함수 호출 참조

함수 호출은 관련성이 있는 상황별 답변을 제공하는 LLM 기능을 향상시킵니다.

Function Calling API를 사용하여 커스텀 함수를 생성형 AI 모델에 제공할 수 있습니다. 모델은 이러한 함수를 직접 호출하지 않지만 대신 함수 이름과 추천 인수를 지정하는 구조화된 데이터 출력을 생성합니다.

이 출력을 통해 외부 API 또는 정보 시스템(예: 데이터베이스, 고객 관계 관리 시스템, 문서 저장소)을 호출할 수 있습니다. LLM에서 응답 품질을 개선하는 데 결과 API 출력을 사용할 수 있습니다.

함수 호출에 대한 자세한 개념 문서는 함수 호출을 참조하세요.

지원되는 모델:

모델 버전
Gemini 1.5 Flash gemini-1.5-flash-002
gemini-1.5-flash-001
Gemini 1.5 Pro gemini-1.5-pro-002
gemini-1.5-pro-001
Gemini 1.0 Pro gemini-1.0-pro-001
gemini-1.0-pro-002

제한사항:

  • 요청에 제공할 수 있는 최대 함수 선언 수는 128개입니다.
  • FunctionCallingConfig.Mode.ANY는 Gemini 1.5 Pro 및 Gemini 1.5 Flash 모델에서만 사용 가능합니다.

예시 문법

함수 호출 API 요청을 보내는 문법입니다.

curl

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \

https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
-d '{
  "contents": [{
    ...
  }],
  "tools": [{
    "function_declarations": [
      {
        ...
      }
    ]
  }]
}'

Python

gemini_model = GenerativeModel(
    MODEL_ID,
    generation_config=generation_config,
    tools=[
        Tool(
            function_declarations=[
                FunctionDeclaration(
                    ...
                )
            ]
        )
    ],
)

매개변수 목록

구현 세부정보는 예시를 참고하세요.

FunctionDeclaration

OpenAPI 3.0 사양에 따라 모델에서 JSON 입력을 생성할 수 있는 함수를 정의합니다.

매개변수

name

string

호출하려는 함수의 이름입니다. 문자 또는 밑줄로 시작해야 하며 a~z, A~Z, 0~9이거나 밑줄과 대시를 포함해야 합니다(최대 64자 길이).

description

선택사항: string

함수 설명 및 용도입니다. 모델은 이를 사용하여 함수를 호출할지 여부와 방법을 결정합니다. 최상의 결과를 얻으려면 설명을 포함하는 것이 좋습니다.

parameters

선택사항: Schema

함수의 매개변수를 OpenAPI JSON 스키마 객체 형식: OpenAPI 3.0 사양으로 설명합니다.

response

(선택사항) Schema

OpenAPI JSON 스키마 객체 형식: OpenAPI 3.0 사양으로 함수의 출력을 설명합니다.

자세한 내용은 함수 호출을 참조하세요.

Schema

OpenAPI 3.0 스키마 사양에 따라 함수 호출에서 입력 및 출력 데이터의 형식을 정의합니다.

매개변수
유형

string

Enum. 데이터 유형입니다. 다음 중 하나여야 합니다.

  • STRING
  • INTEGER
  • BOOLEAN
  • NUMBER
  • ARRAY
  • OBJECT
description

(선택사항) string

데이터에 대한 설명입니다.

enum

(선택사항) string[]

enum 형식의 가능한 Type.STRING 요소 값입니다.

items

선택사항: Schema[]

Type.ARRAY 요소의 스키마

properties

(선택사항) Schema

Type.OBJECT 속성의 스키마

required

(선택사항) string[]

Type.OBJECT의 필수 속성입니다.

nullable

(선택사항) bool

값이 null인지 나타냅니다.

FunctionCallingConfig

FunctionCallingConfig는 모델의 동작을 제어하고 호출할 함수 유형을 결정합니다.

