Migrer vers l'API Interactions

Ce guide vous aide à migrer de l'API generateContent vers l'API Interactions.

L'API Interactions est l'interface standard pour créer des applications avec Gemini. Il est optimisé pour les workflows agentiques, la gestion de l'état côté serveur et les conversations multitours multimodales complexes, tout en prenant toujours en charge les requêtes monotours simples sans état. Bien que generateContent reste entièrement compatible, nous recommandons l'API Interactions pour tout nouveau développement.

Pourquoi migrer ?

L'API Interactions offre une façon plus structurée et plus puissante de créer des applications avec Gemini :

  • Gestion de l'historique côté serveur : simplifiez les flux multitours avec previous_interaction_id. Le serveur active l'état par défaut (store=true), mais vous pouvez choisir un comportement sans état en définissant store=false.
  • Étapes d'exécution observables : les étapes typées facilitent le débogage des flux complexes et le rendu de l'UI pour les événements intermédiaires (comme les réflexions ou les widgets de recherche).
  • Conçu pour les workflows agentiques : prise en charge native de l'utilisation d'outils en plusieurs étapes, de l'orchestration et des flux de raisonnement complexes grâce à des étapes d'exécution typées.
  • Tâches longues et en arrière-plan : permet de décharger les opérations gourmandes en temps, comme Deep Think et Deep Research, vers des processus en arrière-plan à l'aide de background=true.
  • Accès à de nouveaux modèles et capacités : à l'avenir, les nouveaux modèles au-delà de la famille principale, ainsi que les nouvelles capacités agentiques et les nouveaux outils, seront lancés exclusivement sur l'API Interactions. generateContent continuera d'être entièrement compatible avec les cas d'utilisation existants.

Entrée/Sortie de base

Cette section explique comment migrer une simple requête de génération de texte.

Avant (generateContent)

L'API generateContent est sans état et renvoie directement la réponse. La structure de réponse encapsule la sortie dans une liste de candidates, chacune contenant content avec une liste de parts à analyser.

Python

from google import genai

client = genai.Client()

response = client.models.generate_content(
    model="gemini-2.5-flash", contents="Tell me a joke."
)
print(response.text)

JavaScript

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

const ai = new GoogleGenAI({});

const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: "Tell me a joke.",
});
console.log(response.text);

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{
        "parts": [{
            "text": "Tell me a joke."
        }]
    }]
}'

# Response
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Why did the chicken cross the road? To get to the other side!"
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 4,
    "candidatesTokenCount": 12,
    "totalTokenCount": 16
  }
}

After (API Interactions)

L'API Interactions renvoie une ressource d'interaction stockée avec une timeline steps. Au lieu de parcourir les candidats et les pièces, inspectez le tableau steps pour trouver le type de sortie souhaité.

Python

from google import genai

client = genai.Client()

# The input can be a simple string shorthand
interaction = client.interactions.create(
    model="gemini-3-flash-preview", input="Tell me a joke."
)

# Inspect the steps manually
for step in interaction.steps:
    if step.type == "model_output":
        print(step.content[0].text)

JavaScript

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

const client = new GoogleGenAI({});

let interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'Tell me a joke.'
});

// Manual inspection
const modelStep = interaction.steps.find(s => s.type === 'model_output');
console.log(modelStep.content[0].text);

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "Tell me a joke."
}'

# Response
{
  "id": "int_123",
  "status": "completed",
  "steps": [
    {
      "type": "user_input",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "Tell me a joke."
        }
      ]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "Why did the chicken cross the road?"
        }
      ]
    }
  ]
}

Conversations multitours

L'API Interactions stocke les interactions par défaut, ce qui permet la gestion de l'état côté serveur pour les conversations multitours.

Avant (generateContent)

Dans generateContent, vous devez gérer manuellement l'historique des conversations à l'aide du tableau contents ou d'un assistant de chat côté client.

Python

Utiliser l'assistant de chat (recommandé)

from google import genai

client = genai.Client()

chat = client.chats.create(model="gemini-2.5-flash")
response1 = chat.send_message("Hi, my name is Phil.")
print(response1.text)

response2 = chat.send_message("What is my name?")
print(response2.text)

Gérer manuellement l'historique

from google import genai
from google.genai import types

client = genai.Client()

# The second turn requires sending the entire history
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        types.Content(
            role="user", parts=[types.Part.from_text("Hi, my name is Phil.")]
        ),
        types.Content(
            role="model",
            parts=[types.Part.from_text("Hi Phil, how can I help you?")],
        ),
        types.Content(
            role="user", parts=[types.Part.from_text("What is my name?")]
        ),
    ],
)
print(response.text)

