Vamos começar

Este guia ajuda você a começar a usar a API Gemini com a API Interactions. Você vai fazer sua primeira chamada de API em menos de um minuto e conhecer a geração de texto, a compreensão multimodal, a geração de imagens, a saída estruturada, as ferramentas, a chamada de função, os agentes e a execução em segundo plano.

A API Interactions está disponível nos SDKs Python e JavaScript, além de REST.

1. Gerar uma chave de API

Para usar a API Gemini, você precisa de uma chave de API. Crie uma conta sem custo financeiro para começar:

Criar uma chave da API Gemini

Em seguida, defina o ID como uma variável de ambiente:

export GEMINI_API_KEY="YOUR_API_KEY"

2. Instalar o SDK e fazer sua primeira chamada

Instale o SDK e gere texto com uma única chamada de API.

Python

Instale o SDK:

pip install -U google-genai

Inicialize o cliente e faça uma solicitação:

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Explain how AI works in a few words"
)
print(interaction.output_text)

JavaScript

Instale o SDK:

npm install @google/genai

Inicialize o cliente e faça uma solicitação:

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "Explain how AI works in a few words",
});
console.log(interaction.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "Explain how AI works in a few words"
  }'

Resposta:

{
  "id": "v1_ChdpQUFvYXI...",
  "status": "completed",
  "usage": {
    "total_tokens": 197,
    "total_input_tokens": 8,
    "total_output_tokens": 12
  },
  "created": "2026-06-09T12:01:25Z",
  "steps": [
    {
      "type": "thought",
      "signature": "EvEFCu4FAQw..."
    },
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "AI learns patterns from data, then uses those patterns to make predictions or decisions on new data."
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash",
}

Ao usar REST, a API retorna o recurso Interaction completo, que contém metadados, estatísticas de uso e o histórico detalhado da interação.

Embora os SDKs exponham a resposta completa, eles também oferecem propriedades convenientes, como interaction.output_text e interaction.output_image, para acessar os resultados finais diretamente. Saiba mais sobre a estrutura de resposta na Visão geral das interações ou leia o guia de geração de texto para detalhes sobre instruções do sistema e configuração de geração.

3. Mostrar composição da resposta

Para interações mais fluidas, transmita a resposta à medida que ela é gerada. Cada evento step.delta oferece um trecho de texto que pode ser mostrado imediatamente.

Python

from google import genai

client = genai.Client()

stream = client.interactions.create(
    model="gemini-3.5-flash",
    input="Explain how AI works",
    stream=True
)
for event in stream:
    print(event)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const stream = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "Explain how AI works",
  stream: true,
});

for await (const event of stream) {
  console.log(event);
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  --no-buffer \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "Explain how AI works",
    "stream": true
  }'

Ao transmitir, o servidor responde com um fluxo de eventos enviados pelo servidor (SSE). Cada evento inclui um tipo e dados JSON.

Resposta:

event: interaction.created
data: {"interaction":{"id":"v1_Chd...","status":"in_progress","model":"gemini-3.5-flash"},"event_type":"interaction.created"}

event: step.start
data: {"index":0,"step":{"type":"thought"},"event_type":"step.start"}

event: step.delta
data: {"index":0,"delta":{"signature":"EvEFCu4F...","type":"thought_signature"},"event_type":"step.delta"}

event: step.stop
data: {"index":0,"event_type":"step.stop"}

event: step.start
data: {"index":1,"step":{"type":"model_output"},"event_type":"step.start"}

event: step.delta
data: {"index":1,"delta":{"text":"AI ","type":"text"},"event_type":"step.delta"}

event: step.delta
data: {"index":1,"delta":{"text":"works ","type":"text"},"event_type":"step.delta"}

event: step.stop
data: {"index":1,"event_type":"step.stop"}

event: interaction.completed
data: {"interaction":{"id":"v1_Chd...","status":"completed","usage":{"total_tokens":197}},"event_type":"interaction.completed"}

Para uma análise detalhada sobre como processar eventos de streaming e tipos delta, consulte o guia de interações de streaming.