매개변수

mode

(선택사항) enum/string[]

  • AUTO: 기본 모델 동작입니다. 모델은 함수 호출 양식 또는 자연어 응답 양식으로 예측을 수행할 수 있습니다. 모델은 컨텍스트에 따라 사용할 양식을 결정합니다.
  • NONE: 모델이 함수 호출 형식으로 예측하지 않습니다.
  • ANY: 모델이 함수 호출만 예측하도록 제한됩니다. 이 모드는 '제어된 생성으로 함수 호출' 또는 '강제 함수 호출'이라고도 합니다.

allowed_function_names

선택사항: string[]

호출할 함수 이름입니다. modeANY인 경우에만 설정합니다. 함수 이름은 [FunctionDeclaration.name]과 일치해야 합니다. 모드를 ANY로 설정하면 모델이 제공된 함수 이름 세트에서 함수 호출을 예측합니다.

예시

함수 선언 보내기

다음 예시는 쿼리 및 함수 선언을 모델에 보내는 기본 예시입니다.

REST

요청 데이터를 사용하기 전에 다음을 바꿉니다.

  • PROJECT_ID: 프로젝트 ID입니다.
  • LOCATION: 요청을 처리하는 리전
  • MODEL_ID: 처리 중인 모델의 ID
  • ROLE: 메시지를 만드는 항목의 ID
  • TEXT: 모델에 전송할 프롬프트
  • NAME: 호출하려는 함수의 이름
  • DESCRIPTION: 함수 설명 및 용도
  • 다른 필드는 매개변수 목록 테이블을 참조하세요.

HTTP 메서드 및 URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent

JSON 요청 본문:

{
  "contents": [{
    "role": "ROLE",
    "parts": [{
      "text": "TEXT"
    }]
  }],
  "tools": [{
    "function_declarations": [
      {
        "name": "NAME",
        "description": "DESCRIPTION",
        "parameters": {
          "type": "TYPE",
          "properties": {
            "location": {
              "type": "TYPE",
              "description": "DESCRIPTION"
            }
          },
          "required": [
            "location"
          ]
        }
      }
    ]
  }]
}

요청을 보내려면 다음 옵션 중 하나를 선택합니다.

curl

요청 본문을 request.json 파일에 저장하고 다음 명령어를 실행합니다.

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent"

PowerShell

요청 본문을 request.json 파일에 저장하고 다음 명령어를 실행합니다.

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:generateContent" | Select-Object -Expand Content

curl 명령어 예시

PROJECT_ID=myproject
LOCATION=us-central1
MODEL_ID=gemini-1.0-pro-002

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{
        "text": "What is the weather in Boston?"
      }]
    }],
    "tools": [{
      "functionDeclarations": [
        {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616"
              }
            },
            "required": [
              "location"
            ]
          }
        }
      ]
    }]
  }'

Python

import vertexai
from vertexai.generative_models import (
    Content,
    FunctionDeclaration,
    GenerationConfig,
    GenerativeModel,
    Part,
    Tool,
)

# TODO(developer): Update & uncomment below line
# PROJECT_ID = "your-project-id"

# Initialize Vertex AI
vertexai.init(project=PROJECT_ID, location="us-central1")

# Initialize Gemini model
model = GenerativeModel("gemini-1.5-flash-002")

# Define the user's prompt in a Content object that we can reuse in model calls
user_prompt_content = Content(
    role="user",
    parts=[
        Part.from_text("What is the weather like in Boston?"),
    ],
)

# Specify a function declaration and parameters for an API request
function_name = "get_current_weather"
get_current_weather_func = FunctionDeclaration(
    name=function_name,
    description="Get the current weather in a given location",
    # Function parameters are specified in JSON schema format
    parameters={
        "type": "object",
        "properties": {"location": {"type": "string", "description": "Location"}},
    },
)

# Define a tool that includes the above get_current_weather_func
weather_tool = Tool(
    function_declarations=[get_current_weather_func],
)

# Send the prompt and instruct the model to generate content using the Tool that you just created
response = model.generate_content(
    user_prompt_content,
    generation_config=GenerationConfig(temperature=0),
    tools=[weather_tool],
)
function_call = response.candidates[0].function_calls[0]
print(function_call)

# Check the function name that the model responded with, and make an API call to an external system
if function_call.name == function_name:
    # Extract the arguments to use in your API call
    location = function_call.args["location"]  # noqa: F841

