Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Mistralai Client python MistralAzure Init

From Leeroopedia
Revision as of 13:15, 16 February 2026 by Admin (talk | contribs) (Auto-imported from implementations/Mistralai_Client_python_MistralAzure_Init.md)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Knowledge Sources
Domains Cloud_Deployment, Azure, API_Client
Last Updated 2026-02-15 14:00 GMT

Overview

Concrete tool for creating an Azure-specific Mistral API client provided by the mistralai_azure package.

Description

The MistralAzure class initializes a client for Mistral models deployed on Azure AI. It accepts azure_api_key (string or callable) and azure_endpoint (the Azure deployment URL). The constructor normalizes the endpoint by stripping trailing slashes and appending /v1/ if not already present. It registers a CustomUserAgentHook that rewrites the User-Agent header to identify Azure SDK traffic. The client exposes lazy-loaded .chat and .ocr sub-SDKs.

Usage

Install mistralai_azure and instantiate with Azure credentials obtained from the Azure portal after deploying a Mistral model.

Code Reference

Source Location

  • Repository: client-python
  • File: packages/mistralai_azure/src/mistralai_azure/sdk.py
  • Lines: L32-128

Signature

class MistralAzure:
    def __init__(
        self,
        azure_api_key: Union[str, Callable[[], str]],
        azure_endpoint: str,
        retry_config: OptionalNullable[RetryConfig] = UNSET,
        timeout_ms: Optional[int] = None,
        http_client: Optional[HttpClient] = None,
        async_http_client: Optional[AsyncHttpClient] = None,
        debug_logger: Optional[Logger] = None,
    ):
        """
        Args:
            azure_api_key: Azure API key or callable returning a key.
            azure_endpoint: Azure AI deployment endpoint URL.
            retry_config: Retry settings.
            timeout_ms: Request timeout in milliseconds.
        """

Import

from mistralai_azure import MistralAzure

I/O Contract

Inputs

Name Type Required Description
azure_api_key Union[str, Callable] Yes Azure API key from Azure portal
azure_endpoint str Yes Azure AI deployment endpoint URL
retry_config OptionalNullable[RetryConfig] No Retry configuration
timeout_ms Optional[int] No Timeout in milliseconds

Outputs

Name Type Description
MistralAzure instance MistralAzure Configured client with .chat and .ocr sub-SDKs

Usage Examples

Basic Azure Client

import os
from mistralai_azure import MistralAzure

client = MistralAzure(
    azure_api_key=os.environ["AZURE_API_KEY"],
    azure_endpoint=os.environ["AZURE_ENDPOINT"],
)

# Use chat completion
response = client.chat.complete(
    model="azureai",
    messages=[{"role": "user", "content": "Hello from Azure!"}],
)
print(response.choices[0].message.content)

Related Pages

Implements Principle

Requires Environment

Uses Heuristic

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment