Mistral AI

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses the Mistral AI SDK.

You’ll keep calling Mistral exactly as you do today. Telemetry simply observes and enriches those calls.

Auto-instrumentation for Mistral 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 Mistral SDK (mistralai)
A Mistral API key (set as MISTRAL_API_KEY)

Steps

Install

pip install latitude-telemetry mistralai

uv add latitude-telemetry mistralai

poetry add latitude-telemetry mistralai

Initialize and use

import os

import mistralai
from mistralai import Mistral

from latitude_telemetry import Latitude, capture

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

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

def generate_reply():
    response = client.chat.complete(
        model="mistral-small-latest",
        messages=[{"role": "user", "content": "Hello"}],
    )
    return response.choices[0].message.content

capture("generate-reply", generate_reply)

latitude.shutdown()

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

Open your project in the Latitude dashboard
Each execution shows input/output messages, model, token usage, latency, and errors

Groq Ollama

⌘I

Overview

Getting Started

Observe

Understand

Refine

Security and Compliance

Deployment

Development

More

Overview

Requirements

Steps

Seeing Your Traces

​Overview

​Requirements

​Steps

​Seeing Your Traces

Overview

Requirements

Steps

Seeing Your Traces