4. Conversas com vários turnos

A API Interactions é compatível com conversas multiturno de duas maneiras:

  • Com estado (recomendado): continue uma conversa no servidor usando previous_interaction_id. Ideal para a maioria dos fluxos de trabalho de chat e de agentes em que você quer que o servidor gerencie o histórico e otimize o armazenamento em cache.
  • Sem estado: gerencie o histórico da conversa no cliente transmitindo todas as interações anteriores (incluindo etapas de pensamento e ferramentas do modelo intermediário) em cada solicitação.

Encadeie interações transmitindo previous_interaction_id. O servidor gerencia todo o histórico de conversas para você.

Python

from google import genai

client = genai.Client()

# Server-side state (recommended)
interaction1 = client.interactions.create(
    model="gemini-3.5-flash",
    input="I have 2 dogs in my house.",
)
print("Response 1:", interaction1.output_text)

interaction2 = client.interactions.create(
    model="gemini-3.5-flash",
    input="How many paws are in my house?",
    previous_interaction_id=interaction1.id,
)
print("Response 2:", interaction2.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

// Server-side state (recommended)
const interaction1 = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "I have 2 dogs in my house.",
});
console.log("Response 1:", interaction1.output_text);

const interaction2 = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "How many paws are in my house?",
  previous_interaction_id: interaction1.id,
});
console.log("Response 2:", interaction2.output_text);

REST

RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "I have 2 dogs in my house."
  }')

INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')
echo "Interaction 1 ID: $INTERACTION_ID"

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'"
  }'

Sem estado

Defina store=false e gerencie o histórico de conversas no lado do cliente. Você precisa preservar e reenviar todas as etapas geradas pelo modelo (incluindo as etapas thought e function_call) exatamente como foram recebidas.

Python

from google import genai

client = genai.Client()

history = [
    {
        "type": "user_input",
        "content": [{"type": "text", "text": "I have 2 dogs in my house."}]
    }
]

interaction1 = client.interactions.create(
    model="gemini-3.5-flash",
    store=False,
    input=history
)
print("Response 1:", interaction1.steps[-1].content[0].text)

for step in interaction1.steps:
    history.append(step.model_dump())

history.append({
    "type": "user_input",
    "content": [{"type": "text", "text": "How many paws are in my house?"}]
})

interaction2 = client.interactions.create(
    model="gemini-3.5-flash",
    store=False,
    input=history
)
print("Response 2:", interaction2.steps[-1].content[0].text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const history = [
  {
    type: "user_input",
    content: [{ type: "text", text: "I have 2 dogs in my house." }]
  }
];

const interaction1 = await ai.interactions.create({
  model: "gemini-3.5-flash",
  store: false,
  input: history
});
console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

history.push(...interaction1.steps);

history.push({
  type: "user_input",
  content: [{ type: "text", text: "How many paws are in my house?" }]
});

const interaction2 = await ai.interactions.create({
  model: "gemini-3.5-flash",
  store: false,
  input: history
});
console.log("Response 2:", interaction2.steps.at(-1).content[0].text);

REST

# Turn 1: Send with store: false
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "store": false,
    "input": [
      {
        "type": "user_input",
        "content": "I have 2 dogs in my house."
      }
    ]
  }')

MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')

# Turn 2: Build full history
HISTORY=$(jq -n \
  --argjson first_input '[{"type": "user_input", "content": "I have 2 dogs in my house."}]' \
  --argjson model_steps "$MODEL_STEPS" \
  --argjson second_input '[{"type": "user_input", "content": "How many paws are in my house?"}]' \
  '$first_input + $model_steps + $second_input')

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"model\": \"gemini-3.5-flash\",
    \"store\": false,
    \"input\": $HISTORY
  }"

Resposta:

{
  "id": "v2_Chd...",
  "status": "completed",
  "usage": {
    "total_tokens": 240,
    "total_input_tokens": 60,
    "total_output_tokens": 20
  },
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "There are 8 paws in your house. 2 dogs \u00d7 4 paws = 8 paws."
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash"
}

A segunda interação retorna um objeto de resposta completo que inclui apenas as novas etapas, mas se baseia no contexto do turno anterior. Saiba mais sobre como manter o estado no guia de conversas multiturno ou confira o modo sem estado para gerenciamento do histórico do lado do cliente.

5. Compreensão multimodal

Os modelos do Gemini entendem imagens, áudio, vídeo e documentos de forma nativa. Transmita mídia e texto em uma única solicitação.

