다단계 AI 워크플로 설계

Snowflake에서 시작하는 생성형 AI

James Cha-Earley

Senior Developer Advocate, Snowflake

Cortex 리뷰 워크플로

목표: 해외 고객 피드백을 위한 자동화 시스템 구축

각 리뷰를 영어로 번역
핵심 내용 요약
담당 팀 라우팅을 위한 분류
응답 생성
원래 언어로 재번역

리뷰를 받아 번역, 요약, 분류하고 응답을 보내는 워크플로

리뷰 추출

-- SQL cell
SELECT DESCRIPTION
FROM HOTELS.REVIEWS
WHERE LANGUAGE = 'es'
LIMIT 1;

# Python cell
df = dataframe_1.to_pandas()
review_text = df["DESCRIPTION"].iloc[0]

스페인어 리뷰

print(review_text)

Buen hotel y bien situado pero desafortunadamente no me toco buena suerte con 
el servicio; el aire no servía; pedí la cama extra tres veces; la cafetera estaba
dañada; y me sacaron las maletas fuera porque argumentaron que no hice Check out;
siendo que era un día despues; pero su sistema lo marco antes; una total
descortesía hecharme del cuarto y cancelar mis llaves; regresar de caminar y darse
cuenta que han tomado tus cosas fuera es increíble y mas aun sin ninguna disculpa;
yo no volvería ahí aunque la vrd el hotel es bueno y su jubilación el trato
me decepciono

번역

translated = translate(
    text=review_text,
    from_language="es",
    to_language="en"
)

print(translated)

Good hotel and well located, but unfortunately, I didn't have good luck with the service; the air
conditioning didn't work; I asked for the extra bed three times; the coffee maker was broken; 
and they took my bags out because they argued that I hadn't checked out; even though it was a day
later; but their system marked it as checked out; a total discourtesy to throw me out of the room
and cancel my keys; returning from a walk and realizing they've taken your things out is
incredible and even more so without any apology; I wouldn't go back there even though the hotel
itself is good and their retirement the treatment disappoints me.

요약

summary = summarize(text=translated)

print(summary)

The hotel was well-located, but the service was disappointing. The air conditioning
didn't work, an extra bed was not provided despite multiple requests, and the coffee
maker was broken. The hotel staff took the complainant's bags and canceled their
keys despite a later checkout date, which was discourteous and left the complainant
feeling disappointed.

분류

topic = classify_text(
    text=summary,
    labels=["staff", "cleanliness", "pricing", "room", "food"]
)

print(topic)

{
  "label": "staff"
}

텍스트 생성

response = complete(
        prompt=f"Write a brief and professional response to this review: {summary}",
        model='llama3.1-8b',
        options={'temperature':0.3, 'max_tokens':120})

print(response)

Thank you for sharing your feedback. While we're glad you found the location
convenient, we're truly sorry to hear about the service issues you experienced.
We understand how frustrating it must have been to face multiple inconveniences
during your stay. Your comments have been shared with the team to ensure these concerns
are addressed and do not recur.

응답 번역

translated_response = translate(
    text=response,
    from_language="en",
    to_language="es"
)

print(translated_response)

Gracias por compartir sus comentarios. Si bien nos alegra saber que encontró conveniente
la ubicación, lamentamos sinceramente los inconvenientes que experimentó con el servicio.
Entendemos lo frustrante que debió haber sido enfrentar múltiples inconvenientes durante
su estadía. Sus comentarios han sido compartidos con el equipo para asegurarnos de que
estas situaciones se aborden y no vuelvan a ocurrir.

Cortex 비용 모델

입력 토큰, 컴퓨팅, 출력 토큰에 각각 비용이 발생하는 Cortex 워크플로

¹ ChatGPT-4o로 생성된 이미지

비용 제한

입력값 축소, 관련 텍스트만 처리
출력 크기 제한
temperature 값 낮추기

# Limit cost of complete
complete(prompt=prompt, 
         model='llama3.1-8b', 
         options={
            'max_tokens':120,

            'temperature':0})

Cortex 모범 사례

효과적으로 모델 체이닝

# Summarize first if calling multiple downstream functions
summarize()
text_classify()
complete()
translate()

로깅
캐싱
배치 파이프라인

연습해 봅시다!

Snowflake에서 시작하는 생성형 AI