Die Vorabversion von Gemini 2.5 Pro ist jetzt für die Produktion verfügbar. Weitere Informationen

Diese Seite wurde von der Cloud Translation API übersetzt.

Auf die Google Gen AI SDKs umstellen

Als wir die Gemini 2.0-Modellfamilie eingeführt haben, haben wir auch eine Reihe neuer Google Gen AI SDKs für die Arbeit mit der Gemini API veröffentlicht:

Diese aktualisierten SDKs sind vollständig mit allen Gemini API-Modellen und -Funktionen kompatibel, einschließlich neuer Funktionen wie der Live API und Veo.

Wir empfehlen Ihnen, mit der Migration Ihrer Projekte von den alten Gemini SDKs zu den neuen Gen AI SDKs zu beginnen. Dieser Leitfaden enthält Beispiele für vor- und nachher-Code, um Ihnen den Einstieg zu erleichtern. Wir werden hier weitere Beispiele hinzufügen, damit Sie die neuen SDKs schnell und einfach einrichten können.

SDK Installieren

Vorher

Python

pip install -U -q "google-generativeai"

JavaScript

npm install @google/generative-ai

Nachher

Python

pip install -U -q "google-genai"

JavaScript

npm install @google/genai

Authentifizieren

Authentifizieren Sie sich mit einem API-Schlüssel. Sie können Ihren API-Schlüssel in Google AI Studio erstellen.

Vorher

Python

Das alte SDK hat das API-Clientobjekt implizit verarbeitet. Im neuen SDK erstellen Sie den API-Client und verwenden ihn, um die API aufzurufen. In beiden Fällen ruft das SDK Ihren API-Schlüssel aus der Umgebungsvariablen GOOGLE_API_KEY ab, wenn Sie keinen an den Client übergeben.

import google.generativeai as genai

genai.configure(api_key=...)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");

Nachher

Python

export GOOGLE_API_KEY="YOUR_API_KEY"

from google import genai

client = genai.Client() # Set the API key using the GOOGLE_API_KEY env var.
                        # Alternatively, you could set the API key explicitly:
                        # client = genai.Client(api_key="your_api_key")

JavaScript

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

const ai = new GoogleGenAI({apiKey: "GEMINI_API_KEY"});

Inhaltserstellung

Vorher

Python

Das neue SDK bietet über das Client-Objekt Zugriff auf alle API-Methoden. Mit Ausnahme einiger zustandsabhängiger Sonderfälle (chat und Live-API-sessions) sind dies alles zustandslose Funktionen. Aus Gründen der Praktikabilität und Einheitlichkeit sind die zurückgegebenen Objekte pydantic-Klassen.

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content(
    'Tell me a story in 300 words'
)
print(response.text)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const prompt = "Tell me a story in 300 words";

const result = await model.generateContent(prompt);
console.log(result.response.text());

Nachher

Python

from google import genai
client = genai.Client()

response = client.models.generate_content(
    model='gemini-2.0-flash',
    contents='Tell me a story in 300 words.'
)
print(response.text)

print(response.model_dump_json(
    exclude_none=True, indent=4))

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: "Tell me a story in 300 words.",
});
console.log(response.text);

Vorher

Python

Viele der praktischen Funktionen des alten SDKs sind auch im neuen SDK verfügbar. PIL.Image-Objekte werden beispielsweise automatisch konvertiert.

