# Create OpenAI account
az cognitiveservices account create \
  --name myopenai \
  --resource-group MyRG \
  --kind OpenAI \
  --sku S0 \
  --location eastus \
  --custom-domain myopenai \
  --public-network-access Disabled \
  --identity-type SystemAssigned

# Get endpoint and key
az cognitiveservices account show \
  --name myopenai \
  --resource-group MyRG \
  --query "properties.endpoint" \
  --output tsv

az cognitiveservices account keys list \
  --name myopenai \
  --resource-group MyRG \
  --query "key1" \
  --output tsv

# Deploy gpt-5
az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name gpt-5 \
  --model-name gpt-5 \
  --model-version latest \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 100 \
  --scale-type Standard

# Deploy gpt-5-pro (requires registration)
az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name gpt-5-pro \
  --model-name gpt-5-pro \
  --model-version latest \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 50

# Deploy o3 reasoning model
az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name o3-reasoning \
  --model-name o3 \
  --model-version latest \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 50

# Deploy o4-mini
az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name o4-mini \
  --model-name o4-mini \
  --model-version latest \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 100

az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name gpt-4-1 \
  --model-name gpt-4.1 \
  --model-version latest \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 100

az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name image-gen \
  --model-name gpt-image-1 \
  --model-version 2025-04-15 \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 10

az cognitiveservices account deployment create \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name sora \
  --model-name sora \
  --model-version 2025-05-02 \
  --model-format OpenAI \
  --sku-name Standard \
  --sku-capacity 5

from openai import AzureOpenAI
import os

# Initialize client
client = AzureOpenAI(
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    api_version="2025-02-01-preview",
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT")
)

# GPT-5 completion
response = client.chat.completions.create(
    model="gpt-5",  # deployment name
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    max_tokens=1000,
    temperature=0.7,
    top_p=0.95
)

print(response.choices[0].message.content)

# o3 reasoning with chain-of-thought
response = client.chat.completions.create(
    model="o3-reasoning",
    messages=[
        {"role": "system", "content": "You are an expert problem solver. Show your reasoning step-by-step."},
        {"role": "user", "content": "If a train travels 120 km in 2 hours, then speeds up to travel 180 km in the next 2 hours, what is the average speed for the entire journey?"}
    ],
    max_tokens=2000,
    temperature=0.2  # Lower temperature for reasoning tasks
)

print(response.choices[0].message.content)

# Read a large document
with open('large_document.txt', 'r') as f:
    document = f.read()

# GPT-4.1 can handle up to 1M tokens
response = client.chat.completions.create(
    model="gpt-4-1",
    messages=[
        {"role": "system", "content": "You are a document analysis expert."},
        {"role": "user", "content": f"Analyze this document and provide key insights:\n\n{document}"}
    ],
    max_tokens=4000
)

print(response.choices[0].message.content)

# Generate image with DALL-E 3 successor
response = client.images.generate(
    model="image-gen",
    prompt="A futuristic city with flying cars and vertical gardens, cyberpunk style, highly detailed, 4K",
    size="1024x1024",
    quality="hd",
    n=1
)

image_url = response.data[0].url
print(f"Generated image: {image_url}")

# Generate video with Sora
response = client.videos.generate(
    model="sora",
    prompt="A serene lakeside at sunset with birds flying overhead and gentle waves on the shore",
    duration=10,  # seconds
    resolution="1080p",
    fps=30
)

video_url = response.data[0].url
print(f"Generated video: {video_url}")

# Transcribe audio file
audio_file = open("meeting_recording.mp3", "rb")

response = client.audio.transcriptions.create(
    model="gpt-4o-transcribe",
    file=audio_file,
    language="en",
    response_format="verbose_json"
)

print(f"Transcription: {response.text}")
print(f"Duration: {response.duration}s")

# Speaker diarization
for segment in response.segments:
    print(f"[{segment.start}s - {segment.end}s] {segment.text}")

from azure.ai.foundry import ModelRouter

# Initialize model router
router = ModelRouter(
    endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
    credential=os.getenv("AZURE_OPENAI_API_KEY")
)

# Automatically select optimal model
response = router.complete(
    prompt="Analyze this complex scientific paper...",
    optimization_goals=["quality", "cost"],
    available_models=["gpt-5", "gpt-5-mini", "gpt-4-1"]
)

print(f"Selected model: {response.model_used}")
print(f"Response: {response.content}")
print(f"Cost: ${response.cost}")

from azure.search.documents import SearchClient
from azure.core.credentials import AzureKeyCredential

