Referência de chamada de função

A chamada de funções melhora a capacidade dos LLMs de fornecer respostas relevantes e contextuais.

É possível apresentar funções personalizadas para um modelo de IA generativa com a API de chamada de função. O modelo não invoca diretamente essas funções, mas gera uma saída de dados estruturados que especifica o nome da função e os argumentos sugeridos.

Essa saída permite chamar APIs ou sistemas de informação externos, como bancos de dados, sistemas de gestão de relacionamento com o cliente e repositórios de documentos. A saída da API resultante pode ser usada pelo LLM para melhorar a qualidade da resposta.

Para ver mais documentos conceituais sobre chamadas de funções, consulte Como chamar de funções.

Modelos com suporte:

Modelo Versão
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

Limitações:

  • O número máximo de declarações de função que podem ser fornecidas com a solicitação é 128.
  • O FunctionCallingConfig.Mode.ANY está disponível apenas nos modelos Gemini 1.5 Pro e Gemini 1.5 Flash.

Exemplo de sintaxe

Sintaxe para enviar uma solicitação de API de chamada de função.

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(
                    ...
                )
            ]
        )
    ],
)

Lista de parâmetros

Confira exemplos para detalhes de implementação.

FunctionDeclaration

Define uma função em que o modelo pode gerar entradas JSON com base nas especificações da OpenAPI 3.0.

Parâmetros

name

string

O nome da função a ser chamada. Precisa começar com uma letra ou um sublinhado. Precisa ser az, AZ, 0-9 ou conter sublinhados, pontos ou traços, com um tamanho máximo de 64.

description

Opcional: string

A descrição e o propósito da função. O modelo usa isso para decidir como e se a função será chamada. Para melhores resultados, recomendamos incluir uma descrição.

parameters

Opcional: Schema

Descreve os parâmetros da função no formato de objeto de esquema JSON da OpenAPI: especificação OpenAPI 3.0.

response

Opcional: Schema

Descreve a saída da função no formato de objeto de esquema JSON da OpenAPI: especificação OpenAPI 3.0.

Para mais informações, consulte Chamada de função.

Schema

Define o formato dos dados de entrada e saída em uma chamada de função com base na especificação do Esquema da OpenAPI 3.0.

Parâmetros
tipo

string

enumerado. O tipo dos dados. Precisa ser um dos:

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

Opcional: string

Descrição dos dados.

enum

Opcional: string[]

Valores possíveis do elemento de tipo primitivo com formato de tipo enumerado.

items

Opcional: Schema[]

Esquema dos elementos de Type.ARRAY

properties

Opcional: Schema

Esquema das propriedades de Type.OBJECT

required

Opcional: string[]

Propriedades obrigatórias de Type.OBJECT.

nullable

Opcional: bool

Indica se o valor pode ser null.

FunctionCallingConfig

O FunctionCallingConfig controla o comportamento do modelo e determina que tipo de função chamar.

Parâmetros

mode

Opcional: enum/string[]

  • AUTO: comportamento do modelo padrão. O modelo pode fazer previsões em um formulário de chamada de função ou de resposta de linguagem natural. O modelo decide qual formulário usar com base no contexto.
  • NONE: o modelo não faz previsões na forma de chamadas de função.
  • ANY: o modelo é restrito a sempre prever uma chamada de função. Se allowed_function_names não for fornecido, o modelo vai escolher entre todas as declarações de função disponíveis. Se allowed_function_names for fornecido, o modelo vai escolher entre o conjunto de funções permitidas.

allowed_function_names

Opcional: string[]

Nomes de funções a serem chamadas. Definido apenas quando mode é ANY. Os nomes das funções precisam corresponder a [FunctionDeclaration.name]. Com o modo definido como ANY, o modelo prevê uma chamada de função do conjunto de nomes de função fornecido.

Exemplos

Enviar uma declaração de função

O exemplo a seguir é um exemplo básico de envio de uma consulta e uma declaração de função ao modelo.

REST

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • PROJECT_ID: o ID do projeto.
  • LOCATION: a região para processar a solicitação.
  • MODEL_ID: o ID do modelo que está sendo processado.
  • ROLE: a identidade da entidade que cria a mensagem.
  • TEXT: o comando a ser enviado para o modelo.
  • NAME: o nome da função a ser chamada.
  • DESCRIPTION: descrição e propósito da função.
  • Para outros campos, consulte a tabela Lista de parâmetros.

