Mistral

# pip install mistralai
from mistralai import Mistral

# 1. Mistral API 사용
client = Mistral(api_key="your-api-key")

# 기본 채팅 완성
response = client.chat.complete(
    model="mistral-large-latest",  # 또는 "mistral-small-latest", "open-mixtral-8x22b"
    messages=[
        {"role": "user", "content": "Python에서 비동기 프로그래밍의 장점을 설명해주세요."}
    ],
    temperature=0.7,
    max_tokens=1024
)
print(response.choices[0].message.content)

# 2. 스트리밍 응답
stream = client.chat.stream(
    model="mistral-large-latest",
    messages=[{"role": "user", "content": "간단한 FastAPI 서버 코드를 작성해주세요."}]
)

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

# 3. Function Calling (Tool Use)
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "도시의 현재 날씨를 조회합니다",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "도시 이름"}
                },
                "required": ["city"]
            }
        }
    }
]

response = client.chat.complete(
    model="mistral-large-latest",
    messages=[{"role": "user", "content": "서울 날씨 어때?"}],
    tools=tools,
    tool_choice="auto"
)

# 4. HuggingFace Transformers로 로컬 실행
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Mistral 7B Instruct (약 14GB VRAM 필요)
model_id = "mistralai/Mistral-7B-Instruct-v0.3"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [{"role": "user", "content": "메타 러닝이란 무엇인가요?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=True, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

# 5. vLLM으로 고성능 서빙 (프로덕션 권장)
# pip install vllm
from vllm import LLM, SamplingParams

llm = LLM(model="mistralai/Mistral-7B-Instruct-v0.3")
sampling_params = SamplingParams(temperature=0.7, max_tokens=512)

prompts = ["[INST] FastAPI와 Flask의 차이점은? [/INST]"]
outputs = llm.generate(prompts, sampling_params)

for output in outputs:
    print(output.outputs[0].text)