# Initialize search client
search_client = SearchClient(
    endpoint=os.getenv("SEARCH_ENDPOINT"),
    index_name="documents",
    credential=AzureKeyCredential(os.getenv("SEARCH_KEY"))
)

# Agentic retrieval with Azure OpenAI
response = client.chat.completions.create(
    model="gpt-5",
    messages=[
        {"role": "system", "content": "You have access to a document search system."},
        {"role": "user", "content": "What are the company's revenue projections for Q3?"}
    ],
    tools=[{
        "type": "function",
        "function": {
            "name": "search_documents",
            "description": "Search company documents",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "Search query"}
                },
                "required": ["query"]
            }
        }
    }],
    tool_choice="auto"
)

# Process tool calls
if response.choices[0].message.tool_calls:
    for tool_call in response.choices[0].message.tool_calls:
        if tool_call.function.name == "search_documents":
            query = json.loads(tool_call.function.arguments)["query"]
            results = search_client.search(query)
            # Feed results back to model for final answer

from azure.ai.foundry import FoundryObservability

# Enable observability
observability = FoundryObservability(
    workspace_id=os.getenv("AI_FOUNDRY_WORKSPACE_ID"),
    enable_tracing=True,
    enable_metrics=True
)

# Monitor agent execution
with observability.trace_agent("customer_support_agent") as trace:
    response = client.chat.completions.create(
        model="gpt-5",
        messages=messages
    )

    trace.log_tool_call("search_kb", {"query": "refund policy"})
    trace.log_reasoning_step("Retrieved refund policy document")
    trace.log_token_usage(response.usage.total_tokens)

# View in Azure AI Foundry portal:
# - End-to-end trace logs
# - Reasoning steps and tool calls
# - Performance metrics
# - Cost analysis

# List deployments with usage
az cognitiveservices account deployment list \
  --resource-group MyRG \
  --name myopenai \
  --output table

# Check usage metrics
az monitor metrics list \
  --resource $(az cognitiveservices account show -g MyRG -n myopenai --query id -o tsv) \
  --metric "TokenTransaction" \
  --start-time 2025-01-01T00:00:00Z \
  --end-time 2025-01-31T23:59:59Z \
  --interval PT1H \
  --aggregation Total

# Scale up deployment capacity
az cognitiveservices account deployment update \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name gpt-5 \
  --sku-capacity 200

# Scale down during off-peak
az cognitiveservices account deployment update \
  --resource-group MyRG \
  --name myopenai \
  --deployment-name gpt-5 \
  --sku-capacity 50

# Create private endpoint
az network private-endpoint create \
  --name openai-private-endpoint \
  --resource-group MyRG \
  --vnet-name MyVNet \
  --subnet PrivateEndpointSubnet \
  --private-connection-resource-id $(az cognitiveservices account show -g MyRG -n myopenai --query id -o tsv) \
  --group-id account \
  --connection-name openai-connection

# Create private DNS zone
az network private-dns zone create \
  --resource-group MyRG \
  --name privatelink.openai.azure.com

# Link to VNet
az network private-dns link vnet create \
  --resource-group MyRG \
  --zone-name privatelink.openai.azure.com \
  --name openai-dns-link \
  --virtual-network MyVNet \
  --registration-enabled false

# Create DNS zone group
az network private-endpoint dns-zone-group create \
  --resource-group MyRG \
  --endpoint-name openai-private-endpoint \
  --name default \
  --private-dns-zone privatelink.openai.azure.com \
  --zone-name privatelink.openai.azure.com

# Enable system-assigned identity
az cognitiveservices account identity assign \
  --name myopenai \
  --resource-group MyRG

# Grant role to managed identity
PRINCIPAL_ID=$(az cognitiveservices account show -g MyRG -n myopenai --query identity.principalId -o tsv)

az role assignment create \
  --assignee $PRINCIPAL_ID \
  --role "Cognitive Services OpenAI User" \
  --scope /subscriptions/<sub-id>/resourceGroups/MyRG

# Configure content filtering
az cognitiveservices account update \
  --name myopenai \
  --resource-group MyRG \
  --set properties.customContentFilter='{
    "hate": {"severity": "medium", "enabled": true},
    "violence": {"severity": "medium", "enabled": true},
    "sexual": {"severity": "medium", "enabled": true},
    "selfHarm": {"severity": "high", "enabled": true}
  }'