設計多步驟 AI 工作流程

Snowflake 生成式 AI 入門

James Cha-Earley

Senior Developer Advocate, Snowflake

Cortex 評論流程

目標：建立國際旅客回饋的自動化系統

將每則評論翻譯成英文
摘要重點
分類並指派給正確團隊
產生回覆
再翻回原始語言

工作流程：接收評論、翻譯、摘要與分類，並送出回覆

擷取評論

-- 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]

西班牙文評論

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

翻譯

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.

摘要

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.

分類

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

print(topic)

{
  "label": "staff"
}

文字生成

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.

回覆翻譯

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 成本模型

一個 Cortex 成本模型：輸入 token、計算與輸出 token 皆有成本

¹ Image generated by ChatGPT-4o

降低成本

精簡輸入，只處理相關文字
限制輸出長度
降低 temperature

# 限制 complete 的成本
complete(prompt=prompt, 
         model='llama3.1-8b', 
         options={
            'max_tokens':120,

            'temperature':0})

Cortex 最佳實務

有效串接模型

# 若要呼叫多個後續函式，先做摘要
summarize()
text_classify()
complete()
translate()

紀錄
快取
批次管線

一起來練習吧！

Snowflake 生成式 AI 入門