Melhores práticas de cache explícito

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace WorkspaceId with your actual Workspace ID.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# System prompt: product manual (must exceed 1024 tokens)
product_manual = """You are the support assistant for "BaiLian SmartHome" smart home controller. Here is the complete product manual:

## Product Overview
BaiLian SmartHome is a whole-home smart controller supporting voice control, scene automation, and energy management...

## Installation Guide
1. Install at a central location with good WiFi coverage...
2. Connect the power adapter (5V/2A)...

## FAQ
Q: Cannot connect to WiFi? A: Make sure your router supports 2.4GHz...
""" * 80  # Repeat to exceed 1024 tokens

messages = [{"role": "system", "content": product_manual}]

def chat(user_input):
    # Key: add cache_control to the last user message
    messages.append({
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": user_input,
                "cache_control": {"type": "ephemeral"},
            }
        ],
    })
    completion = client.chat.completions.create(
        model="qwen3.7-max",
        messages=messages,
        extra_body={"enable_thinking": False},
    )
    assistant_msg = completion.choices[0].message.content
    messages.append({"role": "assistant", "content": assistant_msg})

    usage = completion.usage
    created = usage.prompt_tokens_details.cache_creation_input_tokens
    cached = usage.prompt_tokens_details.cached_tokens
    print(f"  [Cache] Created: {created} tokens, Hit: {cached} tokens")
    return assistant_msg

# Simulate multi-turn conversation
print("User: What voice assistants does BaiLian SmartHome support?")
print(f"Agent: {chat('What voice assistants does BaiLian SmartHome support?')[:80]}...\n")

print("User: What if I cannot connect to WiFi?")
print(f"Agent: {chat('What if I cannot connect to WiFi?')[:80]}...\n")

print("User: How many devices can it control simultaneously?")
print(f"Agent: {chat('How many devices can it control simultaneously?')[:80]}...")

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace WorkspaceId with your actual Workspace ID.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# Layer 1: System persona (rarely changes)
system_persona = """You are the senior AI support agent for "Model Studio Electronics". Your guidelines:
1. Answer questions based on the knowledge base
2. For information not in the knowledge base, say "Let me transfer you to a human agent"
3. Maintain a professional and friendly tone
4. If the user is unhappy, apologize first then resolve the issue

Below is your complete service specification and script guide:
""" + "Detailed service specification..." * 200  # Ensure > 1024 tokens

# Layer 2: Tools/skills definitions (changes occasionally, e.g. when new features launch)
tools_description = """### Available Tools
- search_product(query): Search product information
- check_inventory(sku, color): Check stock status
- create_ticket(type, description): Create a support ticket
- transfer_to_human(reason): Transfer to a human agent

### Tool Usage Rules
1. When user asks about product details, use search_product first
2. When user asks about stock/shipping, use check_inventory
3. When user requests return/exchange, use create_ticket
4. When a tool returns an error, apologize and transfer_to_human
""" + "Detailed tool usage examples..." * 150  # Ensure > 1024 tokens

# Layer 3: Project knowledge base (semi-stable, changes when user switches products)
knowledge_base_product_a = """### Current product: Model Studio Pro Max Wireless Earbuds
- SKU: BL-PM-2024
- Price: CNY 599
- Colors: Night Black / Nebula White / Ice Blue
- Battery: 8 hours (ANC on), 12 hours (ANC off)
- Water resistance: IPX5
- Warranty: 1 year, 7-day no-questions-asked return
- Stock: Night Black (in stock) / Nebula White (low) / Ice Blue (out of stock)
""" * 50  # Ensure > 1024 tokens

def ask_agent(user_question, history=None):
    if history is None:
        history = []
    messages = [
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": system_persona + "\n\n" + tools_description,
                    "cache_control": {"type": "ephemeral"},  # Marker 1: system persona + tools
                }
            ],
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": f"Here is the knowledge base for the current product:\n{knowledge_base_product_a}",
                    "cache_control": {"type": "ephemeral"},  # Marker 2: knowledge base
                }
            ],
        },
        {"role": "assistant", "content": "Got it. I have the product details ready. How can I help you?"},
    ]
    messages.extend(history)
    # Add current question with marker 3
    messages.append({
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": user_question,
                "cache_control": {"type": "ephemeral"},  # Marker 3: conversation history
            }
        ],
    })

    completion = client.chat.completions.create(
        model="qwen3.7-max",
        messages=messages,
        extra_body={"enable_thinking": False},
    )
    usage = completion.usage
    print(f"  Created: {usage.prompt_tokens_details.cache_creation_input_tokens}, "
          f"Hit: {usage.prompt_tokens_details.cached_tokens}")
    return completion.choices[0].message.content

