LoginSignup
1
2

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

@leolui2013(LEO LUI)in株式会社Nint

関数型プログラミングからAIエージェント関数型プログラミング

Posted at

何を言いたい

Hugging Faceが開発されたAIエージェントsmolagentsの説明資料に、関数をツールと定義する使い方がこのように書いています。

from smolagents import CodeAgent, tool, HfApiModel

# Tool to suggest a menu based on the occasion
@tool
def suggest_menu(occasion: str) -> str:
    """
    Suggests a menu based on the occasion.
    Args:
        occasion: The type of occasion for the party.
    """
    if occasion == "casual":
        return "Pizza, snacks, and drinks."
    elif occasion == "formal":
        return "3-course dinner with wine and dessert."
    elif occasion == "superhero":
        return "Buffet with high-energy and healthy food."
    else:
        return "Custom menu for the butler."

# Alfred, the butler, preparing the menu for the party
agent = CodeAgent(tools=[suggest_menu], model=HfApiModel())

# Preparing the menu for the party
agent.run("Prepare a formal menu for the party.")

このような書き方は、ユーザープロンプトをAIで解析して、ほしい部分を抽出して、そのあとにソースコードを実行して結果を返します。

もっと抽象的に言いますと、このような感じです。

def 何らかの処理をしたい(ユーザープロンプトから関数のインプットを抽出):
    """
    処理の説明文
    """
    
    実際の処理コード
    
    return 結果

もう1ステップ行けたら

上記のロジックは普通のAIエージェントだと思うけど、それもあくまでプロンプトの解析だけなので、実際の処理コードも開発者が書かないといけないです。

でしたら、AIの方でソースコードを生成するのは無理ですか？

自動化じゃだめなんですか

def 何らかの処理をしたい(ユーザープロンプトから関数のインプットを抽出):
    """
    処理の説明文
    """
    
    実際の処理コード　←　つまり、ここもAIに任せる
    
    return 結果

1個の例をやってみましょう

こちらは説明資料に別のページで、同じくツールの定義だけど、実際の処理コードが長くて、人間で書くより、AIの方が早くて書けるかどうかを検証したいです。

import math
from typing import Optional, Tuple

from smolagents import tool


@tool
def calculate_cargo_travel_time(
    origin_coords: Tuple[float, float],
    destination_coords: Tuple[float, float],
    cruising_speed_kmh: Optional[float] = 750.0,  # Average speed for cargo planes
) -> float:
    """
    Calculate the travel time for a cargo plane between two points on Earth using great-circle distance.

    Args:
        origin_coords: Tuple of (latitude, longitude) for the starting point
        destination_coords: Tuple of (latitude, longitude) for the destination
        cruising_speed_kmh: Optional cruising speed in km/h (defaults to 750 km/h for typical cargo planes)

    Returns:
        float: The estimated travel time in hours

    Example:
        >>> # Chicago (41.8781° N, 87.6298° W) to Sydney (33.8688° S, 151.2093° E)
        >>> result = calculate_cargo_travel_time((41.8781, -87.6298), (-33.8688, 151.2093))
    """

    def to_radians(degrees: float) -> float:
        return degrees * (math.pi / 180)

    # Extract coordinates
    lat1, lon1 = map(to_radians, origin_coords)
    lat2, lon2 = map(to_radians, destination_coords)

    # Earth's radius in kilometers
    EARTH_RADIUS_KM = 6371.0

    # Calculate great-circle distance using the haversine formula
    dlon = lon2 - lon1
    dlat = lat2 - lat1

    a = (
        math.sin(dlat / 2) ** 2
        + math.cos(lat1) * math.cos(lat2) * math.sin(dlon / 2) ** 2
    )
    c = 2 * math.asin(math.sqrt(a))
    distance = EARTH_RADIUS_KM * c

    # Add 10% to account for non-direct routes and air traffic controls
    actual_distance = distance * 1.1

    # Calculate flight time
    # Add 1 hour for takeoff and landing procedures
    flight_time = (actual_distance / cruising_speed_kmh) + 1.0

    # Format the results
    return round(flight_time, 2)


print(calculate_cargo_travel_time((41.8781, -87.6298), (-33.8688, 151.2093)))

インプットプロンプト

インプットプロンプトには、処理のコードを削除して、要件だけ残します。

一番最後にソースコード生成を指示しました。

import math
from typing import Optional, Tuple

from smolagents import tool

@tool
def calculate_cargo_travel_time(
    origin_coords: Tuple[float, float],
    destination_coords: Tuple[float, float],
    cruising_speed_kmh: Optional[float] = 750.0,  # Average speed for cargo planes
) -> float:
    """
    Calculate the travel time for a cargo plane between two points on Earth using great-circle distance.