    # Here you can use your preferred method to make an API request to fetch the current weather, for example:
    # api_response = requests.post(weather_api_url, data={"location": location})

    # In this example, we'll use synthetic data to simulate a response payload from an external API
    api_response = """{ "location": "Boston, MA", "temperature": 38, "description": "Partly Cloudy",
                    "icon": "partly-cloudy", "humidity": 65, "wind": { "speed": 10, "direction": "NW" } }"""

# Return the API response to Gemini so it can generate a model response or request another function call
response = model.generate_content(
    [
        user_prompt_content,  # User prompt
        response.candidates[0].content,  # Function call response
        Content(
            parts=[
                Part.from_function_response(
                    name=function_name,
                    response={
                        "content": api_response,  # Return the API response to Gemini
                    },
                ),
            ],
        ),
    ],
    tools=[weather_tool],
)

# Get the model response
print(response.text)
# Example response:
# The weather in Boston is partly cloudy with a temperature of 38 degrees Fahrenheit.
# The humidity is 65% and the wind is blowing from the northwest at 10 mph.

Node.js

const {
  VertexAI,
  FunctionDeclarationSchemaType,
} = require('@google-cloud/vertexai');

const functionDeclarations = [
  {
    function_declarations: [
      {
        name: 'get_current_weather',
        description: 'get weather in a given location',
        parameters: {
          type: FunctionDeclarationSchemaType.OBJECT,
          properties: {
            location: {type: FunctionDeclarationSchemaType.STRING},
            unit: {
              type: FunctionDeclarationSchemaType.STRING,
              enum: ['celsius', 'fahrenheit'],
            },
          },
          required: ['location'],
        },
      },
    ],
  },
];

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function functionCallingBasic(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.5-flash-001'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  // Instantiate the model
  const generativeModel = vertexAI.preview.getGenerativeModel({
    model: model,
  });

  const request = {
    contents: [
      {role: 'user', parts: [{text: 'What is the weather in Boston?'}]},
    ],
    tools: functionDeclarations,
  };
  const result = await generativeModel.generateContent(request);
  console.log(JSON.stringify(result.response.candidates[0].content));
}

자바

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.Content;
import com.google.cloud.vertexai.api.FunctionDeclaration;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.api.Schema;
import com.google.cloud.vertexai.api.Tool;
import com.google.cloud.vertexai.api.Type;
import com.google.cloud.vertexai.generativeai.ChatSession;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;

public class FunctionCalling {
  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    String promptText = "What's the weather like in Paris?";

    whatsTheWeatherLike(projectId, location, modelName, promptText);
  }

  // A request involving the interaction with an external tool
  public static String whatsTheWeatherLike(String projectId, String location,
                                           String modelName, String promptText)
      throws IOException {
    // Initialize client that will be used to send requests.
    // This client only needs to be created once, and can be reused for multiple requests.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {

      FunctionDeclaration functionDeclaration = FunctionDeclaration.newBuilder()
          .setName("getCurrentWeather")
          .setDescription("Get the current weather in a given location")
          .setParameters(
              Schema.newBuilder()
                  .setType(Type.OBJECT)
                  .putProperties("location", Schema.newBuilder()
                      .setType(Type.STRING)
                      .setDescription("location")
                      .build()
                  )
                  .addRequired("location")
                  .build()
          )
          .build();

      System.out.println("Function declaration:");
      System.out.println(functionDeclaration);

      // Add the function to a "tool"
      Tool tool = Tool.newBuilder()
          .addFunctionDeclarations(functionDeclaration)
          .build();

      // Start a chat session from a model, with the use of the declared function.
      GenerativeModel model = new GenerativeModel(modelName, vertexAI)
          .withTools(Arrays.asList(tool));
      ChatSession chat = model.startChat();

      System.out.println(String.format("Ask the question: %s", promptText));
      GenerateContentResponse response = chat.sendMessage(promptText);

      // The model will most likely return a function call to the declared
      // function `getCurrentWeather` with "Paris" as the value for the
      // argument `location`.
      System.out.println("\nPrint response: ");
      System.out.println(ResponseHandler.getContent(response));