# First request
print("Q1: Is the Ice Blue color available?")
a1 = ask_agent("Is the Ice Blue color available?")
print(f"A1: {a1}\n")

# Second request: same product (persona + tools + knowledge base all hit)
history = [
    {"role": "user", "content": "Is the Ice Blue color available?"},
    {"role": "assistant", "content": a1},
]
print("Q2: When will it be back in stock?")
a2 = ask_agent("When will it be back in stock?", history)
print(f"A2: {a2}")

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace WorkspaceId with your actual Workspace ID.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# Long system prompt: detailed classification rules (must exceed 1024 tokens)
classification_prompt = """You are a product review classifier. Classify each review into one of these categories:
- Positive
- Negative
- Neutral
- Question
- Complaint

Output only the category name, nothing else.

Detailed classification rules and examples:
""" + """Rules:
1. Positive: Contains positive sentiment words (e.g., "great", "excellent", "recommend"), or expresses satisfaction.
2. Negative: Contains negative sentiment words (e.g., "terrible", "disappointed", "return"), or expresses dissatisfaction.
3. Neutral: No clear sentiment, merely states facts.
4. Question: Phrased as a question asking for product information.
5. Complaint: Expresses suggestions for improvement or lodges a complaint.
""" * 100

# Reviews to classify (simulating batch processing)
reviews = [
    "This product is amazing, great quality, highly recommended!",
    "Shipping took a week and the packaging was damaged",
    "Does this come in red? Does it run large or small?",
    "You should add more size options, medium is too big for me",
    "It's okay I guess, nothing special, does what it says",
]

print("=== Batch Classification (Explicit Cache) ===")
for i, review in enumerate(reviews):
    completion = client.chat.completions.create(
        model="qwen3.7-max",
        messages=[
            {
                "role": "system",
                "content": [
                    {
                        "type": "text",
                        "text": classification_prompt,
                        "cache_control": {"type": "ephemeral"},  # Cache classification rules
                    }
                ],
            },
            {"role": "user", "content": review},
        ],
    )
    result = completion.choices[0].message.content
    cached = completion.usage.prompt_tokens_details.cached_tokens
    created = completion.usage.prompt_tokens_details.cache_creation_input_tokens
    print(f"Review {i+1}: \"{review[:40]}...\" -> {result}")
    print(f"  Created: {created}, Hit: {cached}")

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # Replace WorkspaceId with your actual Workspace ID.
    base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)

# Long text to meet the 1024-token minimum
long_text_content = "<Your Code Here>" * 400

# Tool definitions: must be exactly identical across requests
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a given city",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "City name"},
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
                },
                "required": ["city"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search_flights",
            "description": "Search flights between two cities",
            "parameters": {
                "type": "object",
                "properties": {
                    "origin": {"type": "string", "description": "Departure city"},
                    "destination": {"type": "string", "description": "Destination city"},
                    "date": {"type": "string", "description": "Departure date in YYYY-MM-DD format"}
                },
                "required": ["origin", "destination", "date"]
            }
        }
    }
]

def ask(user_input):
    messages = [
        {
            "role": "system",
            "content": [
                {
                    "type": "text",
                    "text": long_text_content,
                    # cache_control can only be added to message content, not to tools
                    "cache_control": {"type": "ephemeral"},
                }
            ],
        },
        {"role": "user", "content": user_input},
    ]
    completion = client.chat.completions.create(
        model="qwen3.7-max",
        messages=messages,
        tools=tools,
        extra_body={"enable_thinking": False},
    )
    usage = completion.usage
    print(f"  Created: {usage.prompt_tokens_details.cache_creation_input_tokens}, "
          f"Hit: {usage.prompt_tokens_details.cached_tokens}")
    tool_calls = completion.choices[0].message.tool_calls
    if tool_calls:
        print(f"  Tools called: {[t.function.name for t in tool_calls]}")
    return completion

# First request: creates cache (includes tool definitions)
print("Q1: What's the weather in Beijing today?")
ask("What's the weather in Beijing today?")

# Second request: hits cache
print("\nQ2: Find flights from Shanghai to Beijing tomorrow")
ask("Find flights from Shanghai to Beijing tomorrow")