openinference-instrumentation-mistralai

OpenInference Mistral AI Instrumentation

Python autoinstrumentation library for MistralAI's Python SDK.

The traces emitted by this instrumentation are fully OpenTelemetry compatible and can be sent to an OpenTelemetry collector for viewing, such as arize-phoenix

Installation

pip install openinference-instrumentation-mistralai

Quickstart

In this example we will instrument a small program that uses the MistralAI chat completions API and observe the traces via arize-phoenix.

Install packages.

pip install openinference-instrumentation-mistralai mistralai arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp

Start the phoenix server so that it is ready to collect traces. The Phoenix server runs entirely on your machine and does not send data over the internet.

python -m phoenix.server.main serve

In a python file, setup the MistralAIInstrumentor and configure the tracer to send traces to Phoenix.

from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage
from openinference.instrumentation.mistralai import MistralAIInstrumentor
from opentelemetry import trace as trace_api
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor

endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
# Optionally, you can also print the spans to the console.
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))
trace_api.set_tracer_provider(tracer_provider)

MistralAIInstrumentor().instrument()


if __name__ == "__main__":
    client = MistralClient()
    response = client.chat(
        model="mistral-large-latest",
        messages=[
            ChatMessage(
                content="Who won the World Cup in 2018?",
                role="user",
            )
        ],
    )
    print(response.choices[0].message.content)

Since we are using MistralAI, we must set the MISTRAL_API_KEY environment variable to authenticate with the MistralAI API.

export MISTRAL_API_KEY=[your_key_here]

Now simply run the python file and observe the traces in Phoenix.

python your_file.py

More Info

Fore details about tracing with OpenInference and Phoenix, consult the Phoenix documentation.

For AI/ML observability solutions in production, check out the docs on Arize.