Compatibilidade com o OpenAI

Os modelos do Gemini podem ser acessados usando as bibliotecas da OpenAI (Python e TypeScript / Javascript) e a API REST. Somente a autenticação Google Cloud é compatível com a biblioteca OpenAI na Vertex AI. Se você ainda não usa as bibliotecas do OpenAI, recomendamos que chame a API Gemini diretamente.

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)

O que mudou?

  • api_key=credentials.token: para usar a autenticação Google Cloud , receba um token de autenticaçãoGoogle Cloud usando o código de amostra.

  • base_url: informa à biblioteca OpenAI para enviar solicitações a Google Cloud em vez do URL padrão.

  • model="google/gemini-2.0-flash-001": escolha um modelo do Gemini compatível entre os modelos hospedados pela Vertex.

Thinking

Os modelos Gemini 2.5 são treinados para pensar em problemas complexos, o que melhora muito o raciocínio. A API Gemini vem com um parâmetro de"orçamento de pensamento" que oferece controle refinado sobre quanto o modelo vai pensar.

Ao contrário da API Gemini, a API OpenAI oferece três níveis de controle de pensamento: "baixo", "médio" e "alto", que são mapeados nos bastidores para orçamentos de tokens de pensamento de 1K, 8K e 24K.

Para desativar o pensamento, defina o esforço de raciocínio como None.

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

A API Gemini é compatível com respostas de 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)

Chamadas de função

A chamada de função facilita a obtenção de saídas de dados estruturados de modelos generativos e é compatível com a API Gemini.

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)

Compreensão de imagens

Os modelos do Gemini são multimodais por natureza e oferecem o melhor desempenho da categoria em muitas tarefas comuns de visão.

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])

Gerar uma imagem

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])

Compreensão de áudio

Analisar entrada de áudio:

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)

Resposta estruturada

Os modelos do Gemini podem gerar objetos JSON em qualquer estrutura que você definir.

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)

Limitações atuais

  • Por padrão, os tokens de acesso duram uma hora. Depois da expiração, eles precisam ser atualizados. Consulte este exemplo de código para mais informações.

  • O suporte às bibliotecas da OpenAI ainda está em prévia enquanto estendemos o suporte a recursos. Se precisar de ajuda com dúvidas ou problemas, poste na Google Cloud comunidade.

A seguir