Python

import base64
from google import genai

client = genai.Client()

# Load a local image
with open("sample.jpg", "rb") as f:
    image_bytes = f.read()
image_b64 = base64.b64encode(image_bytes).decode("utf-8")

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input=[
        {"type": "text", "text": "Compare this local image and this remote audio file."},
        {
            "type": "image",
            "data": image_b64,
            "mime_type": "image/jpeg"
        },
        {
            "type": "audio",
            "uri": "https://storage.googleapis.com/generativeai-downloads/data/sample.mp3",
            "mime_type": "audio/mp3"
        }
    ]
)
print(interaction.output_text)

JavaScript

import fs from "fs";
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

// Load a local image
const imageBytes = fs.readFileSync("sample.jpg");
const imageB64 = imageBytes.toString("base64");

const interaction = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: [
    { type: "text", text: "Compare this local image and this remote audio file." },
    {
      type: "image",
      data: imageB64,
      mime_type: "image/jpeg"
    },
    {
      type: "audio",
      uri: "https://storage.googleapis.com/generativeai-downloads/data/sample.mp3",
      mime_type: "audio/mp3"
    }
  ],
});
console.log(interaction.output_text);

REST

# Base64-encode local image
BASE64_IMAGE=$(base64 -w 0 sample.jpg)

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions"   -H "x-goog-api-key: $GEMINI_API_KEY"   -H 'Content-Type: application/json'   -H "Api-Revision: 2026-05-20"   -d '{
    "model": "gemini-3.5-flash",
    "input": [
      {
        "type": "text",
        "text": "Compare this local image and this remote audio file."
      },
      {
        "type": "image",
        "data": "'$BASE64_IMAGE'",
        "mime_type": "image/jpeg"
      },
      {
        "type": "audio",
        "uri": "https://storage.googleapis.com/generativeai-downloads/data/sample.mp3",
        "mime_type": "audio/mp3"
      }
    ]
  }'

Resposta:

{
  "id": "v1_Chd...",
  "status": "completed",
  "usage": {
    "total_tokens": 300
  },
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "The local image displays a pipe organ while the remote audio file is a sample MP3 clip..."
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash",
}

Saiba como transmitir imagens, vídeos e arquivos de áudio no guia de compreensão de imagens.

6. Geração multimodal

O Gemini pode gerar imagens de forma nativa usando os modelos de imagem Nano Banana.

Python

import base64
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Generate an image of a futuristic city skyline at sunset",
)

with open("generated_image.png", "wb") as f:
    f.write(base64.b64decode(interaction.output_image.data))

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3.1-flash-image",
  input: "Generate an image of a futuristic city skyline at sunset",
});

const generatedImage = interaction.output_image;
if (generatedImage) {
  const buffer = Buffer.from(generatedImage.data, "base64");
  fs.writeFileSync("generated_image.png", buffer);
}

REST

curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Generate an image of a futuristic city skyline at sunset"}
    ]
  }'

Resposta:

{
  "id": "v1_Chd...",
  "status": "completed",
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "image",
          "data": "BASE64_ENCODED_IMAGE",
          "mime_type": "image/png"
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.1-flash-image",
}

Quando o modelo gera uma imagem, ele retorna os dados da imagem codificada em base64 em uma etapa na matriz steps, bem como pela propriedade de conveniência output_image. Confira o guia de geração de imagens para saber mais sobre proporções, edição de imagens e referências.

7. Usar saída estruturada

Configure o modelo para retornar um JSON que corresponda a um esquema definido por você. A saída estruturada funciona com Pydantic (Python) e Zod (JavaScript).

Python

from google import genai
from pydantic import BaseModel, Field
from typing import List, Optional

class Recipe(BaseModel):
    recipe_name: str = Field(description="Name of the recipe.")
    ingredients: List[str] = Field(description="List of ingredients.")
    prep_time_minutes: Optional[int] = Field(description="Prep time in minutes.")

