Model Gemini dapat diakses menggunakan library OpenAI (Python dan TypeScript/JavaScript) bersama dengan REST API. Hanya Google Cloud Auth yang didukung menggunakan library OpenAI di Vertex AI. Jika Anda belum menggunakan library OpenAI, sebaiknya panggil Gemini API secara langsung.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
#project_id = "PROJECT_ID"
location = "us-central1"
# # Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
response = client.chat.completions.create(
model="google/gemini-2.0-flash-001",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain to me how AI works"}
]
)
print(response.choices[0].message)
Apa yang berubah?
api_key=credentials.token: Untuk menggunakan autentikasi Google Cloud , dapatkan token autentikasiGoogle Cloud menggunakan kode contoh.base_url: Ini memberi tahu library OpenAI untuk mengirim permintaan ke Google Cloud, bukan URL default.model="google/gemini-2.0-flash-001": Pilih model Gemini yang kompatibel dari model yang dihosting Vertex.
Pemikiran
Model Gemini 2.5 dilatih untuk memikirkan masalah yang kompleks, sehingga menghasilkan penalaran yang jauh lebih baik. Gemini API dilengkapi dengan parameter"anggaran pemikiran" yang memberikan kontrol terperinci atas seberapa banyak model akan berpikir.
Tidak seperti Gemini API, OpenAI API menawarkan tiga tingkat kontrol pemikiran: "rendah", "sedang", dan "tinggi", yang dipetakan di balik layar ke anggaran token pemikiran 1K, 8K, dan 24K.
Untuk menonaktifkan pemikiran, tetapkan upaya penalaran ke "tidak ada".
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
#project_id = PROJECT_ID
location = "us-central1"
# # Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
response = client.chat.completions.create(
model="google/gemini-2.5-flash-preview-04-17",
reasoning_effort="low",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{
"role": "user",
"content": "Explain to me how AI works"
}
]
)
print(response.choices[0].message)
Streaming
Gemini API mendukung respons streaming.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
#project_id = PROJECT_ID
location = "us-central1"
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
response = client.chat.completions.create(
model="google/gemini-2.0-flash",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta)
Panggilan fungsi
Panggilan fungsi mempermudah untuk mendapatkan output data terstruktur dari model generatif dan didukung di Gemini API.
Python
import openai
from google.auth import default
import google.auth.transport.requests
# TODO(developer): Update and un-comment below lines
#project_id = PROJECT_ID
location = "us-central1"
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token
)
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. Chicago, IL",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
}
}
]
messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
response = client.chat.completions.create(
model="google/gemini-2.0-flash",
messages=messages,
tools=tools,
tool_choice="auto"
)
print(response)
Pemahaman gambar
Model Gemini bersifat multimodal secara native dan memberikan performa terbaik di kelasnya pada banyak tugas visi umum.
Python
from google.auth import default
import google.auth.transport.requests
import base64
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
location = "us-central1"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
# Function to encode the image
def encode_image(image_path):
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
# Getting the base64 string
#base64_image = encode_image("Path/to/image.jpeg")
response = client.chat.completions.create(
model="google/gemini-2.0-flash",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is in this image?",
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}"
},
},
],
}
],
)
print(response.choices[0])
Buat gambar
Python
from google.auth import default
import google.auth.transport.requests
import base64
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
location = "us-central1"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
# Function to encode the image
def encode_image(image_path):
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode('utf-8')
# Getting the base64 string
#base64_image = encode_image("Path/to/image.jpeg")
base64_image = encode_image("/content/wayfairsofa.jpg")
response = client.chat.completions.create(
model="google/gemini-2.0-flash",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is in this image?",
},
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{base64_image}"
},
},
],
}
],
)
print(response.choices[0])
Pemahaman audio
Menganalisis input audio:
Python
from google.auth import default
import google.auth.transport.requests
import base64
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
location = "us-central1"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
with open("/path/to/your/audio/file.wav", "rb") as audio_file:
base64_audio = base64.b64encode(audio_file.read()).decode('utf-8')
response = client.chat.completions.create(
model="gemini-2.0-flash",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Transcribe this audio",
},
{
"type": "input_audio",
"input_audio": {
"data": base64_audio,
"format": "wav"
}
}
],
}
],
)
print(response.choices[0].message.content)
Output terstruktur
Model Gemini dapat menghasilkan objek JSON dalam struktur yang Anda tentukan.
Python
from google.auth import default
import google.auth.transport.requests
from pydantic import BaseModel
from openai import OpenAI
# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
location = "us-central1"
# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
credentials.refresh(google.auth.transport.requests.Request())
# OpenAI Client
client = openai.OpenAI(
base_url=f"https://{location}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{location}/endpoints/openapi",
api_key=credentials.token,
)
class CalendarEvent(BaseModel):
name: str
date: str
participants: list[str]
completion = client.beta.chat.completions.parse(
model="google/gemini-2.0-flash",
messages=[
{"role": "system", "content": "Extract the event information."},
{"role": "user", "content": "John and Susan are going to an AI conference on Friday."},
],
response_format=CalendarEvent,
)
print(completion.choices[0].message.parsed)
Batasan saat ini
Kredensial aktif selama 1 jam secara default. Setelah habis masa berlakunya, token tersebut harus diperbarui. Lihat contoh kode ini untuk informasi selengkapnya.
Dukungan untuk library OpenAI masih dalam pratinjau saat kami memperluas dukungan fitur. Untuk mendapatkan bantuan terkait pertanyaan atau masalah, posting di Google Cloud Komunitas.
Langkah berikutnya
Manfaatkan potensi Gemini menggunakan Library AI Generatif Google.
Lihat contoh lainnya menggunakan Chat Completions API dengan sintaksis yang kompatibel dengan OpenAI.
Lihat model dan parameter Gemini yang didukung di halaman Ringkasan.