Halaman ini diterjemahkan oleh Cloud Translation API.

Bermigrasi dari Gemini 1.5 API ke Gemini 2.0 API di Vertex AI

Panduan ini menunjukkan cara bermigrasi dari model Gemini 1.0 dan Gemini 1.5 (Flash dan Pro) ke model Gemini 2.0.

Perbedaan antara Gemini 1.5 dan Gemini 2.0

Berikut adalah beberapa perbedaan antara Gemini 2.0 dan model 1.0 dan 1.5 kami:

Hanya Gemini 1.5 dan 2.0 yang didukung di Gen AI SDK baru kami. Gemini 1.0 tidak didukung. Hal ini penting karena struktur respons Anda bervariasi berdasarkan SDK yang Anda gunakan.
Gemini 2.0 mendukung Multimodal Live API dan pembuatan multimodal.
Kategori keamanannya berbeda. Untuk mempelajari perbedaannya, buka Perbedaan utama antara Gemini dan keluarga model lainnya.

Penyiapan

Vertex AI SDK

Jika Anda menggunakan kembali Vertex AI SDK , proses penyiapannya sama untuk model 1.5 dan 2.0. Untuk mengetahui informasi selengkapnya, lihat Pengantar Vertex AI SDK untuk Python.

Berikut adalah contoh kode singkat yang menginstal Vertex AI SDK untuk Python:

pip install google-cloud-aiplatform

import vertexai

vertexai.init(project="PROJECT_ID", location="LOCATION")

Ganti PROJECT_ID dengan Google Cloud project ID Anda, dan ganti LOCATION dengan lokasi project Google Cloud Anda (misalnya, us-central1).

Gen AI SDK

Jika Anda memilih untuk menggunakan Gen AI SDK, proses penyiapannya berbeda antara model 1.0 dan 1.5/2.0. Untuk informasi selengkapnya, buka SDK Gen AI Google.

Berikut adalah contoh kode singkat yang menginstal Gen AI SDK untuk Python:

pip install --upgrade --quiet google-genai pandas

from google import genai

client = genai.Client(vertexai=True, project= PROJECT_ID , location=LOCATION)

Ganti PROJECT_ID dengan Google Cloud project ID Anda, dan ganti LOCATION dengan lokasi project Google Cloud Anda (misalnya, us-central1).

Bermigrasi ke 2.0

Bagian berikut menyertakan petunjuk tentang cara bermigrasi ke Gemini 2.0 dari Vertex AI SDK dan Gen AI SDK baru kami.

Vertex AI SDK

Setiap pasangan contoh kode berikut menyertakan kode Gemini 1.5 dan kode Gemini 2.0 yang telah dimigrasikan dari kode 1.5.

Pembuatan teks sederhana

Contoh kode berikut menunjukkan perbedaan antara Gemini 1.5 API dan Gemini 2.0 API untuk membuat model pembuatan teks:

Gemini 1.5 Gemini 2.0

Gemini 1.5	Gemini 2.0
`from vertexai.generative_models import GenerativeModel model = GenerativeModel("gemini-1.5-flash-002") responses = model.generate_content("The opposite of hot is") for response in responses: print(response.text)`	`from vertexai.generative_models import GenerativeModel model = GenerativeModel("gemini-2.0-flash-001") responses = model.generate_content("The opposite of hot is") for response in responses: print(response.text)`


        
from vertexai.generative_models import GenerativeModel



model = GenerativeModel("gemini-1.5-flash-002")

responses = model.generate_content("The opposite of hot is")

for response in responses: print(response.text)


        
from vertexai.generative_models import GenerativeModel



model = GenerativeModel("gemini-2.0-flash-001")

responses = model.generate_content("The opposite of hot is")

for response in responses: print(response.text)

Pembuatan teks dengan parameter

Contoh kode berikut menunjukkan perbedaan antara Gemini 1.5 API dan Gemini 2.0 API untuk membuat model pembuatan teks, dengan parameter opsional:

Gemini 1.5 Gemini 2.0

Gemini 1.5	Gemini 2.0
from vertexai.generative_models import GenerativeModel model = GenerativeModel("gemini-1.5-flash-002") prompt = """ You are an expert at solving word problems.Solve the following problem: I have three houses, each with three cats.each cat owns 4 mittens, and a hat. Each mitten was knit from 7m of yarn, each hat from 4m.How much yarn was needed to make all the items? Think about it step by step, and show your work.""" responses = model.generate_content( prompt,generation_config={ "temperature": 0.1,"top_p": 1.0,"top_k": 40,"max_output_tokens": 800,} ) for response in responses: print(response.text)	from vertexai.generative_models import GenerativeModel model = GenerativeModel("gemini-2.0-flash-001") prompt = """ You are an expert at solving word problems.Solve the following problem: I have three houses, each with three cats.each cat owns 4 mittens, and a hat. Each mitten was knit from 7m of yarn, each hat from 4m.How much yarn was needed to make all the items? Think about it step by step, and show your work.""" responses = model.generate_content( prompt,generation_config={ "temperature": 0.1,"top_p": 1.0,"top_k": 40,"max_output_tokens": 800,} ) for response in responses: print(response.text)


        
from vertexai.generative_models import GenerativeModel



model = GenerativeModel("gemini-1.5-flash-002")



prompt = """ You are an expert at solving word problems.Solve the following problem: I have three houses, each with three cats.each cat owns 4 mittens, and a hat. Each mitten was knit from 7m of yarn, each hat from 4m.How much yarn was needed to make all the items? Think about it step by step, and show your work."""



responses = model.generate_content( prompt,generation_config={ "temperature": 0.1,"top_p": 1.0,"top_k": 40,"max_output_tokens": 800,} )



for response in responses:   print(response.text)


        
from vertexai.generative_models import GenerativeModel



model = GenerativeModel("gemini-2.0-flash-001")



prompt = """ You are an expert at solving word problems.Solve the following problem: I have three houses, each with three cats.each cat owns 4 mittens, and a hat. Each mitten was knit from 7m of yarn, each hat from 4m.How much yarn was needed to make all the items? Think about it step by step, and show your work."""



responses = model.generate_content( prompt,generation_config={ "temperature": 0.1,"top_p": 1.0,"top_k": 40,"max_output_tokens": 800,} )



for response in responses: print(response.text)

Gen AI SDK

Setiap pasangan contoh kode berikut menyertakan kode Gemini 1.5 dan kode Gemini 2.0 yang telah dimigrasikan dari kode 1.5:

Gemini 1.5 Gemini 2.0

Gemini 1.5	Gemini 2.0
`from vertexai.generative_models import GenerativeModel model = GenerativeModel("gemini-1.5-flash-002") responses = model.generate_content("The opposite of hot is") for response in responses: print(response.text)`	`from google import genai response = client.models.generate_content(model='gemini-2.0-flash-001', contents='What is your name?') print(response.text)`


        
from vertexai.generative_models import GenerativeModel



model = GenerativeModel("gemini-1.5-flash-002")

responses = model.generate_content("The opposite of hot is")

for response in responses: print(response.text)


        
from google import genai



response = client.models.generate_content(model='gemini-2.0-flash-001', contents='What is your name?')



print(response.text)