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Give me a recipe for banana bread",
    response_format={
        "type": "text",
        "mime_type": "application/json",
        "schema": Recipe.model_json_schema()
    },
)

recipe = Recipe.model_validate_json(interaction.output_text)
print(recipe)

JavaScript

import { GoogleGenAI } from "@google/genai";
import * as z from "zod";

const ai = new GoogleGenAI({});

const recipeJsonSchema = {
  type: "object",
  properties: {
    recipe_name: { type: "string", description: "Name of the recipe." },
    ingredients: {
      type: "array",
      items: { type: "string" },
      description: "List of ingredients."
    },
    prep_time_minutes: {
      type: "integer",
      description: "Prep time in minutes."
    }
  },
  required: ["recipe_name", "ingredients"]
};

const recipeSchema = z.fromJSONSchema(recipeJsonSchema);

const interaction = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "Give me a recipe for banana bread",
  response_format: {
    type: "text",
    mime_type: "application/json",
    schema: recipeJsonSchema
  },
});

const recipe = recipeSchema.parse(JSON.parse(interaction.output_text));
console.log(recipe);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "Give me a recipe for banana bread",
    "response_format": {
      "type": "text",
      "mime_type": "application/json",
      "schema": {
        "type": "object",
        "properties": {
          "recipe_name": { "type": "string", "description": "Name of the recipe." },
          "ingredients": {
            "type": "array",
            "items": { "type": "string" },
            "description": "List of ingredients."
          },
          "prep_time_minutes": {
            "type": "integer",
            "description": "Prep time in minutes."
          }
        },
        "required": ["recipe_name", "ingredients"]
      }
    }
  }'

Resposta:

{
  "id": "v1_Chd...",
  "status": "completed",
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "{\n  \"recipe_name\": \"Classic Banana Bread\",\n  \"ingredients\": [\n    \"3 ripe bananas, mashed\",\n    \"1/3 cup melted butter\",\n    \"3/4 cup sugar\",\n    \"1 egg, beaten\",\n    \"1 teaspoon vanilla extract\",\n    \"1 teaspoon baking soda\",\n    \"Pinch of salt\",\n    \"1.5 cups all-purpose flour\"\n  ],\n  \"prep_time_minutes\": 15\n}"
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash",
}

O bloco de texto de saída contém uma string JSON válida que está exatamente de acordo com o esquema solicitado. Para saber como definir estruturas mais complexas e esquemas recursivos, consulte o guia de saída estruturada.

8. Usar ferramentas

Baseie a resposta do modelo em informações em tempo real com a Pesquisa Google. A API pesquisa, processa resultados e retorna citações automaticamente.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Who won the euro 2024?",
    tools=[{"type": "google_search"}]
)

print(interaction.output_text)

# Print citations
for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text" and content_block.annotations:
                print("\nCitations:")
                for annotation in content_block.annotations:
                    if annotation.type == "url_citation":
                        print(f"  [{annotation.title}]({annotation.url})")

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "Who won the euro 2024?",
  tools: [{ type: "google_search" }]
});

console.log(interaction.output_text);

// Print citations
for (const step of interaction.steps) {
  if (step.type === "model_output") {
    for (const contentBlock of step.content) {
      if (contentBlock.type === "text" && contentBlock.annotations) {
        console.log("\nCitations:");
        for (const annotation of contentBlock.annotations) {
          if (annotation.type === "url_citation") {
            console.log(`  [${annotation.title}](${annotation.url})`);
          }
        }
      }
    }
  }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "Who won the euro 2024?",
    "tools": [{"type": "google_search"}]
  }'

Resposta:

{
  "id": "v1_Chd...",
  "status": "completed",
  "steps": [
    {
      "type": "thought",
      "signature": "EvEFCu4F..."
    },
    {
      "type": "google_search_call",
      "arguments": {
        "queries": ["UEFA Euro 2024 winner"]
      }
    },
    {
      "type": "google_search_result",
      "call_id": "search_001",
      "result": [
        {
          "search_suggestions": "<!-- HTML and CSS search widget -->"
        }
      ]
    },
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "Spain won Euro 2024, defeating England 2-1 in the final.",
          "annotations": [
            {
              "type": "url_citation",
              "url": "https://www.uefa.com/euro2024",
              "title": "uefa.com",
              "start_index": 0,
              "end_index": 56
            }
          ]
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash",
}

As etapas de pesquisa são detalhadas no histórico de interações, e a saída final inclui citações inline que apontam para fontes da Web.

Saiba como extrair citações de pesquisa no guia de embasamento da Pesquisa Google ou veja como combinar várias ferramentas no guia de combinação de ferramentas.

