Implementation:Mistralai Client python Azure Chat Complete
| Knowledge Sources | |
|---|---|
| Domains | Cloud_Deployment, Azure, LLM_Inference |
| Last Updated | 2026-02-15 14:00 GMT |
Overview
Concrete tool for sending chat completion and streaming requests to Azure-deployed Mistral models provided by the mistralai_azure Chat resource.
Description
The Azure Chat resource provides complete(), complete_async(), stream(), and stream_async() methods identical in interface to the standard Mistral Chat resource. The difference is internal: requests are routed to the Azure endpoint configured during MistralAzure client initialization. The same parameters (model, messages, temperature, tools, etc.) and response types (ChatCompletionResponse, EventStream) are used.
Usage
Access via client.chat.complete() or client.chat.stream() on a MistralAzure client instance. The model parameter typically uses the Azure deployment name (e.g., "azureai") rather than Mistral model IDs.
Code Reference
Source Location
- Repository: client-python
- File: packages/mistralai_azure/src/mistralai_azure/chat.py
- Lines: L1-693
Signature
class Chat:
def complete(
self,
*,
model: str,
messages: List[ChatCompletionRequestMessage],
temperature: Optional[float] = None,
top_p: Optional[float] = None,
max_tokens: Optional[int] = None,
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[Tool]] = None,
safe_prompt: Optional[bool] = None,
) -> ChatCompletionResponse:
...
def stream(
self,
*,
model: str,
messages: List[ChatCompletionStreamRequestMessage],
# Same parameters
) -> EventStream[CompletionEvent]:
...
Import
from mistralai_azure import MistralAzure
# Access via: client.chat.complete(...) or client.chat.stream(...)
I/O Contract
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
| model | str | Yes | Azure deployment model name |
| messages | List[ChatCompletionRequestMessage] | Yes | Conversation messages |
| temperature | Optional[float] | No | Sampling temperature |
| max_tokens | Optional[int] | No | Maximum output tokens |
| tools | Optional[List[Tool]] | No | Tool definitions for function calling |
Outputs
| Name | Type | Description |
|---|---|---|
| response | ChatCompletionResponse | Complete response (for complete()) |
| stream | EventStream[CompletionEvent] | Streaming response (for stream()) |
Usage Examples
Azure Chat Completion
import os
from mistralai_azure import MistralAzure
from mistralai_azure.models import UserMessage
client = MistralAzure(
azure_api_key=os.environ["AZURE_API_KEY"],
azure_endpoint=os.environ["AZURE_ENDPOINT"],
)
# Synchronous completion
response = client.chat.complete(
model="azureai",
messages=[UserMessage(content="What is the capital of France?")],
)
print(response.choices[0].message.content)
# Streaming
with client.chat.stream(
model="azureai",
messages=[UserMessage(content="Write a haiku.")],
) as stream:
for chunk in stream:
content = chunk.data.choices[0].delta.content
if content:
print(content, end="")