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content([
    'Tell me a story based on this image',
    Image.open(image_path)
])
print(response.text)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

function fileToGenerativePart(path, mimeType) {
  return {
    inlineData: {
      data: Buffer.from(fs.readFileSync(path)).toString("base64"),
      mimeType,
    },
  };
}

const prompt = "Tell me a story based on this image";

const imagePart = fileToGenerativePart(
  `path/to/organ.jpg`,
  "image/jpeg",
);

const result = await model.generateContent([prompt, imagePart]);
console.log(result.response.text());

Nachher

Python

from google import genai
from PIL import Image

client = genai.Client()

response = client.models.generate_content(
    model='gemini-2.0-flash',
    contents=[
        'Tell me a story based on this image',
        Image.open(image_path)
    ]
)
print(response.text)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

const organ = await ai.files.upload({
  file: "path/to/organ.jpg",
});

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: [
    createUserContent([
      "Tell me a story based on this image",
      createPartFromUri(organ.uri, organ.mimeType)
    ]),
  ],
});
console.log(response.text);

Streaming

Vorher

Python

import google.generativeai as genai

response = model.generate_content(
    "Write a cute story about cats.",
    stream=True)
for chunk in response:
    print(chunk.text)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

const prompt = "Write a story about a magic backpack.";

const result = await model.generateContentStream(prompt);

// Print text as it comes in.
for await (const chunk of result.stream) {
  const chunkText = chunk.text();
  process.stdout.write(chunkText);
}

Nachher

Python

from google import genai

client = genai.Client()

for chunk in client.models.generate_content_stream(
  model='gemini-2.0-flash',
  contents='Tell me a story in 300 words.'
):
    print(chunk.text)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

const response = await ai.models.generateContentStream({
  model: "gemini-2.0-flash",
  contents: "Write a story about a magic backpack.",
});
let text = "";
for await (const chunk of response) {
  console.log(chunk.text);
  text += chunk.text;
}

Optionale Argumente

Vorher

Python

Für alle Methoden im neuen SDK werden die erforderlichen Argumente als Schlüsselwortargumente angegeben. Alle optionalen Eingaben werden im config-Argument angegeben. Konfigurationsargumente können entweder als Python-Wörterbücher oder als Config-Klassen im google.genai.types-Namespace angegeben werden. Aus Gründen der Praktikabilität und Einheitlichkeit sind alle Definitionen im types-Modul pydantic-Klassen.

import google.generativeai as genai

model = genai.GenerativeModel(
  'gemini-1.5-flash',
    system_instruction='you are a story teller for kids under 5 years old',
    generation_config=genai.GenerationConfig(
      max_output_tokens=400,
      top_k=2,
      top_p=0.5,
      temperature=0.5,
      response_mime_type='application/json',
      stop_sequences=['\n'],
    )
)
response = model.generate_content('tell me a story in 100 words')

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
  generationConfig: {
    candidateCount: 1,
    stopSequences: ["x"],
    maxOutputTokens: 20,
    temperature: 1.0,
  },
});

const result = await model.generateContent(
  "Tell me a story about a magic backpack.",
);
console.log(result.response.text())

Nachher

Python

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
  model='gemini-2.0-flash',
  contents='Tell me a story in 100 words.',
  config=types.GenerateContentConfig(
      system_instruction='you are a story teller for kids under 5 years old',
      max_output_tokens= 400,
      top_k= 2,
      top_p= 0.5,
      temperature= 0.5,
      response_mime_type= 'application/json',
      stop_sequences= ['\n'],
      seed=42,
  ),
)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: "Tell me a story about a magic backpack.",
  config: {
    candidateCount: 1,
    stopSequences: ["x"],
    maxOutputTokens: 20,
    temperature: 1.0,
  },
});

console.log(response.text);

Sicherheitseinstellungen

So generieren Sie eine Antwort mit Sicherheitseinstellungen:

Vorher

Python

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content(
    'say something bad',
    safety_settings={
        'HATE': 'BLOCK_ONLY_HIGH',
        'HARASSMENT': 'BLOCK_ONLY_HIGH',
  }
)

JavaScript

import { GoogleGenerativeAI, HarmCategory, HarmBlockThreshold } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
  safetySettings: [
    {
      category: HarmCategory.HARM_CATEGORY_HARASSMENT,
      threshold: HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
    },
  ],
});

const unsafePrompt =
  "I support Martians Soccer Club and I think " +
  "Jupiterians Football Club sucks! Write an ironic phrase telling " +
  "them how I feel about them.";

const result = await model.generateContent(unsafePrompt);

try {
  result.response.text();
} catch (e) {
  console.error(e);
  console.log(result.response.candidates[0].safetyRatings);
}