JavaScript

Utiliser l'assistant de chat (recommandé)

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

const client = new GoogleGenAI({});

const chat = client.chats.create({ model: 'gemini-2.5-flash' });
let response = await chat.sendMessage({ message: 'Hi, my name is Phil.' });
console.log(response.text);

response = await chat.sendMessage({ message: 'What is my name?' });
console.log(response.text);

Gérer manuellement l'historique

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

const client = new GoogleGenAI({});

// The second turn requires sending the entire history
const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
        { role: 'user', parts: [{ text: 'Hi, my name is Phil.' }] },
        { role: 'model', parts: [{ text: 'Hi Phil, how can I help you?' }] },
        { role: 'user', parts: [{ text: 'What is my name?' }] }
    ]
});
console.log(response.text);

REST

# Request (the second turn requires sending the entire history)
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [
        {"role": "user", "parts": [{"text": "Hi, my name is Phil."}]},
        {"role": "model", "parts": [{"text": "Hi Phil, how can I help you?"}]},
        {"role": "user", "parts": [{"text": "What is my name?"}]}
    ]
}'

# Response
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Your name is Phil."
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ]
}

After (API Interactions)

L'API Interactions gère l'état sur le serveur. Vous poursuivez une conversation en faisant référence à previous_interaction_id.

Python

from google import genai

client = genai.Client()

# First turn
interaction1 = client.interactions.create(
    model="gemini-3-flash-preview", input="Hi, my name is Phil."
)
print(interaction1.steps[-1].content[0].text)

# Second turn (passing previous_interaction_id)
interaction2 = client.interactions.create(
    model="gemini-3-flash-preview",
    previous_interaction_id=interaction1.id,
    input="What is my name?",
)
print(interaction2.steps[-1].content[0].text)

JavaScript

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

const client = new GoogleGenAI({});

// First turn
let interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'Hi, my name is Phil.'
});
console.log(interaction.steps.at(-1).content[0].text);

// Second turn
interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    previous_interaction_id: interaction.id,
    input: 'What is my name?'
});
console.log(interaction.steps.at(-1).content[0].text);

REST

# First Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "Hi, my name is Phil."
}'

# Second Request (using ID from first response)
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "previous_interaction_id": "int_123",
    "input": "What is my name?"
}'

# Response to Second Request
{
  "id": "int_123",
  "steps": [
    {
      "type": "user_input",
      "status": "done",
      "content": [{ "type": "text", "text": "Hi, my name is Phil." }]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [{ "type": "text", "text": "Hello Phil! How can I help you today?" }]
    },
    {
      "type": "user_input",
      "status": "done",
      "content": [{ "type": "text", "text": "What is my name?" }]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [{ "type": "text", "text": "Your name is Phil." }]
    }
  ]
}

Entrées multimodales

Les deux API acceptent les entrées multimodales (texte, images, vidéos, etc.).

Avant (generateContent)

Dans generateContent, vous transmettez une liste de parts dans le tableau contents. La réponse renvoie la sortie dans le parts du premier candidat.

Python

from google import genai
from google.genai import types

client = genai.Client()

with open("sample.jpg", "rb") as f:
    image_bytes = f.read()

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        types.Part.from_bytes(data=image_bytes, mime_type="image/jpeg"),
        "Describe this image.",
    ],
)
print(response.text)

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{
        "parts": [
            {
                "inlineData": {
                    "mimeType": "image/jpeg",
                    "data": "..."
                }
            },
            {
                "text": "Describe this image."
            }
        ]
    }]
}'

# Response
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "This is a picture of a beautiful sunset."
          }
        ],
        "role": "model"
      }
    }
  ]
}

After (API Interactions)

Dans l'API Interactions, vous transmettez un tableau au champ input. Pour récupérer le contenu de sortie, recherchez l'étape model_output dans la timeline.

Python

from google import genai

client = genai.Client()

# Assuming you have an image file
with open("sample.jpg", "rb") as f:
    image_bytes = f.read()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {
            "type": "image",
            "mime_type": "image/jpeg",
            "data": image_bytes,
        },
        {"type": "text", "text": "Describe this image."},
    ],
)
for step in interaction.steps:
    if step.type == "model_output":
        print(step.content[0].text)

JavaScript

import { GoogleGenAI } from '@google/genai';
import * as fs from 'fs';

const client = new GoogleGenAI({});

const imageBytes = fs.readFileSync('sample.jpg').toString('base64');

const interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: [
        {
            type: 'image',
            mime_type: 'image/jpeg',
            data: imageBytes
        },
        {
            type: 'text',
            text: 'Describe this image.'
        }
    ]
});
for (const step of interaction.steps) {
    if (step.type === 'model_output') {
        console.log(step.content[0].text);
    }
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": [
        {
            "type": "image",
            "mime_type": "image/jpeg",
            "data": "..."
        },
        {
            "type": "text",
            "text": "Describe this image."
        }
    ]
}'