      // Provide an answer to the model so that it knows what the result
      // of a "function call" is.
      Content content =
          ContentMaker.fromMultiModalData(
              PartMaker.fromFunctionResponse(
                  "getCurrentWeather",
                  Collections.singletonMap("currentWeather", "sunny")));
      System.out.println("Provide the function response: ");
      System.out.println(content);
      response = chat.sendMessage(content);

      // See what the model replies now
      System.out.println("Print response: ");
      String finalAnswer = ResponseHandler.getText(response);
      System.out.println(finalAnswer);

      return finalAnswer;
    }
  }
}

Go

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

// functionCallsBasic opens a chat session and sends 2 messages to the model:
// - first, to convert a text into a structured function call request
// - second, to convert a structured function call response into natural language.
// Writes output of second call to w.
func functionCallsBasic(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	// Build an OpenAPI schema, in memory
	params := &genai.Schema{
		Type: genai.TypeObject,
		Properties: map[string]*genai.Schema{
			"location": {
				Type:        genai.TypeString,
				Description: "location",
			},
		},
	}
	fundecl := &genai.FunctionDeclaration{
		Name:        "getCurrentWeather",
		Description: "Get the current weather in a given location",
		Parameters:  params,
	}
	model.Tools = []*genai.Tool{
		{FunctionDeclarations: []*genai.FunctionDeclaration{fundecl}},
	}

	chat := model.StartChat()

	resp, err := chat.SendMessage(ctx, genai.Text("What's the weather like in Boston?"))
	if err != nil {
		return err
	}
	if len(resp.Candidates) == 0 ||
		len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	// The model has returned a function call to the declared function `getCurrentWeather`
	// with a value for the argument `location`.
	_, err = json.MarshalIndent(resp.Candidates[0].Content.Parts[0], "", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}

	// In this example, we'll use synthetic data to simulate a response payload from an external API
	weather := map[string]string{
		"location":    "Boston",
		"temperature": "38",
		"description": "Partly Cloudy",
		"icon":        "partly-cloudy",
		"humidity":    "65",
		"wind":        "{\"speed\": \"10\", \"direction\": \"NW\"}",
	}
	weather_json, _ := json.Marshal(weather)

	// Create a function call response, to simulate the result of a call to a
	// real service
	funresp := &genai.FunctionResponse{
		Name: "getCurrentWeather",
		Response: map[string]any{
			"currentWeather": weather_json,
		},
	}
	_, err = json.MarshalIndent(funresp, "", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}

	// And provide the function call response to the model
	resp, err = chat.SendMessage(ctx, funresp)
	if err != nil {
		return err
	}
	if len(resp.Candidates) == 0 ||
		len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	// The model has taken the function call response as input, and has
	// reformulated the response to the user.
	content, err := json.MarshalIndent(resp.Candidates[0].Content.Parts[0], "", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}

	fmt.Fprintf(w, "generated summary:\n%s\n", content)
	return nil
}

REST(OpenAI)

OpenAI 라이브러리를 사용하여 Function Calling API를 호출할 수 있습니다. 자세한 내용은 OpenAI 라이브러리를 사용하여 Vertex AI 모델 호출을 참조하세요.

요청 데이터를 사용하기 전에 다음을 바꿉니다.

  • PROJECT_ID: 프로젝트 ID입니다.
  • LOCATION: 요청을 처리하는 리전
  • MODEL_ID: 처리 중인 모델의 ID

HTTP 메서드 및 URL:

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

JSON 요청 본문:

{
  "model": "google/MODEL_ID",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather in Boston?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616"
            }
           },
          "required": ["location"]
        }
      }
    }
  ]
}

요청을 보내려면 다음 옵션 중 하나를 선택합니다.

curl

요청 본문을 request.json 파일에 저장하고 다음 명령어를 실행합니다.

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

PowerShell

요청 본문을 request.json 파일에 저장하고 다음 명령어를 실행합니다.

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python(OpenAI)

OpenAI 라이브러리를 사용하여 Function Calling API를 호출할 수 있습니다. 자세한 내용은 OpenAI 라이브러리를 사용하여 Vertex AI 모델 호출을 참조하세요.

