Berpikir

Model pemikiran dilatih untuk menghasilkan "proses pemikiran" yang dilalui model sebagai bagian dari responsnya. Akibatnya, model pemikiran mampu memiliki kemampuan penalaran yang lebih kuat dalam responsnya daripada model dasar yang setara.

Proses berpikir aktif secara default. Saat menggunakan Vertex AI Studio, Anda dapat melihat proses pemikiran lengkap bersama dengan respons yang dihasilkan model.

Model yang didukung

Pemikiran didukung dalam model berikut:

Menggunakan pemikiran

Konsol

  1. Buka Vertex AI Studio > Create prompt.
  2. Di panel Model, klik Switch model, lalu pilih salah satu model yang didukung dari menu.
    • Anggaran pemikiran ditetapkan ke Otomatis secara default saat model dimuat (khusus Gemini 2.5 Flash).
  3. (Opsional) Berikan beberapa petunjuk mendetail tentang cara model memformat responsnya di kolom Petunjuk sistem.
  4. Masukkan perintah di kolom Tulis perintah Anda.
  5. Klik Run.

Gemini akan menampilkan respons setelah respons dibuat. Bergantung pada kompleksitas respons, pembuatan dapat memerlukan waktu beberapa detik.

Anda dapat melihat proses pemikiran ringkas model dengan meluaskan panel Pemikiran. Untuk menonaktifkan penalaran, tetapkan Anggaran penalaran ke Nonaktif.

Gen AI SDK for Python

Instal

pip install --upgrade google-genai

Untuk mempelajari lebih lanjut, lihat dokumentasi referensi SDK.

Tetapkan variabel lingkungan untuk menggunakan Gen AI SDK dengan Vertex AI:

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

from google import genai

client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.5-pro-preview-03-25",
    contents="solve x^2 + 4x + 4 = 0",
)
print(response.text)
# Example Response:
#     Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
#
#     We can solve this equation by factoring, using the quadratic formula, or by recognizing it as a perfect square trinomial.
#
#     **Method 1: Factoring**
#
#     1.  We need two numbers that multiply to the constant term (4) and add up to the coefficient of the x term (4).
#     2.  The numbers 2 and 2 satisfy these conditions: 2 * 2 = 4 and 2 + 2 = 4.
#     3.  So, we can factor the quadratic as:
#         (x + 2)(x + 2) = 0
#         or
#         (x + 2)² = 0
#     4.  For the product to be zero, the factor must be zero:
#         x + 2 = 0
#     5.  Solve for x:
#         x = -2
#
#     **Method 2: Quadratic Formula**
#
#     The quadratic formula for an equation ax² + bx + c = 0 is:
#     x = [-b ± sqrt(b² - 4ac)] / (2a)
#
#     1.  In our equation x² + 4x + 4 = 0, we have a=1, b=4, and c=4.
#     2.  Substitute these values into the formula:
#         x = [-4 ± sqrt(4² - 4 * 1 * 4)] / (2 * 1)
#         x = [-4 ± sqrt(16 - 16)] / 2
#         x = [-4 ± sqrt(0)] / 2
#         x = [-4 ± 0] / 2
#         x = -4 / 2
#         x = -2
#
#     **Method 3: Perfect Square Trinomial**
#
#     1.  Notice that the expression x² + 4x + 4 fits the pattern of a perfect square trinomial: a² + 2ab + b², where a=x and b=2.
#     2.  We can rewrite the equation as:
#         (x + 2)² = 0
#     3.  Take the square root of both sides:
#         x + 2 = 0
#     4.  Solve for x:
#         x = -2
#
#     All methods lead to the same solution.
#
#     **Answer:**
#     The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

Mengontrol anggaran pemikiran

Khusus untuk Gemini 2.5 Flash, Anda dapat mengontrol seberapa banyak model berpikir selama responsnya. Batas atas ini disebut anggaran pemikiran dan berlaku untuk proses pemikiran lengkap model. Secara default, model secara otomatis mengontrol jumlah pemikirannya hingga maksimum 8.192 token. Setelan default ini berlaku untuk Gemini 2.5 Flash dan Gemini 2.5 Pro.