Nachher

Python

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
  model='gemini-2.0-flash',
  contents='say something bad',
  config=types.GenerateContentConfig(
      safety_settings= [
          types.SafetySetting(
              category='HARM_CATEGORY_HATE_SPEECH',
              threshold='BLOCK_ONLY_HIGH'
          ),
      ]
  ),
)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const unsafePrompt =
  "I support Martians Soccer Club and I think " +
  "Jupiterians Football Club sucks! Write an ironic phrase telling " +
  "them how I feel about them.";

const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: unsafePrompt,
  config: {
    safetySettings: [
      {
        category: "HARM_CATEGORY_HARASSMENT",
        threshold: "BLOCK_ONLY_HIGH",
      },
    ],
  },
});

console.log("Finish reason:", response.candidates[0].finishReason);
console.log("Safety ratings:", response.candidates[0].safetyRatings);

Asynchron

Vorher

Python

Für die Verwendung des neuen SDK mit asyncio gibt es unter client.aio eine separate async-Implementierung jeder Methode.

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content_async(
    'tell me a story in 100 words'
)

Nachher

Python

from google import genai

client = genai.Client()

response = await client.aio.models.generate_content(
    model='gemini-2.0-flash', 
    contents='Tell me a story in 300 words.'
)

Chat

So starten Sie einen Chat und senden eine Nachricht an das Modell:

Vorher

Python

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
chat = model.start_chat()

response = chat.send_message(
    "Tell me a story in 100 words")
response = chat.send_message(
    "What happened after that?")

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const chat = model.startChat({
  history: [
    {
      role: "user",
      parts: [{ text: "Hello" }],
    },
    {
      role: "model",
      parts: [{ text: "Great to meet you. What would you like to know?" }],
    },
  ],
});
let result = await chat.sendMessage("I have 2 dogs in my house.");
console.log(result.response.text());
result = await chat.sendMessage("How many paws are in my house?");
console.log(result.response.text());

Nachher

Python

from google import genai

client = genai.Client()

chat = client.chats.create(model='gemini-2.0-flash')

response = chat.send_message(
    message='Tell me a story in 100 words')
response = chat.send_message(
    message='What happened after that?')

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const chat = ai.chats.create({
  model: "gemini-2.0-flash",
  history: [
    {
      role: "user",
      parts: [{ text: "Hello" }],
    },
    {
      role: "model",
      parts: [{ text: "Great to meet you. What would you like to know?" }],
    },
  ],
});

const response1 = await chat.sendMessage({
  message: "I have 2 dogs in my house.",
});
console.log("Chat response 1:", response1.text);

const response2 = await chat.sendMessage({
  message: "How many paws are in my house?",
});
console.log("Chat response 2:", response2.text);

Funktionsaufrufe

Vorher

Python

Im neuen SDK ist der automatische Funktionsaufruf standardmäßig aktiviert. Hier können Sie sie deaktivieren.

import google.generativeai as genai
from enum import Enum 

def get_current_weather(location: str) -> str:
    """Get the current whether in a given location.

    Args:
        location: required, The city and state, e.g. San Franciso, CA
        unit: celsius or fahrenheit
    """
    print(f'Called with: {location=}')
    return "23C"

model = genai.GenerativeModel(
    model_name="gemini-1.5-flash",
    tools=[get_current_weather]
)

response = model.generate_content("What is the weather in San Francisco?")
function_call = response.candidates[0].parts[0].function_call

Nachher

Python

from google import genai
from google.genai import types

client = genai.Client()

def get_current_weather(location: str) -> str:
    """Get the current whether in a given location.