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update & uncomment below line
# PROJECT_ID = "your-project-id"
location = "us-central1"

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# # OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616",
                    },
                },
                "required": ["location"],
            },
        },
    }
]

messages = []
messages.append(
    {
        "role": "system",
        "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.",
    }
)
messages.append({"role": "user", "content": "What is the weather in Boston?"})

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-001",
    messages=messages,
    tools=tools,
)

print("Function:", response.choices[0].message.tool_calls[0].id)
print("Arguments:", response.choices[0].message.tool_calls[0].function.arguments)
# Example response:
# Function: get_current_weather
# Arguments: {"location":"Boston"}

FunctionCallingConfig를 사용하여 함수 선언 전송

다음 예시에서는 FunctionCallingConfig를 모델에 전달하는 방법을 보여줍니다.

functionCallingConfig는 모델 출력이 항상 특정 함수 호출이 되도록 확인합니다. 구성 방법:

  • 호출 함수 modeANY로 설정합니다.
  • allowed_function_names에 사용할 함수 이름을 지정합니다. allowed_function_names가 비어 있으면 제공된 함수 중 하나가 반환될 수 있습니다.

REST

PROJECT_ID=myproject
LOCATION=us-central1
MODEL_ID=gemini-1.5-pro-001

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{
        "text": "Do you have the White Pixel 8 Pro 128GB in stock in the US?"
      }]
    }],
    "tools": [{
      "functionDeclarations": [
        {
          "name": "get_product_sku",
          "description": "Get the available inventory for a Google products, e.g: Pixel phones, Pixel Watches, Google Home etc",
          "parameters": {
            "type": "object",
            "properties": {
              "product_name": {"type": "string", "description": "Product name"}
            }
          }
        },
        {
          "name": "get_store_location",
          "description": "Get the location of the closest store",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {"type": "string", "description": "Location"}
            },
          }
        }
      ]
    }],
    "toolConfig": {
        "functionCallingConfig": {
            "mode":"ANY",
            "allowedFunctionNames": ["get_product_sku"]
      }
    },
    "generationConfig": {
      "temperature": 0.95,
      "topP": 1.0,
      "maxOutputTokens": 8192
    }
  }'

Python

import vertexai
from vertexai.preview.generative_models import (
    FunctionDeclaration,
    GenerativeModel,
    Tool,
    ToolConfig,
)

# TODO(developer): Update & uncomment below line
# PROJECT_ID = "your-project-id"

# Initialize Vertex AI
vertexai.init(project=PROJECT_ID, location="us-central1")

# Specify a function declaration and parameters for an API request
get_product_sku_func = FunctionDeclaration(
    name="get_product_sku",
    description="Get the available inventory for a Google products, e.g: Pixel phones, Pixel Watches, Google Home etc",
    # Function parameters are specified in JSON schema format
    parameters={
        "type": "object",
        "properties": {
            "product_name": {"type": "string", "description": "Product name"}
        },
    },
)

# Specify another function declaration and parameters for an API request
get_store_location_func = FunctionDeclaration(
    name="get_store_location",
    description="Get the location of the closest store",
    # Function parameters are specified in JSON schema format
    parameters={
        "type": "object",
        "properties": {"location": {"type": "string", "description": "Location"}},
    },
)

# Define a tool that includes the above functions
retail_tool = Tool(
    function_declarations=[
        get_product_sku_func,
        get_store_location_func,
    ],
)

# Define a tool config for the above functions
retail_tool_config = ToolConfig(
    function_calling_config=ToolConfig.FunctionCallingConfig(
        # ANY mode forces the model to predict a function call
        mode=ToolConfig.FunctionCallingConfig.Mode.ANY,
        # List of functions that can be returned when the mode is ANY.
        # If the list is empty, any declared function can be returned.
        allowed_function_names=["get_product_sku"],
    )
)

model = GenerativeModel(
    model_name="gemini-1.5-flash-002",
    tools=[retail_tool],
    tool_config=retail_tool_config,
)
response = model.generate_content(
    "Do you have the Pixel 8 Pro 128GB in stock?",
)

print(response.candidates[0].function_calls)
# Example response:
# [
# name: "get_product_sku"
# args {
#   fields { key: "product_name" value { string_value: "Pixel 8 Pro 128GB" }}
#   }
# ]