# Response
{
  "id": "int_multimodal",
  "steps": [
    {
      "type": "user_input",
      "status": "done",
      "content": [
        {
          "type": "image",
          "mime_type": "image/jpeg",
          "data": "..."
        },
        {
          "type": "text",
          "text": "Describe this image."
        }
      ]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "This is a picture of a beautiful sunset over the mountains."
        }
      ]
    }
  ]
}

Sortie structurée

Pour que le modèle renvoie un fichier JSON correspondant à un schéma spécifique, configurez le format de réponse.

Avant (generateContent)

Dans generateContent, vous configurez le format de sortie à l'aide du champ response_format imbriqué dans l'objet generationConfig.

Python

from google import genai
from google.genai import types
from pydantic import BaseModel

client = genai.Client()

class Recipe(BaseModel):
    recipe_name: str
    ingredients: list[str]

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Give me a recipe for chocolate chip cookies.",
    config=types.GenerateContentConfig(
        response_format=[
            {
                "type": "text",
                "mime_type": "application/json",
                "schema": Recipe,
            }
        ]
    ),
)
print(response.text)

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{
        "parts": [{
            "text": "Give me a recipe for chocolate chip cookies."
        }]
    }],
    "generationConfig": {
        "responseFormat": [
            {
                "type": "text",
                "mimeType": "application/json",
                "schema": {
                    "type": "OBJECT",
                    "properties": {
                        "recipe_name": { "type": "STRING" },
                        "ingredients": {
                            "type": "ARRAY",
                            "items": { "type": "STRING" }
                        }
                    },
                    "required": ["recipe_name", "ingredients"]
                }
            }
        ]
    }
}'

# Response
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "{\n  \"recipe_name\": \"Chocolate Chip Cookies\",\n  \"ingredients\": [\n    \"1 cup butter\",\n    \"1 cup sugar\",\n    \"2 cups flour\",\n    \"1 cup chocolate chips\"\n  ]\n}"
          }
        ],
        "role": "model"
      }
    }
  ]
}

After (API Interactions)

Dans l'API Interactions, les contrôles du format de sortie sont déplacés vers un tableau response_format de premier niveau.

Python

from google import genai
from pydantic import BaseModel

client = genai.Client()

class Recipe(BaseModel):
    recipe_name: str
    ingredients: list[str]

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Give me a recipe for chocolate chip cookies.",
    response_format=[
        {
            "type": "text",
            "mime_type": "application/json",
            "schema": Recipe,
        }
    ],
)

for step in interaction.steps:
    if step.type == "model_output":
        print(step.content[0].text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'Give me a recipe for chocolate chip cookies.',
    response_format: [
        {
            type: 'text',
            mime_type: 'application/json',
            schema: {
                type: 'object',
                properties: {
                    recipe_name: { type: 'string' },
                    ingredients: {
                        type: 'array',
                        items: { type: 'string' }
                    }
                },
                required: ['recipe_name', 'ingredients']
            }
        }
    ]
});
for (const step of interaction.steps) {
    if (step.type === 'model_output') {
        console.log(step.content[0].text);
    }
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "Give me a recipe for chocolate chip cookies.",
    "response_format": [
        {
            "type": "text",
            "mime_type": "application/json",
            "schema": {
                "type": "OBJECT",
                "properties": {
                    "recipe_name": { "type": "STRING" },
                    "ingredients": {
                        "type": "ARRAY",
                        "items": { "type": "STRING" }
                    }
                },
                "required": ["recipe_name", "ingredients"]
            }
        }
    ]
}'

# Response
{
  "id": "int_structured",
  "steps": [
    {
      "type": "user_input",
      "status": "done",
      "content": [{ "type": "text", "text": "Give me a recipe for chocolate chip cookies." }]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "{\n  \"recipe_name\": \"Chocolate Chip Cookies\",\n  \"ingredients\": [\n    \"1 cup butter\",\n    \"1 cup sugar\",\n    \"2 cups flour\",\n    \"1 cup chocolate chips\"\n  ]\n}"
        }
      ]
    }
  ]
}

Génération multimodale

Lorsque vous générez du contenu dans des modalités autres que le texte (comme des images ou de l'audio), la principale différence réside dans la façon dont la réponse structure le contenu multimédia généré.