    Args:
        location: required, The city and state, e.g. San Franciso, CA
        unit: celsius or fahrenheit
    """
    print(f'Called with: {location=}')
    return "23C"

response = client.models.generate_content(
  model='gemini-2.0-flash',
  contents="What is the weather like in Boston?",
  config=types.GenerateContentConfig(
      tools=[get_current_weather],
      automatic_function_calling={'disable': True},
  ),
)

function_call = response.candidates[0].content.parts[0].function_call

Automatischer Funktionsaufruf

Vorher

Python

Das alte SDK unterstützt nur den automatischen Funktionsaufruf im Chat. Im neuen SDK ist dies das Standardverhalten in generate_content.

import google.generativeai as genai

def get_current_weather(city: str) -> str:
    return "23C"

model = genai.GenerativeModel(
    model_name="gemini-1.5-flash",
    tools=[get_current_weather]
)

chat = model.start_chat(
    enable_automatic_function_calling=True)
result = chat.send_message("What is the weather in San Francisco?")

Nachher

Python

from google import genai
from google.genai import types
client = genai.Client()

def get_current_weather(city: str) -> str:
    return "23C"

response = client.models.generate_content(
  model='gemini-2.0-flash',
  contents="What is the weather like in Boston?",
  config=types.GenerateContentConfig(
      tools=[get_current_weather] 
  ),
)

Codeausführung

Die Codeausführung ist ein Tool, mit dem das Modell Python-Code generieren, ausführen und das Ergebnis zurückgeben kann.

Vorher

Python

import google.generativeai as genai

model = genai.GenerativeModel(
    model_name="gemini-1.5-flash",
    tools="code_execution"
)

result = model.generate_content(
  "What is the sum of the first 50 prime numbers? Generate and run code for "
  "the calculation, and make sure you get all 50.")

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({
  model: "gemini-1.5-flash",
  tools: [{ codeExecution: {} }],
});

const result = await model.generateContent(
  "What is the sum of the first 50 prime numbers? " +
    "Generate and run code for the calculation, and make sure you get " +
    "all 50.",
);

console.log(result.response.text());

Nachher

Python

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model='gemini-2.0-flash',
    contents='What is the sum of the first 50 prime numbers? Generate and run '
            'code for the calculation, and make sure you get all 50.',
    config=types.GenerateContentConfig(
        tools=[types.Tool(code_execution=types.ToolCodeExecution)],
    ),
)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });

const response = await ai.models.generateContent({
  model: "gemini-2.0-pro-exp-02-05",
  contents: `Write and execute code that calculates the sum of the first 50 prime numbers.
            Ensure that only the executable code and its resulting output are generated.`,
});

// Each part may contain text, executable code, or an execution result.
for (const part of response.candidates[0].content.parts) {
  console.log(part);
  console.log("\n");
}

console.log("-".repeat(80));
// The `.text` accessor concatenates the parts into a markdown-formatted text.
console.log("\n", response.text);

Suchgrundlagen

GoogleSearch (Gemini>=2.0) und GoogleSearchRetrieval (Gemini < 2.0) sind Tools, mit denen das Modell öffentliche Webdaten von Google abrufen kann, um die Antwort zu fundieren.

Vorher

Python

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content(
    contents="what is the Google stock price?",
    tools='google_search_retrieval'
)

Nachher

Python

from google import genai
from google.genai import types

client = genai.Client()

response = client.models.generate_content(
    model='gemini-2.0-flash',
    contents='What is the Google stock price?',
    config=types.GenerateContentConfig(
        tools=[
            types.Tool(
                google_search=types.GoogleSearch()
            )
        ]
    )
)

JSON-Antwort

Antworten im JSON-Format generieren.

