Ollama is available in the Python SDK. For other languages, send traces via the OpenTelemetry exporter.

​
Requirements

  • A Latitude account and API key
  • A Latitude project slug
  • A project that uses the Ollama SDK (ollama)
  • A running Ollama server (set OLLAMA_HOST if it is not the default http://localhost:11434)

​
Steps

1

Install

pip install latitude-telemetry ollama
2

Initialize and use

import ollama

from latitude_telemetry import Latitude, capture

latitude = Latitude(
    api_key="your-api-key",
    project="your-project-slug",
    instrumentations={"ollama": ollama},
)

def generate_reply():
    response = ollama.chat(
        model="llama3.2",
        messages=[{"role": "user", "content": "Hello"}],
    )
    return response["message"]["content"]

capture("generate-reply", generate_reply)

latitude.shutdown()

​
Seeing Your Traces

Once connected, traces appear automatically in Latitude:
  1. Open your project in the Latitude dashboard
  2. Each execution shows input/output messages, model, token usage, latency, and errors