Avant (generateContent)

Dans generateContent, la réponse renvoie le contenu multimédia généré directement dans le parts du candidat, généralement sous forme de données base64 dans inlineData.

# Response structure concept
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Here is your generated image:"
          },
          {
            "inlineData": {
              "mimeType": "image/jpeg",
              "data": "...base64..."
            }
          }
        ]
      }
    }
  ]
}

After (API Interactions)

Dans l'API Interactions, les contenus multimédias générés apparaissent sous forme d'éléments distincts dans le tableau content d'une étape model_output de la timeline, ce qui permet de maintenir le flux chronologique de l'interaction.

# Response structure concept
{
  "id": "int_123",
  "steps": [
    {
      "type": "model_output",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "Here is your generated image:"
        },
        {
          "type": "image",
          "mime_type": "image/jpeg",
          "data": "...base64..." // Or a reference URL in future
        }
      ]
    }
  ]
}

Cela permet de conserver une analyse des réponses cohérente avec la façon dont les entrées et les sorties de texte sont traitées : tout est une étape de la chronologie.

Outils côté serveur

Gemini est compatible avec les outils intégrés côté serveur, comme l'ancrage de la recherche Google. La principale différence réside dans la façon dont la réponse représente l'exécution de l'outil.

Avant (generateContent)

Dans generateContent, les outils côté serveur sont en grande partie opaques. Vous activez l'outil et obtenez une réponse finale avec un objet groundingMetadata distinct. Il est important de noter que les citations ne sont pas intégrées. groundingSupports utilise des index de caractères pour mapper les segments de texte aux sources Web dans groundingChunks.

Python

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Who won Euro 2024?",
    config=types.GenerateContentConfig(
        tools=[{"google_search": {}}]
    ),
)

# Access search entry point (widget) and citations
metadata = response.candidates[0].grounding_metadata
if metadata.search_entry_point:
    print(f"Search Entry Point: {metadata.search_entry_point.rendered_content}")

for support in metadata.grounding_supports:
    print(f"Citation: {support.segment.text}")

JavaScript

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

const client = new GoogleGenAI({});

const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'Who won Euro 2024?',
    config: {
        tools: [{ google_search: {} }]
    }
});

const metadata = response.candidates[0].groundingMetadata;
if (metadata.searchEntryPoint) {
    console.log(`Search Entry Point: ${metadata.searchEntryPoint.renderedContent}`);
}
for (const support of metadata.groundingSupports) {
    console.log(`Citation: ${support.segment.text}`);
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{
        "parts": [{
            "text": "Who won Euro 2024?"
        }]
    }],
    "tools": [{
        "googleSearchRetrieval": {}
    }]
}'

# Response
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Spain won Euro 2024, defeating England 2-1 in the final. This victory marks Spain's record fourth European Championship title."
          }
        ],
        "role": "model"
      },
      "groundingMetadata": {
        "webSearchQueries": [
          "UEFA Euro 2024 winner",
          "who won euro 2024"
        ],
        "searchEntryPoint": {
          "renderedContent": "<!-- HTML and CSS for the search widget -->"
        },
        "groundingChunks": [
          {"web": {"uri": "https://vertexaisearch.cloud.google.com.....", "title": "aljazeera.com"}},
          {"web": {"uri": "https://vertexaisearch.cloud.google.com.....", "title": "uefa.com"}}
        ],
        "groundingSupports": [
          {
            "segment": {"startIndex": 0, "endIndex": 85, "text": "Spain won Euro 2024, defeatin..."},
            "groundingChunkIndices": [0]
          },
          {
            "segment": {"startIndex": 86, "endIndex": 210, "text": "This victory marks Spain's..."},
            "groundingChunkIndices": [0, 1]
          }
        ]
      }
    }
  ]
}

After (API Interactions)

Dans l'API Interactions, les outils côté serveur offrent une transparence totale de la chronologie. L'API enregistre l'appel et le résultat en tant qu'exécutions steps distinctes (google_search_call et google_search_result), ce qui permet de voir exactement les données récupérées par le modèle.

