マルチステップ AI ワークフローの設計

Snowflake による Generative AI 入門

James Cha-Earley

Senior Developer Advocate, Snowflake

Cortex レビューワークフロー

目標: 海外ゲストのフィードバックを自動処理するシステムを構築

各レビューを英語に翻訳する
要点を要約する
適切なチームに振り分けるため分類する
返信を生成する
元の言語に翻訳し直す

レビューを受信し、翻訳、要約、分類してから返信を送信するワークフロー

レビューの抽出

-- 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]

スペイン語のレビュー

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

翻訳

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.

要約

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"
}

テキスト生成

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.

返信の翻訳

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 のコストモデル

入力トークン、計算処理、出力トークンにそれぞれコストがかかることを示す Cortex ワークフロー

¹ 画像生成: ChatGPT-4o

コストを抑える

入力を絞り込み、関連するテキストのみを処理する
出力サイズを制限する
temperature を下げる

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

            'temperature':0})

Cortex 利用の推奨手法

モデルを効果的に連結する

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

ロギング
キャッシング
バッチパイプライン

練習しましょう！

Snowflake による Generative AI 入門