Mistral API - European Open-Source AI Developer Interface

pip install mistralai
# Or use OpenAI SDK (compatible)
pip install openai

from mistralai.client import MistralClient
from mistralai.models.chat_completion import ChatMessage

# Initialize client
client = MistralClient(api_key="YOUR_API_KEY")

# Send request
messages = [
    ChatMessage(role="user", content="What is machine learning?")
]

response = client.chat(
    model="mistral-large-latest",
    messages=messages
)

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

from openai import OpenAI

# Initialize client (using Mistral API)
client = OpenAI(
    api_key="YOUR_MISTRAL_API_KEY",
    base_url="https://api.mistral.ai/v1"
)

# Send request
response = client.chat.completions.create(
    model="mistral-large-latest",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain the basic principles of deep learning."}
    ],
    max_tokens=1000,
    temperature=0.7
)

print(response.choices[0].message.content)
print(f"\nTokens Used: {response.usage.total_tokens}")

# Streaming output (real-time display)
stream = client.chat.completions.create(
    model="mistral-large-latest",
    messages=[
        {"role": "user", "content": "Write a poem about AI"}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

curl https://api.mistral.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "mistral-large-latest",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Hello, please introduce yourself."
      }
    ],
    "max_tokens": 1000,
    "temperature": 0.7
  }'

curl https://api.mistral.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "mistral-large-latest",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_MISTRAL_API_KEY',
  baseURL: 'https://api.mistral.ai/v1',
});

async function main() {
  const completion = await client.chat.completions.create({
    model: 'mistral-large-latest',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello, please introduce yourself.' }
    ],
    max_tokens: 1000,
    temperature: 0.7,
  });

  console.log(completion.choices[0].message.content);
  console.log(`\nTokens Used: ${completion.usage.total_tokens}`);
}

main();

from openai import OpenAI
import base64

client = OpenAI(
    api_key="YOUR_MISTRAL_API_KEY",
    base_url="https://api.mistral.ai/v1"
)

# Read image and convert to base64
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

image_base64 = encode_image("path/to/your/image.jpg")

# Send multimodal request
response = client.chat.completions.create(
    model="pixtral-large-latest",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{image_base64}"
                    }
                }
            ]
        }
    ]
)

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

# Creative tasks (poetry, stories)
temperature = 0.9

# Balanced (daily chat)
temperature = 0.7

# Precise tasks (code, translation)
temperature = 0.3

# Batch process multiple requests
requests = ["Question 1", "Question 2", "Question 3"]
responses = []

for question in requests:
    response = client.chat.completions.create(
        model="mistral-large-latest",
        messages=[{"role": "user", "content": question}]
    )
    responses.append(response.choices[0].message.content)

def customer_service_bot(user_message, conversation_history):
    """Smart customer service assistant"""
    messages = [
        {"role": "system", "content": "You are a professional customer service assistant, friendly and efficient."}
    ]
    
    # Add conversation history
    messages.extend(conversation_history)
    
    # Add user message
    messages.append({"role": "user", "content": user_message})
    
    response = client.chat.completions.create(
        model="mistral-medium-latest",  # Use Medium for cost balance
        messages=messages,
        temperature=0.7
    )
    
    return response.choices[0].message.content

# Usage example
history = []
user_msg = "I'd like to know about your return policy"
reply = customer_service_bot(user_msg, history)
print(reply)

def analyze_document(image_path):
    """Analyze document image and extract information"""
    import base64
    
    with open(image_path, "rb") as f:
        image_data = base64.b64encode(f.read()).decode()
    
    response = client.chat.completions.create(
        model="pixtral-large-latest",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": "Please analyze this document and extract key information."},
                    {
                        "type": "image_url",
                        "image_url": {"url": f"data:image/jpeg;base64,{image_data}"}
                    }
                ]
            }
        ]
    )
    
    return response.choices[0].message.content

# Usage example
result = analyze_document("invoice.jpg")
print(result)

def code_review(code):
    """Code review and optimization suggestions"""
    response = client.chat.completions.create(
        model="mistral-large-latest",  # Large model better for code
        messages=[
            {
                "role": "system",
                "content": "You are a senior code reviewer providing constructive feedback."
            },
            {
                "role": "user",
                "content": f"Please review the following code and provide optimization suggestions:\n\n```python\n{code}\n```"
            }
        ],
        temperature=0.3  # Low temperature for precision
    )
    
    return response.choices[0].message.content

# Usage example
code = """
def calculate(a, b):
    return a + b
"""
review = code_review(code)
print(review)

# Original OpenAI
client = OpenAI(api_key="sk-...")

# Change to Mistral
client = OpenAI(
    api_key="YOUR_MISTRAL_KEY",
    base_url="https://api.mistral.ai/v1"
)