De plus, l'API renvoie des citations intégrées. Au lieu de mapper les index à partir d'un objet de métadonnées distinct, l'élément de texte de l'étape model_output contient son propre tableau annotations qui renvoie directement à la source.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Who won Euro 2024?",
    tools=[{"type": "google_search"}],
)

for step in interaction.steps:
    if step.type == "google_search_result":
        print(f"Search Suggestions: {step.search_suggestions}")
    elif step.type == "model_output":
        print(f"Answer: {step.content[0].text}")
        if step.content[0].annotations:
            for anno in step.content[0].annotations:
                print(f"Citation: {anno.title} ({anno.uri})")

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'Who won Euro 2024?',
    tools: [{ type: 'google_search' }]
});

for (const step of interaction.steps) {
    if (step.type === 'google_search_result') {
        console.log(`Search Suggestions: ${step.search_suggestions}`);
    } else if (step.type === 'model_output') {
        console.log(`Answer: ${step.content[0].text}`);
        if (step.content[0].annotations) {
            for (const anno of step.content[0].annotations) {
                console.log(`Citation: ${anno.title} (${anno.uri})`);
            }
        }
    }
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "Who won Euro 2024?",
    "tools": [{"type": "google_search"}]
}'

# Response (showing grounding)
{
  "id": "int_grounded",
  "steps": [
    {
      "type": "user_input",
      "status": "done",
      "content": [{ "type": "text", "text": "Who won Euro 2024?" }]
    },
    {
      "type": "google_search_call",
      "status": "done",
      "content": [{ "type": "text", "text": "UEFA Euro 2024 winner" }]
    },
    {
      "type": "google_search_result",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "Spain won Euro 2024..." 
        }
      ]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [
        {
          "type": "text",
          "text": "Spain won Euro 2024, defeating England 2-1.",
          "annotations": [
            {
              "start_index": 0,
              "end_index": 42,
              "uri": "https://vertexaisearch...",
              "title": "aljazeera.com"
            }
          ]
        }
      ]
    }
  ]
}

Appel de fonction

La structure des appels de fonction et des résultats a également été modifiée pour s'adapter au schéma "Steps".

Avant (generateContent)

Dans generateContent, la réponse renvoie les appels de fonction dans les candidats.

Python

from google import genai
from google.genai import types

client = genai.Client()

# Step 1: Send prompt with tools
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="What's the weather in Boston?",
    config=types.GenerateContentConfig(tools=[weather_tool]),
)

# Assume model returned function_call
function_call = response.candidates[0].content.parts[0].function_call
print(f"Requested tool: {function_call.name}")

# Step 2: Execute local function and send result back
result = "52°F and rain"

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        types.Content(
            role="user",
            parts=[
                types.Part.from_text(text="What's the weather in Boston?")
            ],
        ),
        response.candidates[0].content,  # Model turn with function call
        types.Content(
            role="user",
            parts=[
                types.Part.from_function_response(
                    name=function_call.name,
                    response={"result": result},
                )
            ],
        ),
    ],
    config=types.GenerateContentConfig(tools=[weather_tool]),
)
print(response.text)

JavaScript

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

const client = new GoogleGenAI({});

// Step 1: Send prompt with tools
let response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: "What's the weather in Boston?",
    config: { tools: [weatherTool] }
});

const functionCall = response.candidates[0].content.parts[0].functionCall;
console.log(`Requested tool: ${functionCall.name}`);

// Step 2: Execute local function and send result back
const result = "52°F and rain";

response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
        { role: 'user', parts: [{ text: "What's the weather in Boston?" }] },
        response.candidates[0].content, // Model turn
        {
            role: 'user',
            parts: [{
                functionResponse: {
                    name: functionCall.name,
                    response: { result: result }
                }
            }]
        }
    ],
    config: { tools: [weatherTool] }
});
console.log(response.text);

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{
        "parts": [{
            "text": "What is the weather like in Boston, MA?"
        }]
    }],
    "tools": [{
        "functionDeclarations": [{
            "name": "get_weather",
            "description": "Get the current weather",
            "parameters": {
                "type": "OBJECT",
                "properties": {
                    "location": {"type": "STRING"}
                },
                "required": ["location"]
            }
        }]
    }]
}'

# Response
{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "functionCall": {
              "name": "get_weather",
              "args": { "location": "Boston, MA" }
            }
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP",
      "index": 0
    }
  ]
}

After (API Interactions)

Les appels d'outils et les résultats sont désormais des étapes distinctes dans la chronologie.

Python

from google import genai

client = genai.Client()

weather_tool = {
    "type": "function",
    "name": "get_weather",
    "description": "Gets weather",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {"type": "string"}
        },
    },
}

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What's the weather in Boston?",
    tools=[weather_tool],
)

# Check if the model requested a tool call
for step in interaction.steps:
    if step.type == "function_call":
        print(f"Executing {step.name} for {step.arguments}")

        # Execute your local function here...
        result = "52°F and rain"

        # Submit the result back as a step
        interaction = client.interactions.create(
            model="gemini-3-flash-preview",
            previous_interaction_id=interaction.id,
            input=[
                {
                    "type": "function_result",
                    "call_id": step.id,
                    "name": step.name,
                    "result": [{"type": "text", "text": result}],
                }
            ],
        )
        # Inspect steps for final response
        for s in interaction.steps:
            if s.type == "model_output":
                print(s.content[0].text)

JavaScript

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

const client = new GoogleGenAI({});

const weatherTool = {
    type: "function",
    name: "get_weather",
    description: "Get weather for a location",
    parameters: {
        type: "object",
        properties: {
            location: { type: "string" }
        },
        required: ["location"]
    }
};

const interaction = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: "What's the weather in Boston?",
    tools: [weatherTool]
});

// Check if the model requested a tool call
for (const step of interaction.steps) {
    if (step.type === 'function_call') {
        console.log(`Executing ${step.name} for ${JSON.stringify(step.arguments)}`);

        const result = "52°F and rain";

        // Submit the result back as a step
        const nextInteraction = await client.interactions.create({
            model: 'gemini-3-flash-preview',
            previous_interaction_id: interaction.id,
            input: [
                {
                    type: 'function_result',
                    call_id: step.id,
                    name: step.name,
                    result: [{ type: 'text', text: result }]
                }
            ]
        });

        // Inspect steps for final response
        for (const s of nextInteraction.steps) {
            if (s.type === 'model_output') {
                console.log(s.content[0].text);
            }
        }
    }
}

REST

# Initial Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "What's the weather in Boston?",
    "tools": [{
        "type": "function",
        "name": "get_weather",
        "description": "Get weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": { "type": "string" }
            },
            "required": ["location"]
        }
    }]
}'

# Response (requires action)
{
  "id": "int_001",
  "status": "requires_action",
  "steps": [
    {
      "type": "user_input",
      "status": "done",
      "content": [
        { "type": "text", "text": "What's the weather in Boston?" }
      ]
    },
    {
      "type": "function_call",
      "status": "waiting",
      "id": "fc_1",
      "name": "get_weather",
      "arguments": { "location": "Boston, MA" }
    }
  ]
}

# Submit Tool Result Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "previous_interaction_id": "int_001",
    "input": {
        "type": "function_result",
        "call_id": "fc_1",
        "name": "get_weather",
        "result": [
            { "type": "text", "text": "52°F with rain" }
        ]
    }
}'

# Final Response
{
  "id": "int_002",
  "status": "completed",
  "steps": [
    {
      "type": "function_result",
      "call_id": "fc_1",
      "name": "get_weather",
      "result": [
        { "type": "text", "text": "52°F with rain" }
      ]
    },
    {
      "type": "model_output",
      "status": "done",
      "content": [
        { "type": "text", "text": "It's 52°F with rain in Boston." }
      ]
    }
  ]
}

Streaming

Une différence majeure entre le streaming et l'API Interactions est que cette dernière utilise le même point de terminaison avec "stream": true dans le corps de la requête, tandis que l'API generateContent nécessitait l'appel d'un point de terminaison dédié (:streamGenerateContent).

De plus, les événements de streaming utilisent désormais des types spécialisés pour surveiller le cycle de vie des interactions et suivre les étapes d'exécution tout au long de la chronologie.

Avant (generateContentStream)

Avec generateContent, vous consommez un flux de blocs de réponse.

Python

response = client.models.generate_content_stream(
    model="gemini-2.5-flash", contents="Tell me a story"
)
for chunk in response:
    print(chunk.text, end="")

JavaScript

const responseStream = await client.models.generateContentStream({
    model: 'gemini-2.5-flash',
    contents: 'Tell me a story',
});
for await (const chunk of responseStream) {
    process.stdout.write(chunk.text);
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:streamGenerateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{
        "parts": [{
            "text": "Tell me a story"
        }]
    }]
}'

# Response stream
event: content.start
data: {"event_type": "content.start", "index": 0, "content": {"type": "thought"}}
event: content.delta
data: {"event_type": "content.delta", "index": 0, "delta": {"type": "thought_summary", "text": "User wants an explanation."}}
event: content.stop
data: {"event_type": "content.stop", "index": 0}
event: content.start
data: {"event_type": "content.start", "index": 1, "content": {"type": "text"}}
event: content.delta
data: {"event_type": "content.delta", "index": 1, "delta": {"type": "text", "text": "Hello"}}
event: content.stop
data: {"event_type": "content.stop", "index": 1}

After (API Interactions)

Dans l'API Interactions, le streaming utilise des événements envoyés par le serveur (SSE) et des types delta spécialisés pour représenter les étapes d'exécution au fur et à mesure qu'elles se produisent.