Método HTTP e URL:

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

Corpo JSON da solicitação:

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

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo com o nome request.json e execute o comando a seguir:

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

Salve o corpo da solicitação em um arquivo com o nome request.json e execute o comando a seguir:

$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

Exemplo de comando curl

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));
}

Java

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"
)

// functionCalling demonstrates how to submit a prompt and a function declaration to the model,
// allowing it to suggest a call to the function to fetch external data. Returning this data
// to the model enables it to generate a text response that incorporates the data.
func functionCalling(w io.Writer, projectID, location, modelName string) error {
	// location = "us-central1"
	// modelName = "gemini-1.5-flash-002"
	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("failed to create GenAI client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)
	// Set temperature to 0.0 for maximum determinism in function calling.
	model.SetTemperature(0.0)

	funcName := "getCurrentWeather"
	funcDecl := &genai.FunctionDeclaration{
		Name:        funcName,
		Description: "Get the current weather in a given location",
		Parameters: &genai.Schema{
			Type: genai.TypeObject,
			Properties: map[string]*genai.Schema{
				"location": {
					Type:        genai.TypeString,
					Description: "location",
				},
			},
			Required: []string{"location"},
		},
	}
	// Add the weather function to our model toolbox.
	model.Tools = []*genai.Tool{
		{
			FunctionDeclarations: []*genai.FunctionDeclaration{funcDecl},
		},
	}

	prompt := genai.Text("What's the weather like in Boston?")
	resp, err := model.GenerateContent(ctx, prompt)

	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}
	if len(resp.Candidates) == 0 {
		return errors.New("got empty response from model")
	} else if len(resp.Candidates[0].FunctionCalls()) == 0 {
		return errors.New("got no function call suggestions from model")
	}

	// In a production environment, consider adding validations for function names and arguments.
	for _, fnCall := range resp.Candidates[0].FunctionCalls() {
		fmt.Fprintf(w, "The model suggests to call the function %q with args: %v\n", fnCall.Name, fnCall.Args)
		// Example response:
		// The model suggests to call the function "getCurrentWeather" with args: map[location:Boston]
	}
	// Use synthetic data to simulate a response from the external API.
	// In a real application, this would come from an actual weather API.
	mockAPIResp, err := json.Marshal(map[string]string{
		"location":         "Boston",
		"temperature":      "38",
		"temperature_unit": "F",
		"description":      "Cold and cloudy",
		"humidity":         "65",
		"wind":             `{"speed": "10", "direction": "NW"}`,
	})
	if err != nil {
		return fmt.Errorf("failed to marshal function response to JSON: %w", err)
	}

	funcResp := &genai.FunctionResponse{
		Name: funcName,
		Response: map[string]any{
			"content": mockAPIResp,
		},
	}

	// Return the API response to the model allowing it to complete its response.
	resp, err = model.GenerateContent(ctx, prompt, funcResp)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}
	if len(resp.Candidates) == 0 || len(resp.Candidates[0].Content.Parts) == 0 {
		return errors.New("got empty response from model")
	}

	fmt.Fprintln(w, resp.Candidates[0].Content.Parts[0])
	// Example response:
	// The weather in Boston is cold and cloudy, with a humidity of 65% and a temperature of 38°F. ...

	return nil
}

REST (OpenAI)

É possível chamar a API Function Calling usando a biblioteca OpenAI. Para mais informações, consulte Chamar modelos da Vertex AI usando a biblioteca OpenAI.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • PROJECT_ID: o ID do projeto.
  • LOCATION: a região para processar a solicitação.
  • MODEL_ID: o ID do modelo que está sendo processado.

Método HTTP e URL:

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

Corpo JSON da solicitação:

{
  "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"]
        }
      }
    }
  ]
}

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo com o nome request.json e execute o comando a seguir:

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

Salve o corpo da solicitação em um arquivo com o nome request.json e execute o comando a seguir:

$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)

É possível chamar a API Function Calling usando a biblioteca OpenAI. Para mais informações, consulte Chamar modelos da Vertex AI usando a biblioteca OpenAI.

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"}

Enviar uma declaração de função com FunctionCallingConfig

O exemplo abaixo demonstra como transmitir um FunctionCallingConfig. ao modelo.

O functionCallingConfig garante que a saída do modelo seja sempre um chamada de função específica. Para configurar:

  • Defina a função que chama mode como ANY.
  • Especifique os nomes das funções que você quer usar em allowed_function_names. Se allowed_function_names estiver vazio, qualquer uma das funções fornecidas podem ser retornados.

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)

É possível chamar a API Function Calling usando a biblioteca OpenAI. Para mais informações, consulte Chamar modelos da Vertex AI usando a biblioteca OpenAI.

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • PROJECT_ID: o ID do projeto.
  • LOCATION: a região para processar a solicitação.
  • MODEL_ID: o ID do modelo que está sendo processado.

Método HTTP e URL:

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

Corpo JSON da solicitação:

{
  "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"
}

Para enviar a solicitação, escolha uma destas opções:

curl

Salve o corpo da solicitação em um arquivo com o nome request.json e execute o comando a seguir:

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

Salve o corpo da solicitação em um arquivo com o nome request.json e execute o comando a seguir:

$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)

É possível chamar a API Function Calling usando a biblioteca OpenAI. Para mais informações, consulte Chamar modelos da Vertex AI usando a biblioteca OpenAI.

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, MA?"})

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"}

A seguir

Para consultar a documentação detalhada, acesse: