Mistral AI

​

Setup

1. Install Langtrace’s SDK and initialize the SDK in your code.

Note: You’ll need API keys from Langtrace and MistralAI. Sign up for Langtrace and/or MistralAI if you haven’t done so already.

# Install the SDK
pip install -U langtrace-python-sdk mistralai

2. Setup environment variables:

export LANGTRACE_API_KEY=YOUR_LANGTRACE_API_KEY
export MISTRAL_API_KEY=YOUR_MISTRAL_API_KEY

​

Usage

Generate a simple output with your deployment’s model:

import os
from langtrace_python_sdk import langtrace, with_langtrace_root_span
from mistralai import Mistral

langtrace.init(api_key=os.environ["LANGTRACE_API_KEY"])


@with_langtrace_root_span("chat_complete")
def chat_complete():
    model = "mistral-large-latest"
    client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])
    chat_response = client.chat.complete(
        model=model,
        messages=[
            {
                "role": "user",
                "content": "I need 10 cocktail recipes with tequila other than the classics like margarita, tequila"
            },
        ]
    )
    print(chat_response.choices[0].message.content)


chat_complete()

You can now view and analyze your traces on the Langtrace dashboard. Here’s what you can expect:

1. View all your Mistral AI traces in the main traces view:

2. Dive deep into conversation details and responses:

3. Analyze span timing and relationships in the trace visualization:

Want to see more supported methods? Check out the sample code in the Langtrace Mistral Python Example repository.

For advanced usage patterns and detailed examples, explore the Langtrace Mistral Cookbook in the official Mistral AI cookbook repository.