    Args:
        origin_coords: Tuple of (latitude, longitude) for the starting point
        destination_coords: Tuple of (latitude, longitude) for the destination
        cruising_speed_kmh: Optional cruising speed in km/h (defaults to 750 km/h for typical cargo planes)

    Returns:
        float: The estimated travel time in hours

    Example:
        >>> # Chicago (41.8781° N, 87.6298° W) to Sydney (33.8688° S, 151.2093° E)
        >>> result = calculate_cargo_travel_time((41.8781, -87.6298), (-33.8688, 151.2093))
    """

    ** GENERATE CODE HERE BASED ON THE FOLLOWING REQUIREMENTS **
    # Extract coordinates
    # Earth's radius in kilometers
    # Calculate great-circle distance using the haversine formula
    # Add 10% to account for non-direct routes and air traffic controls
    # Calculate flight time
    # Format the results

print(calculate_cargo_travel_time((41.8781, -87.6298), (-33.8688, 151.2093)))

Above is the function calculate_cargo_travel_time, please follow the requirements inside the function to fill in the code.

生成結果

Gemini 2.0 Proを使って、生成結果はこちらになります。

import math
from typing import Optional, Tuple

from smolagents import tool

@tool
def calculate_cargo_travel_time(
    origin_coords: Tuple[float, float],
    destination_coords: Tuple[float, float],
    cruising_speed_kmh: Optional[float] = 750.0,  # Average speed for cargo planes
) -> float:
    """
    Calculate the travel time for a cargo plane between two points on Earth using great-circle distance.

    Args:
        origin_coords: Tuple of (latitude, longitude) for the starting point
        destination_coords: Tuple of (latitude, longitude) for the destination
        cruising_speed_kmh: Optional cruising speed in km/h (defaults to 750 km/h for typical cargo planes)

    Returns:
        float: The estimated travel time in hours

    Example:
        >>> # Chicago (41.8781° N, 87.6298° W) to Sydney (33.8688° S, 151.2093° E)
        >>> result = calculate_cargo_travel_time((41.8781, -87.6298), (-33.8688, 151.2093))
    """

    # Extract coordinates
    lat1, lon1 = origin_coords
    lat2, lon2 = destination_coords

    # Earth's radius in kilometers
    R = 6371.0

    # Calculate great-circle distance using the haversine formula
    lat1_rad = math.radians(lat1)
    lon1_rad = math.radians(lon1)
    lat2_rad = math.radians(lat2)
    lon2_rad = math.radians(lon2)

    dlon = lon2_rad - lon1_rad
    dlat = lat2_rad - lat1_rad

    a = math.sin(dlat / 2)**2 + math.cos(lat1_rad) * math.cos(lat2_rad) * math.sin(dlon / 2)**2
    c = 2 * math.atan2(math.sqrt(a), math.sqrt(1 - a))

    distance_km = R * c

    # Add 10% to account for non-direct routes and air traffic controls
    distance_km *= 1.10

    # Calculate flight time
    flight_time_hours = distance_km / cruising_speed_kmh

    # Format the results
    return flight_time_hours

print(calculate_cargo_travel_time((41.8781, -87.6298), (-33.8688, 151.2093)))

計算結果は完璧だけど、最後の出力は要件定義が甘かったので、切り上げの処理はなかったですね。

結論

今まで関数型プログラミングの概念だったけど、生成AIによって、関数の中に要件定義をしっかりできたら、ソースコードを書くこともいらなくて、AIに任せればできってしまいますね。

1
2
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
Sign upLogin
1
2

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?