Python

from google import genai

client = genai.Client()

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Tell me a story",
    stream=True,
)

for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="", flush=True)
    elif event.event_type == "interaction.complete":
        print(f"\n\n--- Stream Finished ---")

JavaScript

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

const client = new GoogleGenAI({});

const stream = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: 'Tell me a story',
    stream: true,
});

for await (const event of stream) {
    if (event.event_type === 'step.delta') {
        if (event.delta.type === 'text' && 'text' in event.delta) {
            process.stdout.write(event.delta.text);
        }
    } else if (event.event_type === 'interaction.complete') {
        console.log('\n\n--- Stream Finished ---');
    }
}

REST

# Exemple de sortie de flux SSE event: interaction.created data: {"type": "interaction.created", "interaction": {"id": "int_xyz", "status": "created"}} event: interaction.status_update data: {"type": "interaction.status_update", "status": "in_progress"} event: step.start data: {"type": "step.start", "index": 0, "step": {"type": "thought"}} event: step.delta data: {"type": "step.delta", "index": 0, "delta": {"type": "thought", "text": "User wants an explanation."}} event: step.stop data: {"type": "step.stop", "index": 0, "status": "done"} event: step.start data: {"type": "step.start", "index": 1, "step": {"type": "model_output"}} event: step.delta data: {"type": "step.delta", "index": 1, "delta": {"type": "text", "text": "Hello"}} event: step.stop data: {"type": "step.stop", "index": 1, "status": "done"} event: interaction.complete data: {"type": "interaction.complete", "interaction": {"id": "int_xyz", "status": "completed", "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}}} ```

Outils de streaming et appels de fonction

Le comportement des outils dans le flux a considérablement changé depuis generateContent pour offrir un contrôle et une visibilité plus précis.

Avant (generateContent)

Avec generateContent, les appels de fonction de streaming arrivaient complets en un seul bloc. Vous ne pouviez pas voir les arguments générés en temps réel. Le gestionnaire vérifiait donc simplement la présence d'un objet functionCall complet.

Python

from google import genai
from google.genai import types

client = genai.Client()

stream = client.models.generate_content_stream(
    model="gemini-2.5-flash",
    contents="What's the weather in Boston?",
    config=types.GenerateContentConfig(tools=[weather_tool]),
)

for chunk in stream:
    # Function calls arrived complete — no partial arguments
    if chunk.candidates[0].content.parts[0].function_call:
        fc = chunk.candidates[0].content.parts[0].function_call
        print(f"Call: {fc.name}({fc.args})")
    elif chunk.text:
        print(chunk.text, end="")

JavaScript

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

const client = new GoogleGenAI({});

const stream = await client.models.generateContentStream({
    model: 'gemini-2.5-flash',
    contents: "What's the weather in Boston?",
    config: { tools: [weatherTool] }
});

for await (const chunk of stream) {
    // Function calls arrived complete — no partial arguments
    const part = chunk.candidates[0].content.parts[0];
    if (part.functionCall) {
        console.log(`Call: ${part.functionCall.name}(${JSON.stringify(part.functionCall.args)})`);
    } else if (part.text) {
        process.stdout.write(part.text);
    }
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:streamGenerateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "contents": [{"parts": [{"text": "What'\''s the weather in Boston?"}]}],
    "tools": [{"functionDeclarations": [{"name": "get_weather", "parameters": {"type": "OBJECT", "properties": {"location": {"type": "STRING"}}}}]}]
}'

# Response stream — function call arrives complete in one chunk
{"candidates": [{"content": {"parts": [{"functionCall": {"name": "get_weather", "args": {"location": "Boston, MA"}}}]}}]}

After (API Interactions)

L'API Interactions diffuse les arguments d'appel de fonction caractère par caractère sous forme d'événements arguments. L'ensemble du cycle de vie de l'outil (réflexion, appel, résultat et sortie) se déroule en une série d'étapes distinctes.

Python

from google import genai

client = genai.Client()

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="What's the weather in Boston?",
    tools=[get_weather_tool],
    stream=True,
)

for event in stream:
    if event.event_type == "step.start":
        if event.step.type == "function_call":
            print(f"Calling: {event.step.name}")
    elif event.event_type == "step.delta":
        if event.delta.type == "arguments":
            print(f"  args: {event.delta.partial_arguments}")
        elif event.delta.type == "text":
            print(event.delta.text, end="")
    elif event.event_type == "interaction.complete":
        print("\n--- Done ---")

