텍스트 생성

Snowflake에서 시작하는 생성형 AI

James Cha-Earley

Senior Developer Advocate, Snowflake

호텔 리뷰 응답 관리

일몰의 해안가 호텔

¹ Google Gemini 2.5 Pro로 생성된 이미지

summarize()

long_review = """
This hotel was nothing short of amazing. The best views; the best location;
and the best staff. It's clean; conveniently located to other restaurants
on the strip; although we ate at the restaurants on site and each was so good
there's really no reason to leave. Ohhh the views. The beach was free of seaweed; 
amazingly clean and plenty of space; it wasn't crowded at all. 
Stay here; you will not regret it. Did I mention how comfortable the beds were. 
Yes save yourself trouble and stay here. It's really perfect.
"""


from snowflake.cortex import summarize
summarized_review = summarize(text=long_review)

요약 출력하기

print(summarized_review)

The hotel exceeded expectations with stunning views, exceptional staff,
comfortable beds, and top-notch on-site dining, making it a perfect and 
highly recommended stay.

데이터베이스에서 추출하기

셀1의 SQL 쿼리

셀2의 Python 코드

답글 생성하기

from snowflake.cortex import complete


prompt = f"Write a short response to this hotel review: {latest_review}."


# 프롬프트 전달
response = complete(prompt=prompt,

답글 생성하기

from snowflake.cortex import complete


prompt = f"Write a short response to this hotel review: {latest_review}."


# 모델 지정
response = complete(prompt=prompt, 
                    model='llama3.1-8b',

답글 생성하기

from snowflake.cortex import complete


prompt = f"Write a short response to this hotel review: {latest_review}."


# temperature 설정 - 출력 예측 가능성 제어
response = complete(prompt=prompt, 
                    model='llama3.1-8b',
                    options={
                        'temperature':0.3,

답글 생성하기

from snowflake.cortex import complete


prompt = f"Write a short response to this hotel review: {latest_review}."


# max_tokens로 토큰 수 제한
response = complete(prompt=prompt, 
                    model='llama3.1-8b',
                    options={
                        'temperature':0.3,
                        'max_tokens':150
                        }
                    )

응답 확인하기

print(response)

Thank you so much for sharing your wonderful experience at the Hyatt Nice! 
We're thrilled to hear that you had a fantastic stay with us.

빠름, 유연함, 자연스러움

AI_COMPLETE()로 텍스트 생성

SELECT
  DESCRIPTION,
  AI_COMPLETE(

    'llama3.1-8b',

    PROMPT('Write a short response to this hotel review: {0}.', DESCRIPTION),

    {'temperature': 0.3, 'max_tokens': 150}

    ) AS completion
FROM HOTELS.REVIEWS
ORDER BY date DESC
LIMIT 1;

Snowflake 노트북의 출력

Snowflake 노트북의 AI_COMPLETE() 출력

AI_COMPLETE()는 기본 제공됩니다

Snowflake에서 텍스트 생성

-- SQL 셀에서 코딩
AI_COMPLETE(
  'llama3.1-8b',
  PROMPT('Write a short response 
          to this hotel review: {0}.', 
          DESCRIPTION),
  {'temperature': 0.3, 
   'max_tokens': 150}
    )

여러 행에 대해 일괄 생성

# Python 셀에서 코딩
complete(
    model='llama3.1-8b', 
    prompt = f"""Write a short response
        to this hotel review: 
        {latest_review}.""",
    options={'temperature':0.3,
             'max_tokens':150}
    )

다단계 워크플로우 연결에 활용

Ayo berlatih!

Snowflake에서 시작하는 생성형 AI