Vorher

Python

Durch Angabe einer response_schema und Festlegen von response_mime_type="application/json" können Nutzer das Modell so einschränken, dass eine JSON-Antwort mit einer bestimmten Struktur ausgegeben wird. Das neue SDK verwendet pydantic-Klassen, um das Schema bereitzustellen. Sie können aber auch eine genai.types.Schema oder eine entsprechende dict übergeben. Sofern möglich, analysiert das SDK das zurückgegebene JSON und gibt das Ergebnis in response.parsed zurück. Wenn Sie eine pydantic-Klasse als Schema angegeben haben, wandelt das SDK diese JSON in eine Instanz der Klasse um.

import google.generativeai as genai
import typing_extensions as typing

class CountryInfo(typing.TypedDict):
    name: str
    population: int
    capital: str
    continent: str
    major_cities: list[str]
    gdp: int
    official_language: str
    total_area_sq_mi: int

model = genai.GenerativeModel(model_name="gemini-1.5-flash")
result = model.generate_content(
    "Give me information of the United States",
    generation_config=genai.GenerationConfig(
        response_mime_type="application/json",
        response_schema = CountryInfo
    ),
)

JavaScript

import { GoogleGenerativeAI, SchemaType } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");

const schema = {
  description: "List of recipes",
  type: SchemaType.ARRAY,
  items: {
    type: SchemaType.OBJECT,
    properties: {
      recipeName: {
        type: SchemaType.STRING,
        description: "Name of the recipe",
        nullable: false,
      },
    },
    required: ["recipeName"],
  },
};

const model = genAI.getGenerativeModel({
  model: "gemini-1.5-pro",
  generationConfig: {
    responseMimeType: "application/json",
    responseSchema: schema,
  },
});

const result = await model.generateContent(
  "List a few popular cookie recipes.",
);
console.log(result.response.text());

Nachher

Python

from google import genai
from pydantic import BaseModel

client = genai.Client()

class CountryInfo(BaseModel):
    name: str
    population: int
    capital: str
    continent: str
    major_cities: list[str]
    gdp: int
    official_language: str
    total_area_sq_mi: int

response = client.models.generate_content( 
    model='gemini-2.0-flash', 
    contents='Give me information of the United States.', 
    config={ 
        'response_mime_type': 'application/json',
        'response_schema': CountryInfo, 
    }, 
)

response.parsed

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: "List a few popular cookie recipes.",
  config: {
    responseMimeType: "application/json",
    responseSchema: {
      type: "array",
      items: {
        type: "object",
        properties: {
          recipeName: { type: "string" },
          ingredients: { type: "array", items: { type: "string" } },
        },
        required: ["recipeName", "ingredients"],
      },
    },
  },
});
console.log(response.text);

Dateien

Hochladen

So laden Sie eine Datei hoch:

Vorher

Python

import requests
import pathlib
import google.generativeai as genai

# Download file
response = requests.get(
    'https://storage.googleapis.com/generativeai-downloads/data/a11.txt')
pathlib.Path('a11.txt').write_text(response.text)

file = genai.upload_file(path='a11.txt')

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.generate_content([
    'Can you summarize this file:', 
    my_file
])
print(response.text)

Nachher

Python

import requests
import pathlib
from google import genai

client = genai.Client()

# Download file
response = requests.get(
    'https://storage.googleapis.com/generativeai-downloads/data/a11.txt')
pathlib.Path('a11.txt').write_text(response.text)

my_file = client.files.upload(file='a11.txt')

response = client.models.generate_content(
    model='gemini-2.0-flash', 
    contents=[
        'Can you summarize this file:', 
        my_file
    ]
)
print(response.text)

Auflisten und abrufen

Liste der hochgeladenen Dateien auflisten und eine hochgeladene Datei mit einem Dateinamen abrufen:

Vorher

Python

import google.generativeai as genai

for file in genai.list_files():
  print(file.name)

file = genai.get_file(name=file.name)

Nachher

Python

from google import genai
client = genai.Client()

for file in client.files.list():
    print(file.name)

file = client.files.get(name=file.name)

