Generazione di testo

L'API Gemini può generare output di testo da input di testo, immagini, video e audio.

Ecco un esempio di base:

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How does AI work?"
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How does AI work?",
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
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-flash-preview",
    "input": "How does AI work?"
  }'

Pensare con Gemini

I modelli Gemini spesso hanno "riflessione" attivata per impostazione predefinita, il che consente al modello di ragionare prima di rispondere a una richiesta.

Ogni modello supporta configurazioni di riflessione diverse, che ti consentono di controllare costi, latenza e intelligenza. Per maggiori dettagli, consulta la guida alla riflessione.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How does AI work?",
    generation_config={
        "thinking_level": "low"
    }
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How does AI work?",
    generation_config: {
      thinking_level: "low",
    },
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
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-flash-preview",
    "input": "How does AI work?",
    "generation_config": {
      "thinking_level": "low"
    }
  }'

Istruzioni di sistema e altre configurazioni

Puoi guidare il comportamento dei modelli Gemini con le istruzioni di sistema. Passa un parametro system_instruction per configurare il comportamento del modello.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    system_instruction="You are a cat. Your name is Neko.",
    input="Hello there"
)

print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Hello there",
    system_instruction: "You are a cat. Your name is Neko.",
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
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-flash-preview",
    "system_instruction": "You are a cat. Your name is Neko.",
    "input": "Hello there"
  }'

Puoi anche sostituire i parametri di generazione predefiniti, ad esempio la temperatura, utilizzando il parametro generation_config.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain how AI works",
    generation_config={
        "temperature": 1.0
    }
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Explain how AI works",
    generation_config: {
      temperature: 1.0,
    },
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
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-flash-preview",
    "input": "Explain how AI works",
    "generation_config": {
      "temperature": 1.0
    }
  }'

Per un elenco completo dei parametri configurabili e delle relative descrizioni, consulta la documentazione di riferimento dell'API Interactions.

Input multimodali

L'API Gemini supporta input multimodali, che ti consentono di combinare testo con file multimediali. L'esempio seguente mostra come fornire un'immagine:

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

uploaded_file = client.files.upload(file="path/to/organ.jpg")

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input=[
        {"type": "text", "text": "Tell me about this instrument"},
        {
            "type": "image",
            "uri": uploaded_file.uri,
            "mime_type": uploaded_file.mime_type
        }
    ]
)
print(interaction.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const uploadedFile = await ai.files.upload({
    file: "path/to/organ.jpg",
    config: { mimeType: "image/jpeg" }
  });

  const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: [
      {type: "text", text: "Tell me about this instrument"},
      {
        type: "image",
        uri: uploadedFile.uri,
        mime_type: uploadedFile.mimeType
      }
    ],
  });
  console.log(interaction.steps.at(-1).content[0].text);
}

await main();

REST

# First upload the file using the Files API, then use the URI:
# Specifies the API revision to avoid breaking changes when they become default
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-flash-preview",
    "input": [
      {"type": "text", "text": "Tell me about this instrument"},
      {
        "type": "image",
        "uri": "YOUR_FILE_URI",
        "mime_type": "image/jpeg"
      }
    ]
  }'

Per metodi alternativi per fornire immagini ed elaborazioni di immagini più avanzate, consulta la nostra guida alla comprensione delle immagini. L'API supporta anche input e comprensione di documenti, video e audio.

Risposte dinamiche

Per impostazione predefinita, il modello restituisce una risposta solo al termine dell'intero processo di generazione.

Per interazioni più fluide, utilizza lo streaming per gestire i blocchi di risposta man mano che vengono generati. Per una guida completa che illustra i tipi di eventi, lo streaming con gli strumenti, la riflessione, gli agenti e la generazione di immagini, consulta la guida dedicata alle interazioni di streaming.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain how AI works",
    stream=True
)
for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="")

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const stream = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Explain how AI works",
    stream: true,
  });

  for await (const event of stream) {
    if (event.event_type === "step.delta") {
      if (event.delta.type === "text") {
        process.stdout.write(event.delta.text);
      }
    }
  }
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  --no-buffer \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "Explain how AI works",
    "stream": true
  }'

Conversazioni a più turni

L'API Interactions supporta le conversazioni a più turni concatenando le interazioni utilizzando previous_interaction_id. Ogni turno è un'interazione separata e l'API gestisce automaticamente la cronologia delle conversazioni.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="I have 2 dogs in my house.",
)
print(interaction1.steps[-1].content[0].text)

interaction2 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How many paws are in my house?",
    previous_interaction_id=interaction1.id,
)
print(interaction2.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "I have 2 dogs in my house.",
  });
  console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

  const interaction2 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How many paws are in my house?",
    previous_interaction_id: interaction1.id,
  });
  console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -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-flash-preview",
    "input": "I have 2 dogs in my house."
  }')

INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have two dogs in my house. How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'"
  }'