9. Chamar suas próprias funções

Com a chamada de função, você pode conectar o modelo ao seu código. Você declara o nome e os parâmetros de uma função, o modelo decide quando chamar e retorna argumentos estruturados, e você executa localmente e envia o resultado de volta.

Python

import json
from google import genai

client = genai.Client()

weather_tool = {
    "type": "function",
    "name": "get_current_temperature",
    "description": "Gets the current temperature for a given location.",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "The city name, e.g. San Francisco",
            },
        },
        "required": ["location"],
    },
}

available_functions = {
    "get_current_temperature": lambda location: {
        "location": location, "temperature": "22", "unit": "celsius"
    },
}

user_input = "What is the temperature in London?"
previous_id = None

while True:
    interaction = client.interactions.create(
        model="gemini-3.5-flash",
        input=user_input,
        tools=[weather_tool],
        previous_interaction_id=previous_id,
    )

    function_results = []
    for step in interaction.steps:
        if step.type == "function_call":
            result = available_functions[step.name](**step.arguments)
            print(f"Called {step.name}({step.arguments}) → {result}")
            function_results.append({
                "type": "function_result",
                "name": step.name,
                "call_id": step.id,
                "result": [{"type": "text", "text": json.dumps(result)}],
            })

    if not function_results:
        break

    user_input = function_results
    previous_id = interaction.id

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const weatherTool = {
  type: "function",
  name: "get_current_temperature",
  description: "Gets the current temperature for a given location.",
  parameters: {
    type: "object",
    properties: {
      location: {
        type: "string",
        description: "The city name, e.g. San Francisco",
      },
    },
    required: ["location"],
  },
};

const availableFunctions = {
  get_current_temperature: ({ location }) => ({
    location, temperature: "22", unit: "celsius"
  }),
};

let input = "What is the temperature in London?";
let previousId = null;
let interaction;

while (true) {
  interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    input,
    tools: [weatherTool],
    previous_interaction_id: previousId,
  });

  const functionResults = [];
  for (const step of interaction.steps) {
    if (step.type === "function_call") {
      const result = availableFunctions[step.name](step.arguments);
      console.log(`Called ${step.name}(${JSON.stringify(step.arguments)}) →`, result);
      functionResults.push({
        type: "function_result",
        name: step.name,
        call_id: step.id,
        result: [{ type: "text", text: JSON.stringify(result) }],
      });
    }
  }

  if (functionResults.length === 0) break;

  input = functionResults;
  previousId = interaction.id;
}

console.log(interaction.output_text);

REST

# Turn 1: Send prompt with function declaration
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "What is the temperature in London?",
    "tools": [{
      "type": "function",
      "name": "get_current_temperature",
      "description": "Gets the current temperature for a given location.",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "The city name"}
        },
        "required": ["location"]
      }
    }]
  }')

INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')
FC_NAME=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .name')
FC_ID=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .id')
echo "Function: $FC_NAME, Call ID: $FC_ID"

# Turn 2: Send function result back
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "previous_interaction_id": "'$INTERACTION_ID'",
    "input": [{
      "type": "function_result",
      "name": "'$FC_NAME'",
      "call_id": "'$FC_ID'",
      "result": [{"type": "text", "text": "{\"location\": \"London\", \"temperature\": \"22\", \"unit\": \"celsius\"}"}]
    }],
    "tools": [{
      "type": "function",
      "name": "get_current_temperature",
      "description": "Gets the current temperature for a given location.",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "The city name"}
        },
        "required": ["location"]
      }
    }]
  }'

Sem estado

Também é possível usar a chamada de função no modo sem estado gerenciando o histórico de conversas no lado do cliente e definindo store=false. No modo sem estado, é necessário transmitir todo o histórico da conversa no campo input de cada solicitação subsequente. Esse histórico precisa incluir:

  1. A etapa inicial user_input.
  2. Todas as etapas geradas pelo modelo retornadas na rodada 1 (incluindo as etapas thought e function_call) exatamente como foram recebidas.
  3. A etapa function_result que contém a saída da função executada.