JavaScript

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

const client = new GoogleGenAI({});

const stream = await client.interactions.create({
    model: 'gemini-3-flash-preview',
    input: "What's the weather in Boston?",
    tools: [getWeatherTool],
    stream: true,
});

for await (const event of stream) {
    if (event.event_type === 'step.start') {
        if (event.step.type === 'function_call') {
            console.log(`Calling: ${event.step.name}`);
        }
    } else if (event.event_type === 'step.delta') {
        if (event.delta.type === 'arguments') {
            console.log(`  args: ${event.delta.partial_arguments}`);
        } else if (event.delta.type === 'text') {
            process.stdout.write(event.delta.text);
        }
    } else if (event.event_type === 'interaction.complete') {
        console.log('\n--- Done ---');
    }
}

REST

# Request
curl -X POST "https://generativelanguage.googleapis.com/v1beta2/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "model": "gemini-3-flash-preview",
    "input": "What'\''s the weather in Boston?",
    "tools": [{"type": "function", "name": "get_weather", "parameters": {"type": "object", "properties": {"location": {"type": "string"}}}}],
    "stream": true
}'

# Response stream
// Interaction created
event: interaction.created
data: {"type": "interaction.created", "interaction": {"id": "int_xyz", "status": "created"}}

event: interaction.status_update
data: {"type": "interaction.status_update", "status": "in_progress"}

// ── Step 0: Thought ──────────────────────────────────
event: step.start
data: {"type": "step.start", "index": 0, "step": {"type": "thought"}}

event: step.delta
data: {"type": "step.delta", "index": 0, "delta": {"type": "thought", "text": "The user wants weather data for Boston. I'll call the get_weather tool."}}

event: step.stop
data: {"type": "step.stop", "index": 0, "status": "done"}

// ── Step 1: Function Call (arguments streamed) ───────
event: step.start
data: {"type": "step.start", "index": 1, "step": {"type": "function_call", "id": "fc_1", "name": "get_weather"}}

event: step.delta
data: {"type": "step.delta", "index": 1, "delta": {"type": "arguments", "partial_arguments": "{\"location\": \"Boston, MA\"}"}}

event: step.stop
data: {"type": "step.stop", "index": 1, "status": "waiting"}

// The interaction pauses — the model needs the tool result before continuing.
event: interaction.status_update
data: {"type": "interaction.status_update", "status": "requires_action"}

// ── (Client submits the tool result) ──────────────────
// The client calls interactions.create with the function_result as input
// and the previous interaction's ID, then resumes consuming the stream.

event: interaction.status_update
data: {"type": "interaction.status_update", "status": "in_progress"}

// ── Step 2: Function Result (echoed back, no deltas) ─
event: step.start
data: {"type": "step.start", "index": 2, "step": {"type": "function_result", "call_id": "fc_1", "name": "get_weather", "result": [{"type": "text", "text": "52°F, rain"}]}}

event: step.stop
data: {"type": "step.stop", "index": 2, "status": "done"}

// ── Step 3: Thought ──────────────────────────────────
event: step.start
data: {"type": "step.start", "index": 3, "step": {"type": "thought"}}

event: step.delta
data: {"type": "step.delta", "index": 3, "delta": {"type": "thought", "text": "Got weather data. Composing the final response."}}

event: step.stop
data: {"type": "step.stop", "index": 3, "status": "done"}

// ── Step 4: Model Output (text streamed) ─────────────
event: step.start
data: {"type": "step.start", "index": 4, "step": {"type": "model_output"}}

event: step.delta
data: {"type": "step.delta", "index": 4, "delta": {"type": "text", "text": "It's currently 52°F and rainy in Boston."}}

event: step.stop
data: {"type": "step.stop", "index": 4, "status": "done"}

// ── Interaction complete ─────────────────────────────
event: interaction.complete
data: {"type": "interaction.complete", "interaction": {"id": "int_xyz", "status": "completed", "usage": {"prompt_tokens": 256, "completion_tokens": 128, "total_tokens": 384}}}

Outils côté serveur dans le flux

Les outils côté serveur tels que la recherche Google se comportent différemment des appels de fonction dans le flux. Leur appel et leur résultat arrivent complets dans l'événement step.start sans deltas, juste step.start suivi immédiatement de step.stop :

// Server-side tool call — payload arrives complete in step.start
event: step.start
data: {"type": "step.start", "index": 4, "step": {"type": "google_search_call", "id": "gs_2", "query": "Alphabet Q4 2025 earnings"}}

event: step.stop
data: {"type": "step.stop", "index": 4, "status": "done"}

// Server-side tool result — also complete in step.start
event: step.start
data: {"type": "step.start", "index": 5, "step": {"type": "google_search_result", "call_id": "gs_2", "rendered_content": "<div>Alphabet Q4 2025 Revenue: $105.6B</div>", "signature": "abc123..."}}

event: step.stop
data: {"type": "step.stop", "index": 5, "status": "done"}