Löschen

So löschen Sie eine Datei:

Vorher

Python

import pathlib
import google.generativeai as genai

pathlib.Path('dummy.txt').write_text(dummy)
dummy_file = genai.upload_file(path='dummy.txt')

file = genai.delete_file(name=dummy_file.name)

Nachher

Python

import pathlib
from google import genai

client = genai.Client()

pathlib.Path('dummy.txt').write_text(dummy)
dummy_file = client.files.upload(file='dummy.txt')

response = client.files.delete(name=dummy_file.name)

Kontext-Caching

Mit dem Kontext-Caching kann der Nutzer die Inhalte einmal an das Modell übergeben, die Eingabe-Tokens im Cache speichern und dann bei nachfolgenden Aufrufen auf die im Cache gespeicherten Tokens verweisen, um die Kosten zu senken.

Vorher

Python

import requests
import pathlib
import google.generativeai as genai
from google.generativeai import caching

# Download file
response = requests.get(
    'https://storage.googleapis.com/generativeai-downloads/data/a11.txt')
pathlib.Path('a11.txt').write_text(response.text)

# Upload file
document = genai.upload_file(path="a11.txt")

# Create cache
apollo_cache = caching.CachedContent.create(
    model="gemini-1.5-flash-001",
    system_instruction="You are an expert at analyzing transcripts.",
    contents=[document],
)

# Generate response
apollo_model = genai.GenerativeModel.from_cached_content(
    cached_content=apollo_cache
)
response = apollo_model.generate_content("Find a lighthearted moment from this transcript")

JavaScript

import { GoogleAICacheManager, GoogleAIFileManager } from "@google/generative-ai/server";
import { GoogleGenerativeAI } from "@google/generative-ai";

const cacheManager = new GoogleAICacheManager("GOOGLE_API_KEY");
const fileManager = new GoogleAIFileManager("GOOGLE_API_KEY");

const uploadResult = await fileManager.uploadFile("path/to/a11.txt", {
  mimeType: "text/plain",
});

const cacheResult = await cacheManager.create({
  model: "models/gemini-1.5-flash",
  contents: [
    {
      role: "user",
      parts: [
        {
          fileData: {
            fileUri: uploadResult.file.uri,
            mimeType: uploadResult.file.mimeType,
          },
        },
      ],
    },
  ],
});

console.log(cacheResult);

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModelFromCachedContent(cacheResult);
const result = await model.generateContent(
  "Please summarize this transcript.",
);
console.log(result.response.text());

Nachher

Python

import requests
import pathlib
from google import genai
from google.genai import types

client = genai.Client()

# Check which models support caching.
for m in client.models.list():
  for action in m.supported_actions:
    if action == "createCachedContent":
      print(m.name) 
      break

# Download file
response = requests.get(
    'https://storage.googleapis.com/generativeai-downloads/data/a11.txt')
pathlib.Path('a11.txt').write_text(response.text)

# Upload file
document = client.files.upload(file='a11.txt')

# Create cache
model='gemini-1.5-flash-001'
apollo_cache = client.caches.create(
      model=model,
      config={
          'contents': [document],
          'system_instruction': 'You are an expert at analyzing transcripts.',
      },
  )

# Generate response
response = client.models.generate_content(
    model=model,
    contents='Find a lighthearted moment from this transcript',
    config=types.GenerateContentConfig(
        cached_content=apollo_cache.name,
    )
)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const filePath = path.join(media, "a11.txt");
const document = await ai.files.upload({
  file: filePath,
  config: { mimeType: "text/plain" },
});
console.log("Uploaded file name:", document.name);
const modelName = "gemini-1.5-flash";

const contents = [
  createUserContent(createPartFromUri(document.uri, document.mimeType)),
];

const cache = await ai.caches.create({
  model: modelName,
  config: {
    contents: contents,
    systemInstruction: "You are an expert analyzing transcripts.",
  },
});
console.log("Cache created:", cache);

const response = await ai.models.generateContent({
  model: modelName,
  contents: "Please summarize this transcript",
  config: { cachedContent: cache.name },
});
console.log("Response text:", response.text);

Tokens zählen

Anzahl der Tokens in einer Anfrage zählen

Vorher

Python

import google.generativeai as genai

model = genai.GenerativeModel('gemini-1.5-flash')
response = model.count_tokens(
    'The quick brown fox jumps over the lazy dog.')