Lo streaming può essere utilizzato anche per le conversazioni a più turni combinando previous_interaction_id con i metodi di streaming.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    input="I have 2 dogs in my house.",
)
print(interaction1.steps[-1].content[0].text)

stream = client.interactions.create(
    model="gemini-3-flash-preview",
    input="How many paws are in my house?",
    previous_interaction_id=interaction1.id,
    stream=True
)
for event in stream:
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="")

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  const interaction1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "I have 2 dogs in my house.",
  });
  console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

  const stream = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "How many paws are in my house?",
    previous_interaction_id: interaction1.id,
    stream: true,
  });
  for await (const event of stream) {
    if (event.event_type === "step.delta") {
      if (event.delta.type === "text") {
        process.stdout.write(event.delta.text);
      }
    }
  }
}

await main();

REST

# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "I have 2 dogs in my house."
  }')
INTERACTION_ID=$(echo "$RESPONSE1" | jq -r '.id')

# Specifies the API revision to avoid breaking changes when they become default
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions?alt=sse" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -H "Api-Revision: 2026-05-20" \
  --no-buffer \
  -d '{
    "model": "gemini-3-flash-preview",
    "input": "How many paws are in my house?",
    "previous_interaction_id": "'$INTERACTION_ID'",
    "stream": true
  }'

Conversazioni senza stato

Per impostazione predefinita, l'API Interactions gestisce lo stato della conversazione lato server quando utilizzi previous_interaction_id. Tuttavia, puoi anche operare in modalità senza stato gestendo autonomamente la cronologia delle conversazioni lato client.

Per utilizzare la modalità senza stato: 1. Imposta store=false nella richiesta per disattivare l'archiviazione lato server. 2. Mantieni la cronologia delle conversazioni come array di passaggi lato client. 3. Nelle richieste successive, passa i passaggi accumulati nel campo input e aggiungi il nuovo turno come passaggio user_input.

Python

# This will only work for SDK newer than 2.0.0
from google import genai

client = genai.Client()

# Initialize history with the first user turn
history = [
    {
        "type": "user_input",
        "content": [{"type": "text", "text": "I have 2 dogs in my house."}]
    }
]

# Turn 1: Send request with store=False
interaction1 = client.interactions.create(
    model="gemini-3-flash-preview",
    store=False,
    input=history
)
print("Response 1:", interaction1.steps[-1].content[0].text)

# Append the model's response steps to history
for step in interaction1.steps:
    # Convert the SDK Step object to a dictionary
    history.append(step.model_dump())

# Append the next user turn as a user_input step
history.append({
    "type": "user_input",
    "content": [{"type": "text", "text": "How many paws are in my house?"}]
})

# Turn 2: Send full history with store=False
interaction2 = client.interactions.create(
    model="gemini-3-flash-preview",
    store=False,
    input=history
)
print("Response 2:", interaction2.steps[-1].content[0].text)

JavaScript

// This will only work for SDK newer than 2.0.0
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({});

async function main() {
  // Initialize history with the first user turn
  const history = [
    {
      type: "user_input",
      content: [{ type: "text", text: "I have 2 dogs in my house." }]
    }
  ];

  // Turn 1: Send request with store: false
  const interaction1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    store: false,
    input: history
  });
  console.log("Response 1:", interaction1.steps.at(-1).content[0].text);

  // Append model response steps to history
  history.push(...interaction1.steps);

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

  // Turn 2: Send full history with store: false
  const interaction2 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    store: false,
    input: history
  });
  console.log("Response 2:", interaction2.steps.at(-1).content[0].text);
}

await main();

REST

# Turn 1: Send request with store: false
# Specifies the API revision to avoid breaking changes when they become default
RESPONSE1=$(curl -s -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-flash-preview",
    "store": false,
    "input": [
      {
        "type": "user_input",
        "content": [{"type": "text", "text": "I have 2 dogs in my house."}]
      }
    ]
  }')

# Extract the steps from response
MODEL_STEPS=$(echo "$RESPONSE1" | jq '.steps')

# Reconstruct the full history for Turn 2 by combining:
# 1. First user input
# 2. Model response steps
# 3. Second user input
HISTORY=$(jq -n \
  --argjson first_input '[{"type": "user_input", "content": [{"type": "text", "text": "I have 2 dogs in my house."}]}]' \
  --argjson model_steps "$MODEL_STEPS" \
  --argjson second_input '[{"type": "user_input", "content": [{"type": "text", "text": "How many paws are in my house?"}]}]' \
  "'"'"'$first_input + $model_steps + $second_input'"'"'")

# Turn 2: Send the full history
# Specifies the API revision to avoid breaking changes when they become default
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-flash-preview\",
    \"store\": false,
    \"input\": $HISTORY
  }"

Suggerimenti per i prompt

Consulta la nostra guida all'ingegneria dei prompt per suggerimenti su come sfruttare al meglio Gemini.

Passaggi successivi