Node.js

const {
  VertexAI,
  FunctionDeclarationSchemaType,
} = require('@google-cloud/vertexai');

const functionDeclarations = [
  {
    function_declarations: [
      {
        name: 'get_product_sku',
        description:
          'Get the available inventory for a Google products, e.g: Pixel phones, Pixel Watches, Google Home etc',
        parameters: {
          type: FunctionDeclarationSchemaType.OBJECT,
          properties: {
            productName: {type: FunctionDeclarationSchemaType.STRING},
          },
        },
      },
      {
        name: 'get_store_location',
        description: 'Get the location of the closest store',
        parameters: {
          type: FunctionDeclarationSchemaType.OBJECT,
          properties: {
            location: {type: FunctionDeclarationSchemaType.STRING},
          },
        },
      },
    ],
  },
];

const toolConfig = {
  function_calling_config: {
    mode: 'ANY',
    allowed_function_names: ['get_product_sku'],
  },
};

const generationConfig = {
  temperature: 0.95,
  topP: 1.0,
  maxOutputTokens: 8192,
};

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function functionCallingAdvanced(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.5-flash-001'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  // Instantiate the model
  const generativeModel = vertexAI.preview.getGenerativeModel({
    model: model,
  });

  const request = {
    contents: [
      {
        role: 'user',
        parts: [
          {text: 'Do you have the White Pixel 8 Pro 128GB in stock in the US?'},
        ],
      },
    ],
    tools: functionDeclarations,
    tool_config: toolConfig,
    generation_config: generationConfig,
  };
  const result = await generativeModel.generateContent(request);
  console.log(JSON.stringify(result.response.candidates[0].content));
}

Go

import (
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

// functionCallsChat opens a chat session and sends 4 messages to the model:
// - convert a first text question into a structured function call request
// - convert the first structured function call response into natural language
// - convert a second text question into a structured function call request
// - convert the second structured function call response into natural language
func functionCallsChat(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	// Build an OpenAPI schema, in memory
	paramsProduct := &genai.Schema{
		Type: genai.TypeObject,
		Properties: map[string]*genai.Schema{
			"productName": {
				Type:        genai.TypeString,
				Description: "Product name",
			},
		},
	}
	fundeclProductInfo := &genai.FunctionDeclaration{
		Name:        "getProductSku",
		Description: "Get the SKU for a product",
		Parameters:  paramsProduct,
	}
	paramsStore := &genai.Schema{
		Type: genai.TypeObject,
		Properties: map[string]*genai.Schema{
			"location": {
				Type:        genai.TypeString,
				Description: "Location",
			},
		},
	}
	fundeclStoreLocation := &genai.FunctionDeclaration{
		Name:        "getStoreLocation",
		Description: "Get the location of the closest store",
		Parameters:  paramsStore,
	}
	model.Tools = []*genai.Tool{
		{FunctionDeclarations: []*genai.FunctionDeclaration{
			fundeclProductInfo,
			fundeclStoreLocation,
		}},
	}
	model.SetTemperature(0.0)

	chat := model.StartChat()

	// Send a prompt for the first conversation turn that should invoke the getProductSku function
	prompt := "Do you have the Pixel 8 Pro in stock?"
	fmt.Fprintf(w, "Question: %s\n", prompt)
	resp, err := chat.SendMessage(ctx, genai.Text(prompt))
	if err != nil {
		return err
	}
	if len(resp.Candidates) == 0 ||
		len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	// The model has returned a function call to the declared function `getProductSku`
	// with a value for the argument `productName`.
	jsondata, err := json.MarshalIndent(resp.Candidates[0].Content.Parts[0], "\t", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintf(w, "function call generated by the model:\n\t%s\n", string(jsondata))

	// Create a function call response, to simulate the result of a call to a
	// real service
	funresp := &genai.FunctionResponse{
		Name: "getProductSku",
		Response: map[string]any{
			"sku":      "GA04834-US",
			"in_stock": "yes",
		},
	}
	jsondata, err = json.MarshalIndent(funresp, "\t", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintf(w, "function call response sent to the model:\n\t%s\n\n", string(jsondata))