JavaScript

 import { GoogleGenerativeAI } from "@google/generative-ai";

 const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY+);
 const model = genAI.getGenerativeModel({
   model: "gemini-1.5-flash",
 });

 // Count tokens in a prompt without calling text generation.
 const countResult = await model.countTokens(
   "The quick brown fox jumps over the lazy dog.",
 );

 console.log(countResult.totalTokens); // 11

 const generateResult = await model.generateContent(
   "The quick brown fox jumps over the lazy dog.",
 );

 // On the response for `generateContent`, use `usageMetadata`
 // to get separate input and output token counts
 // (`promptTokenCount` and `candidatesTokenCount`, respectively),
 // as well as the combined token count (`totalTokenCount`).
 console.log(generateResult.response.usageMetadata);
 // candidatesTokenCount and totalTokenCount depend on response, may vary
 // { promptTokenCount: 11, candidatesTokenCount: 124, totalTokenCount: 135 }

Nachher

Python

from google import genai

client = genai.Client()

response = client.models.count_tokens(
    model='gemini-2.0-flash',
    contents='The quick brown fox jumps over the lazy dog.',
)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const prompt = "The quick brown fox jumps over the lazy dog.";
const countTokensResponse = await ai.models.countTokens({
  model: "gemini-2.0-flash",
  contents: prompt,
});
console.log(countTokensResponse.totalTokens);

const generateResponse = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: prompt,
});
console.log(generateResponse.usageMetadata);

Bilder erstellen

Bilder generieren:

Vorher

Python

#pip install https://github.com/google-gemini/generative-ai-python@imagen
import google.generativeai as genai

imagen = genai.ImageGenerationModel(
    "imagen-3.0-generate-001")
gen_images = imagen.generate_images(
    prompt="Robot holding a red skateboard",
    number_of_images=1,
    safety_filter_level="block_low_and_above",
    person_generation="allow_adult",
    aspect_ratio="3:4",
)

Nachher

Python

from google import genai

client = genai.Client()

gen_images = client.models.generate_images(
    model='imagen-3.0-generate-001',
    prompt='Robot holding a red skateboard',
    config=types.GenerateImagesConfig(
        number_of_images= 1,
        safety_filter_level= "BLOCK_LOW_AND_ABOVE",
        person_generation= "ALLOW_ADULT",
        aspect_ratio= "3:4",
    )
)

for n, image in enumerate(gen_images.generated_images):
    pathlib.Path(f'{n}.png').write_bytes(
        image.image.image_bytes)

Inhalte einbetten

Inhalteinbettungen generieren

Vorher

Python

import google.generativeai as genai

response = genai.embed_content(
  model='models/text-embedding-004',
  content='Hello world'
)

JavaScript

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI("GOOGLE_API_KEY");
const model = genAI.getGenerativeModel({
  model: "text-embedding-004",
});

const result = await model.embedContent("Hello world!");

console.log(result.embedding);

Nachher

Python

from google import genai

client = genai.Client()

response = client.models.embed_content(
  model='text-embedding-004',
  contents='Hello world',
)

JavaScript

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

const ai = new GoogleGenAI({ apiKey: "GOOGLE_API_KEY" });
const text = "Hello World!";
const result = await ai.models.embedContent({
  model: "text-embedding-004",
  contents: text,
  config: { outputDimensionality: 10 },
});
console.log(result.embeddings);

Modell abstimmen

Ein abgestimmtes Modell erstellen und verwenden.

