azure-ai-inference

import os from azure.ai.inference import AzureAIInferenceClient from azure.ai.inference.models import ChatCompletionsOptions from azure.identity import DefaultAzureCredential # Set your Azure AI Inference service endpoint as an environment variable: # export AZURE_AI_INFERENCE_ENDPOINT="https://<your-service-name>.inference.ai.azure.com/" endpoint = os.environ.get("AZURE_AI_INFERENCE_ENDPOINT", "") if not endpoint: raise ValueError("Please set the AZURE_AI_INFERENCE_ENDPOINT environment variable.") # Authenticate using DefaultAzureCredential (checks environment variables, Azure CLI, etc.) credential = DefaultAzureCredential() try: # Initialize the client client = AzureAIInferenceClient(endpoint=endpoint, credential=credential) # Example: Chat Completion messages = [ {"role": "system", "content": "You are a helpful AI assistant."}, {"role": "user", "content": "What is the capital of France?"}, ] chat_options = ChatCompletionsOptions( messages=messages, model="gpt-35-turbo", # Replace with your deployed model name max_tokens=128 ) print(f"Sending chat completion request to model: {chat_options.model}...") response = client.chat.completions(chat_options) for choice in response.choices: print(f"Assistant: {choice.message.content}") except Exception as e: print(f"An error occurred: {e}") print("Ensure AZURE_AI_INFERENCE_ENDPOINT is set and you are authenticated to Azure (e.g., via `az login`).")