	// And provide the function call response to the model
	resp, err = chat.SendMessage(ctx, funresp)
	if err != nil {
		return err
	}
	if len(resp.Candidates) == 0 ||
		len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	// The model has taken the function call response as input, and has
	// reformulated the response to the user.
	jsondata, err = json.MarshalIndent(resp.Candidates[0].Content.Parts[0], "\t", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintf(w, "Answer generated by the model:\n\t%s\n\n", string(jsondata))

	// Send a prompt for the second conversation turn that should invoke the getStoreLocation function
	prompt2 := "Is there a store in Mountain View, CA that I can visit to try it out?"
	fmt.Fprintf(w, "Question: %s\n", prompt)

	resp, err = chat.SendMessage(ctx, genai.Text(prompt2))
	if err != nil {
		return err
	}
	if len(resp.Candidates) == 0 ||
		len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	// The model has returned a function call to the declared function `getStoreLocation`
	// with a value for the argument `store`.
	jsondata, err = json.MarshalIndent(resp.Candidates[0].Content.Parts[0], "\t", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintf(w, "function call generated by the model:\n\t%s\n", string(jsondata))

	// Create a function call response, to simulate the result of a call to a
	// real service
	funresp = &genai.FunctionResponse{
		Name: "getStoreLocation",
		Response: map[string]any{
			"store": "2000 N Shoreline Blvd, Mountain View, CA 94043, US",
		},
	}
	jsondata, err = json.MarshalIndent(funresp, "\t", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintf(w, "function call response sent to the model:\n\t%s\n\n", string(jsondata))

	// And provide the function call response to the model
	resp, err = chat.SendMessage(ctx, funresp)
	if err != nil {
		return err
	}
	if len(resp.Candidates) == 0 ||
		len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	// The model has taken the function call response as input, and has
	// reformulated the response to the user.
	jsondata, err = json.MarshalIndent(resp.Candidates[0].Content.Parts[0], "\t", "  ")
	if err != nil {
		return fmt.Errorf("json.MarshalIndent: %w", err)
	}
	fmt.Fprintf(w, "Answer generated by the model:\n\t%s\n\n", string(jsondata))
	return nil
}

REST(OpenAI)

OpenAI 라이브러리를 사용하여 Function Calling API를 호출할 수 있습니다. 자세한 내용은 OpenAI 라이브러리를 사용하여 Vertex AI 모델 호출을 참조하세요.

요청 데이터를 사용하기 전에 다음을 바꿉니다.

  • PROJECT_ID: 프로젝트 ID입니다.
  • LOCATION: 요청을 처리하는 리전
  • MODEL_ID: 처리 중인 모델의 ID

HTTP 메서드 및 URL:

POST https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions

JSON 요청 본문:

{
  "model": "google/MODEL_ID",
  "messages": [
  {
    "role": "user",
    "content": "What is the weather in Boston?"
  }
],
"tools": [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "OBJECT",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616"
          }
         },
        "required": ["location"]
      }
    }
  }
],
"tool_choice": "auto"
}

요청을 보내려면 다음 옵션 중 하나를 선택합니다.

curl

요청 본문을 request.json 파일에 저장하고 다음 명령어를 실행합니다.

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions"

PowerShell

요청 본문을 request.json 파일에 저장하고 다음 명령어를 실행합니다.

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python(OpenAI)

OpenAI 라이브러리를 사용하여 Function Calling API를 호출할 수 있습니다. 자세한 내용은 OpenAI 라이브러리를 사용하여 Vertex AI 모델 호출을 참조하세요.

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update & uncomment below line
# PROJECT_ID = "your-project-id"
location = "us-central1"

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616",
                    },
                },
                "required": ["location"],
            },
        },
    }
]

messages = []
messages.append(
    {
        "role": "system",
        "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.",
    }
)
messages.append({"role": "user", "content": "What is the weather in Boston?"})

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=messages,
    tools=tools,
    tool_choice="auto",
)

print("Function:", response.choices[0].message.tool_calls[0].id)
print("Arguments:", response.choices[0].message.tool_calls[0].function.arguments)
# Example response:
# Function: get_current_weather
# Arguments: {"location":"Boston"}

다음 단계

자세한 문서는 다음을 참조하세요.