Das neue SDK vereinfacht die Optimierung mit client.tunings.tune. Damit wird der Optimierungsjob gestartet und es wird gewartet, bis der Job abgeschlossen ist.

Vorher

Python

import google.generativeai as genai
import random

# create tuning model
train_data = {} 
for i in range(1, 6): 
  key = f'input {i}' 
  value = f'output {i}' 
  train_data[key] = value

name = f'generate-num-{random.randint(0,10000)}'
operation = genai.create_tuned_model(
    source_model='models/gemini-1.5-flash-001-tuning',
    training_data=train_data,
    id = name,
    epoch_count = 5,
    batch_size=4,
    learning_rate=0.001,
)
# wait for tuning complete
tuningProgress = operation.result()

# generate content with the tuned model
model = genai.GenerativeModel(model_name=f'tunedModels/{name}')
response = model.generate_content('55')

Nachher

Python

from google import genai
from google.genai import types

client = genai.Client()

# Check which models are available for tuning.
for m in client.models.list():
  for action in m.supported_actions:
    if action == "createTunedModel":
      print(m.name) 
      break

# create tuning model
training_dataset=types.TuningDataset(
        examples=[
            types.TuningExample(
                text_input=f'input {i}',
                output=f'output {i}',
            )
            for i in range(5)
        ],
    )
tuning_job = client.tunings.tune(
    base_model='models/gemini-1.5-flash-001-tuning',
    training_dataset=training_dataset,
    config=types.CreateTuningJobConfig(
        epoch_count= 5,
        batch_size=4,
        learning_rate=0.001,
        tuned_model_display_name="test tuned model"
    )
)

# generate content with the tuned model
response = client.models.generate_content(
    model=tuning_job.tuned_model.model,
    contents='55', 
)

JavaScript im Browser

Wenn Sie die Gemini API im Browser verwenden möchten, können Sie das Gen AI SDK für JavaScript aus einem CDN importieren, wie im folgenden Beispiel gezeigt:

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
    <title>Using My Package</title>
  </head>
  <body>
    <script type="module">
      import {GoogleGenAI} from 'https://cdn.jsdelivr.net/npm/@google/genai@latest/+esm'

          const ai = new GoogleGenAI({apiKey: "GOOGLE_API_KEY"});

          async function main() {
            const response = await ai.models.generateContent({
              model: 'gemini-2.0-flash-001',
              contents: 'Why is the sky blue?',
            });
            console.log(response.text);
          }

          main();
    </script>
  </body>
</html>

Wenn Sie diesen Code lokal ausführen möchten, sollten Sie einen Server wie http-server verwenden. Wenn Sie versuchen, den Code aus einem lokalen Dateisystem auszuführen, kann ein CORS-Fehler auftreten.

Auf die Google Gen AI SDKs umstellen

SDK Installieren

Python

JavaScript

Python

JavaScript

Authentifizieren

Python

JavaScript

Python

JavaScript

Inhaltserstellung

Python

JavaScript

Python

JavaScript

Python

JavaScript

Python

JavaScript

Streaming

Python

JavaScript

Python

JavaScript

Optionale Argumente

Python

JavaScript

Python

JavaScript

Sicherheits­einstellungen

Python

JavaScript

Python

JavaScript

Asynchron

Python

Python

Chat

Python

JavaScript

Python

JavaScript

Funktionsaufrufe

Python

Python

Automatischer Funktionsaufruf

Python

Python

Codeausführung

Python

JavaScript

Python

JavaScript

Suchgrundlagen

Python

Python

JSON-Antwort

Python

JavaScript

Python

JavaScript

Dateien

Hochladen

Python

Python

Auflisten und abrufen

Python

Python

Löschen

Python

Python

Kontext-Caching

Python

JavaScript

Python

JavaScript

Tokens zählen

Python

JavaScript

Sicherheitseinstellungen