Claude Models Guide

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {
            "role": "user",
            "content": """
            Write a Python function to implement:
            1. Binary search algorithm
            2. Include detailed comments
            3. Provide usage examples
            4. Time complexity analysis
            """
        }
    ],
    temperature=0.5  # Lower temperature for more accurate code
)

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

# Read long document
with open('long_document.txt', 'r', encoding='utf-8') as f:
    document = f.read()

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {
            "role": "user",
            "content": f"""
            Please analyze the following document and provide:
            1. Summary (3-5 sentences)
            2. Key information extraction
            3. Insights and recommendations
            
            Document content:
            {document}
            """
        }
    ],
    max_tokens=2000
)

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

data_analysis_prompt = """
Please analyze the following sales data and provide:
1. Growth trends
2. Key insights
3. Potential problems
4. Optimization recommendations

Sales data:
Q1: 1000 units, revenue $50,000
Q2: 1200 units, revenue $58,000
Q3: 900 units, revenue $42,000
Q4: 1500 units, revenue $75,000
"""

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[{"role": "user", "content": data_analysis_prompt}],
    temperature=0.3  # Lower temperature for more objective analysis
)

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

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {
            "role": "user",
            "content": """
            Write a 500-word short story:
            - Theme: Future city
            - Style: Cyberpunk
            - Conflict: Human-AI relationship
            """
        }
    ],
    temperature=1.0  # Higher temperature for more creativity
)

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

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image? Provide detailed description."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg"
                    }
                }
            ]
        }
    ]
)

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

complex_task = """
Please complete the following tasks in order:
1. Write a Python function to check if a string is a palindrome
2. Write unit tests for this function
3. Explain the function's time and space complexity
4. Provide optimization suggestions
"""

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[{"role": "user", "content": complex_task}]
)

# Chinese dialogue
response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {"role": "user", "content": "请介绍一下中国的四大发明"}
    ]
)

# ❌ Inefficient: Passing too much history
def chat_inefficient(user_input, all_history):
    messages = all_history  # May be very long
    messages.append({"role": "user", "content": user_input})
    return client.chat.completions.create(model="claude-3-5-sonnet", messages=messages)

# ✅ Efficient: Only keep necessary context
def chat_efficient(user_input, recent_history):
    messages = [
        {"role": "system", "content": "You are a helpful assistant"},
        *recent_history[-6:],  # Only recent 3 rounds (6 messages)
        {"role": "user", "content": user_input}
    ]
    return client.chat.completions.create(model="claude-3-5-sonnet", messages=messages)

import hashlib
import json

# Simple cache implementation
cache = {}

def get_cached_response(messages, model="claude-3-5-sonnet"):
    # Generate cache key
    cache_key = hashlib.md5(
        json.dumps(messages).encode()
    ).hexdigest()
    
    # Check cache
    if cache_key in cache:
        return cache[cache_key]
    
    # Call API
    response = client.chat.completions.create(
        model=model,
        messages=messages
    )
    
    # Save to cache
    cache[cache_key] = response
    return response

# Good system prompt example
system_prompt = """
You are a professional Python programming assistant with the following characteristics:
1. Provide clear, runnable code
2. Include detailed comments
3. Follow PEP 8 standards
4. Consider edge cases
5. Give usage examples
"""

response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": "Write a function to merge two sorted arrays"}
    ]
)

# Maintain conversation history
conversation_history = [
    {"role": "system", "content": "You are a helpful assistant"}
]

def chat(user_input):
    # Add user message
    conversation_history.append({
        "role": "user",
        "content": user_input
    })
    
    # Get response
    response = client.chat.completions.create(
        model="claude-3-5-sonnet-20241022",
        messages=conversation_history
    )
    
    # Add assistant response
    assistant_message = response.choices[0].message.content
    conversation_history.append({
        "role": "assistant",
        "content": assistant_message
    })
    
    return assistant_message

# Usage
print(chat("What is quantum computing?"))
print(chat("What are its application scenarios?"))  # Continues previous topic

def chat_stream(user_input):
    stream = client.chat.completions.create(
        model="claude-3-5-sonnet-20241022",
        messages=[{"role": "user", "content": user_input}],
        stream=True
    )
    
    print("Response: ", end="")
    for chunk in stream:
        if chunk.choices[0].delta.content:
            print(chunk.choices[0].delta.content, end="", flush=True)
    print()

# Usage
chat_stream("Write a story about AI")