Python

import json
from google import genai

client = genai.Client()

weather_tool = {
    "type": "function",
    "name": "get_current_temperature",
    "description": "Gets the current temperature for a given location.",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "The city name, e.g. San Francisco",
            },
        },
        "required": ["location"],
    },
}

available_functions = {
    "get_current_temperature": lambda location: {
        "location": location, "temperature": "22", "unit": "celsius"
    },
}

history = [
    {
        "type": "user_input",
        "content": [{"type": "text", "text": "What is the temperature in London?"}]
    }
]

while True:
    interaction = client.interactions.create(
        model="gemini-3.5-flash",
        store=False,
        input=history,
        tools=[weather_tool],
    )

    function_results = []
    for step in interaction.steps:
        history.append(step.model_dump())
        if step.type == "function_call":
            result = available_functions[step.name](**step.arguments)
            print(f"Called {step.name}({step.arguments}) → {result}")
            fn_result = {
                "type": "function_result",
                "name": step.name,
                "call_id": step.id,
                "result": [{"type": "text", "text": json.dumps(result)}],
            }
            function_results.append(fn_result)
            history.append(fn_result)

    if not function_results:
        break

print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const weatherTool = {
  type: "function",
  name: "get_current_temperature",
  description: "Gets the current temperature for a given location.",
  parameters: {
    type: "object",
    properties: {
      location: {
        type: "string",
        description: "The city name, e.g. San Francisco",
      },
    },
    required: ["location"],
  },
};

const availableFunctions = {
  get_current_temperature: ({ location }) => ({
    location, temperature: "22", unit: "celsius"
  }),
};

const history = [
  {
    type: "user_input",
    content: [{ type: "text", text: "What is the temperature in London?" }]
  }
];

let interaction;

while (true) {
  interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    store: false,
    input: history,
    tools: [weatherTool],
  });

  const functionResults = [];
  for (const step of interaction.steps) {
    history.push(step);
    if (step.type === "function_call") {
      const result = availableFunctions[step.name](step.arguments);
      console.log(`Called ${step.name}(${JSON.stringify(step.arguments)}) →`, result);
      const fnResult = {
        type: "function_result",
        name: step.name,
        call_id: step.id,
        result: [{ type: "text", text: JSON.stringify(result) }],
      };
      functionResults.push(fnResult);
      history.push(fnResult);
    }
  }

  if (functionResults.length === 0) break;
}

console.log(interaction.output_text);

REST

# Turn 1: Send request with tools and store: false
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "store": false,
    "input": [
      {
        "type": "user_input",
        "content": "What is the temperature in London?"
      }
    ],
    "tools": [{
      "type": "function",
      "name": "get_current_temperature",
      "description": "Gets the current temperature for a given location.",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "The city name"}
        },
        "required": ["location"]
      }
    }]
  }')

# Extract model steps (thought, function_call)
MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')
FC_NAME=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .name')
FC_ID=$(echo "$RESPONSE1" | jq -r '.steps[] | select(.type=="function_call") | .id')
echo "Function: $FC_NAME, Call ID: $FC_ID"

# Assume local execution returns:
RESULT="{\"location\": \"London\", \"temperature\": \"22\", \"unit\": \"celsius\"}"

# Reconstruct history for Turn 2
HISTORY=$(jq -n \
  --argjson first_input '[{"type": "user_input", "content": "What is the temperature in London?"}]' \
  --argjson model_steps "$MODEL_STEPS" \
  --arg fc_name "$FC_NAME" \
  --arg fc_id "$FC_ID" \
  --arg result "$RESULT" \
  '$first_input + $model_steps + [{"type": "function_result", "name": $fc_name, "call_id": $fc_id, "result": [{"type": "text", "text": $result}]}]')

# Turn 2: Send the full history
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d "{
    \"model\": \"gemini-3.5-flash\",
    \"store\": false,
    \"input\": $HISTORY,
    \"tools\": [{
      \"type\": \"function\",
      \"name\": \"get_current_temperature\",
      \"description\": \"Gets the current temperature for a given location.\",
      \"parameters\": {
        \"type\": \"object\",
        \"properties\": {
          \"location\": {\"type\": \"string\", \"description\": \"The city name\"}
        },
        \"required\": [\"location\"]
      }
    }]
  }"

Resposta:

Durante a vez 1, o modelo retorna uma resposta com o status requires_action e a etapa function_call:

{
  "id": "v1_Chd...",
  "status": "requires_action",
  "steps": [
    {
      "type": "function_call",
      "id": "call_abc123",
      "name": "get_current_temperature",
      "arguments": {
        "location": "London"
      }
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash"
}

Depois de executar a função localmente e enviar o resultado (Turno 2), a interação final concluída retorna:

{
  "id": "v1_Chd...",
  "status": "completed",
  "steps": [
    {
      "type": "function_call",
      "id": "call_abc123",
      "name": "get_current_temperature",
      "arguments": {
        "location": "London"
      }
    },
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "The temperature in London is currently 22°C."
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash",
}

Para recursos avançados, como chamada de função paralela ou modos de escolha de função, consulte o guia de chamada de função.

10. Executar um agente gerenciado

Os agentes gerenciados são executados em um sandbox remoto com acesso a ferramentas como execução de código e gerenciamento de arquivos. Transmita um agent em vez de um model e defina environment="remote".

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
    environment="remote",
)
print(f"Environment: {interaction.environment_id}")
print(interaction.output_text)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  agent: "antigravity-preview-05-2026",
  input: "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
  environment: "remote",
});
console.log(`Environment: ${interaction.environment_id}`);
console.log(interaction.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "agent": "antigravity-preview-05-2026",
    "input": "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
    "environment": "remote"
  }'

Você também pode definir e salvar agentes personalizados com suas próprias instruções, habilidades e fontes de dados.

11. Executar tarefas em segundo plano

Defina background=True para executar tarefas longas de forma assíncrona. Pesquise os resultados com interactions.get().

Python

import time
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Write a detailed analysis of the impact of artificial intelligence on modern healthcare.",
    background=True,
)
print(f"Started background task: {interaction.id}")
print(f"Status: {interaction.status}")

# Poll for completion
while True:
    result = client.interactions.get(interaction.id)
    print(f"Status: {result.status}")
    if result.status == "completed":
        print(f"\nResult:\n{result.output_text}")
        break
    elif result.status == "failed":
        print(f"Failed: {result.error}")
        break
    time.sleep(5)

JavaScript

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

const interaction = await ai.interactions.create({
  model: "gemini-3.5-flash",
  input: "Write a detailed analysis of the impact of artificial intelligence on modern healthcare.",
  background: true,
});
console.log(`Started background task: ${interaction.id}`);
console.log(`Status: ${interaction.status}`);

// Poll for completion
while (true) {
  const result = await ai.interactions.get(interaction.id);
  console.log(`Status: ${result.status}`);
  if (result.status === "completed") {
    console.log(`\nResult:\n${result.output_text}`);
    break;
  } else if (result.status === "failed") {
    console.log(`Failed: ${result.error}`);
    break;
  }
  await new Promise(r => setTimeout(r, 5000));
}

REST

# Start a background task
RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.5-flash",
    "input": "Write a detailed analysis of the impact of artificial intelligence on modern healthcare.",
    "background": true
  }')

INTERACTION_ID=$(echo "$RESPONSE" | jq -r '.id')
echo "Started background task: $INTERACTION_ID"

# Poll for completion
while true; do
  RESULT=$(curl -s "https://generativelanguage.googleapis.com/v1beta/interactions/$INTERACTION_ID" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H "Api-Revision: 2026-05-20")
  STATUS=$(echo "$RESULT" | jq -r '.status')
  echo "Status: $STATUS"
  if [ "$STATUS" = "completed" ]; then
    echo "$RESULT" | jq -r '.steps[] | select(.type=="model_output") | .content[] | select(.type=="text") | .text'
    break
  elif [ "$STATUS" = "failed" ]; then
    echo "Failed"
    break
  fi
  sleep 5
done

Resposta:

A resposta inicial é retornada imediatamente com o status in_progress:

{
  "id": "v1_abc123",
  "status": "in_progress",
  "object": "interaction",
  "model": "gemini-3.5-flash"
}

Quando a tarefa em segundo plano é totalmente executada, a verificação do estado da interação retorna:

{
  "id": "v1_abc123",
  "status": "completed",
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "Artificial intelligence has transformed modern healthcare in several..."
        }
      ]
    }
  ],
  "object": "interaction",
  "model": "gemini-3.5-flash",
}

Leia sobre a execução assíncrona de modelos e agentes no guia de execução em segundo plano.

A seguir