1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
|
# ------------------------------------
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
# ------------------------------------
"""
DESCRIPTION:
This sample demonstrates how to get a chat completion response
from the service using an asynchronous client.
This sample assumes the AI model is hosted on a Serverless API or
Managed Compute endpoint. For GitHub Models or Azure OpenAI endpoints,
the client constructor needs to be modified. See package documentation:
https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-inference/README.md#key-concepts
USAGE:
python sample_chat_completion_async.py
Set these two environment variables before running the sample:
1) AZURE_AI_CHAT_ENDPOINT - Your endpoint URL, in the form
https://<your-deployment-name>.<your-azure-region>.models.ai.azure.com
where `your-deployment-name` is your unique AI Model deployment name, and
`your-azure-region` is the Azure region where your model is deployed.
2) AZURE_AI_CHAT_KEY - Your model key. Keep it secret.
"""
import asyncio
async def sample_chat_completions_async():
import os
from azure.ai.inference.aio import ChatCompletionsClient
from azure.ai.inference.models import SystemMessage, UserMessage
from azure.core.credentials import AzureKeyCredential
try:
endpoint = os.environ["AZURE_AI_CHAT_ENDPOINT"]
key = os.environ["AZURE_AI_CHAT_KEY"]
except KeyError:
print("Missing environment variable 'AZURE_AI_CHAT_ENDPOINT' or 'AZURE_AI_CHAT_KEY'")
print("Set them before running this sample.")
exit()
async with ChatCompletionsClient(endpoint=endpoint, credential=AzureKeyCredential(key)) as client:
response = await client.complete(
messages=[
SystemMessage("You are a helpful assistant."),
UserMessage("How many feet are in a mile?"),
]
)
print(response.choices[0].message.content)
print(f"\nToken usage: {response.usage}")
async def main():
await sample_chat_completions_async()
if __name__ == "__main__":
asyncio.run(main())
|
