Notebooks
M
Mistral AI Cookbook Maxim Mistral Integration

Cookbook Maxim Mistral Integration

mistral-cookbookthird_partyMaxim
alph-notebooks/mistral-cookbook / cookbook_maxim_mistral_integration.ipynb

Open In Colab

Observability with Mistral AI and Maxim

In this cookbook, we show you how to use Maxim, to observe Mistral LLM calls & metrics.

What is Maxim?

Maxim AI provides comprehensive observability for your Mistral based AI applications. With Maxim's one-line integration, you can easily trace and analyse LLM calls, metrics, and more.

Pros:

  • Performance Analytics: Track latency, tokens consumed, and costs
  • Advanced Visualisation: Understand agent trajectories through intuitive dashboards

Install and Import Required Modules

You need to install mistralai and maxim-py packages from pypy

[ ]
Collecting mistralai
  Downloading mistralai-1.8.1-py3-none-any.whl.metadata (33 kB)
Collecting maxim-py
  Downloading maxim_py-3.8.1-py3-none-any.whl.metadata (13 kB)
Collecting eval-type-backport>=0.2.0 (from mistralai)
  Downloading eval_type_backport-0.2.2-py3-none-any.whl.metadata (2.2 kB)
Requirement already satisfied: httpx>=0.28.1 in /usr/local/lib/python3.11/dist-packages (from mistralai) (0.28.1)
Requirement already satisfied: pydantic>=2.10.3 in /usr/local/lib/python3.11/dist-packages (from mistralai) (2.11.5)
Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from mistralai) (2.9.0.post0)
Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from mistralai) (0.4.1)
Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from maxim-py) (2.32.3)
Requirement already satisfied: urllib3 in /usr/local/lib/python3.11/dist-packages (from maxim-py) (2.4.0)
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.11/dist-packages (from maxim-py) (4.13.2)
Collecting filetype (from maxim-py)
  Downloading filetype-1.2.0-py2.py3-none-any.whl.metadata (6.5 kB)
Requirement already satisfied: anyio in /usr/local/lib/python3.11/dist-packages (from httpx>=0.28.1->mistralai) (4.9.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.11/dist-packages (from httpx>=0.28.1->mistralai) (2025.4.26)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx>=0.28.1->mistralai) (1.0.9)
Requirement already satisfied: idna in /usr/local/lib/python3.11/dist-packages (from httpx>=0.28.1->mistralai) (3.10)
Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.11/dist-packages (from httpcore==1.*->httpx>=0.28.1->mistralai) (0.16.0)
Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.10.3->mistralai) (0.7.0)
Requirement already satisfied: pydantic-core==2.33.2 in /usr/local/lib/python3.11/dist-packages (from pydantic>=2.10.3->mistralai) (2.33.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->mistralai) (1.17.0)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->maxim-py) (3.4.2)
Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.11/dist-packages (from anyio->httpx>=0.28.1->mistralai) (1.3.1)
Downloading mistralai-1.8.1-py3-none-any.whl (373 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 373.2/373.2 kB 3.6 MB/s eta 0:00:00
Downloading maxim_py-3.8.1-py3-none-any.whl (174 kB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 174.2/174.2 kB 7.5 MB/s eta 0:00:00
Downloading eval_type_backport-0.2.2-py3-none-any.whl (5.8 kB)
Downloading filetype-1.2.0-py2.py3-none-any.whl (19 kB)
Installing collected packages: filetype, eval-type-backport, maxim-py, mistralai
Successfully installed eval-type-backport-0.2.2 filetype-1.2.0 maxim-py-3.8.1 mistralai-1.8.1

Set the environment variables

You can sign up on Maxim and create a new Api Key from Settings. After that go to Logs section and create a new Log Repository, you will receive a Log Repository Id. Get ready with your Mistral Api Key also.

[ ]

Initialize logger

Create an instance of Maxim Logger

[ ]
INFO:maxim:[MaximSDK] Starting flush thread with interval {10} seconds

[MaximSDK] Initializing Maxim AI(v3.8.1)
[MaximSDK] Using info logging level.
[MaximSDK] For debug logs, set global logging level to debug logging.basicConfig(level=logging.DEBUG).

Make LLM calls using MaximMistralClient

Make a call to Mistral via Mistral Api Client provided by Maxim, define the model you want to use and list of messages.

[ ]
id='e161b1cd452042549d5292b6a60f6b83' object='chat.completion' model='mistral-medium-latest' usage=UsageInfo(prompt_tokens=16, completion_tokens=23, total_tokens=39) created=1749107242 choices=[ChatCompletionChoice(index=0, message=AssistantMessage(content='Claude Monet is often regarded as the best French painter, renowned for his pioneering role in Impressionism.', tool_calls=None, prefix=False, role='assistant'), finish_reason='stop')]

To check the logs shared by Mistral SDK with Maxim -

  1. Go to Logs section in Maxim Platform
  2. Go to the respective Log Repository you created.
  3. Switch to Logs from top tab view and analyse the traces received

Gif

Async LLM call

[ ]
id='ef228964167649278f1eeecfe6d985d4' object='chat.completion' model='mistral-small-latest' usage=UsageInfo(prompt_tokens=18, completion_tokens=34, total_tokens=52) created=1749106669 choices=[ChatCompletionChoice(index=0, message=AssistantMessage(content='Async programming in Python allows for concurrent execution of tasks using `async` and `await` keywords, while sync programming executes tasks sequentially, blocking until each task completes.', tool_calls=None, prefix=False, role='assistant'), finish_reason='stop')]

Feedback

If you have any feedback or requests, please create a GitHub Issue.