Gemini 2.5 Flash memungkinkan Anda menetapkan batas atas jumlah token secara manual dalam situasi saat Anda mungkin memerlukan lebih banyak atau lebih sedikit token daripada anggaran pemikiran default. Anda dapat menetapkan batas token yang lebih rendah untuk tugas yang kurang kompleks, atau batas yang lebih tinggi untuk tugas yang lebih kompleks.

Anggaran pemikiran maksimum yang dapat Anda tetapkan adalah 24.576 token, dan minimum yang dapat Anda tetapkan dan masih mengaktifkan pemikiran adalah 1. Namun, nilai minimum untuk anggaran pemikiran adalah 1.024 token, yang berarti nilai apa pun yang Anda tetapkan di bawah 1.024 token akan direset ke 1.024 di API.

Jika Anda menetapkan anggaran penalaran ke 0, penalaran akan dinonaktifkan.

Konsol

  1. Buka Vertex AI Studio > Create prompt.
  2. Di panel Model, klik Switch model, lalu pilih salah satu model yang didukung dari menu.
  3. Untuk Anggaran pemikiran (khusus Gemini 2.5 Flash), tetapkan ke Manual, lalu gunakan penggeser untuk menyesuaikan batas anggaran pemikiran.

Gen AI SDK untuk Python

Gunakan kolom thinking_budget di ThinkingConfig untuk menetapkan anggaran pertimbangan.

response = client.models.generate_content(
  model=MODEL_ID,
  contents="PROMPT",
  config=GenerateContentConfig(
    thinking_config=ThinkingConfig(
        thinking_budget=THINKING_BUDGET,
    )
  )
)

print(response.text))
print(response.usage_metadata.thoughts_token_count) #Output thought token count
print(response.usage_metadata.total_token_count) #Output thought and response token count
       

Teknik perintah untuk model pemikiran

Perintah yang efektif sangat penting untuk memaksimalkan manfaat model pemikiran Gemini. Bagian ini menguraikan beberapa praktik perintah untuk model pemikiran.

Memulai

Mulailah dengan petunjuk umum yang menjelaskan hasil yang diinginkan. Mulailah dengan perintah sederhana dan amati pemikiran awal model tentang cara mengatasi tantangan.

Describe the most unusual or striking architectural feature you've ever seen in a building or structure.
  
<...>
The most unusual architectural feature that has truly stayed with me is the "floating roof" of the
  Heydar Aliyev Center in Baku, Azerbaijan, designed by Zaha Hadid Architects.

Visually, it's breathtaking. Imagine a vast, undulating landscape of pure white, seemingly draped
over the building. It's not just a roof in the traditional sense; it's an extension of the ground,
flowing seamlessly upwards and over the building's various spaces before curving back down to meet
the earth again. There are no sharp angles, no rigid lines. Instead, everything is fluid, organic,
and continuous. It resembles a giant, pristine white wave frozen in motion, or perhaps a sand dune
sculpted by an unseen wind.
<...>
  

Memberikan Petunjuk Langkah demi Langkah

Jika upaya awal tidak menghasilkan hasil yang diinginkan, tingkatkan kualitas perintah Anda dengan memberikan petunjuk langkah demi langkah yang lebih eksplisit untuk memandu Gemini melalui proses pemecahan masalah untuk pendekatan yang lebih terfokus. Hal ini memungkinkan Anda mengarahkan pemahaman awal model tentang tugas dengan saran dan panduan eksplisit.

Now imagine that architectural feature is not just for looks, but has a specific function or
purpose related to the building's environment or the people who use it. Explain what that
function could be and how it enhances the building's overall design and usability.
  
<...>
Let's imagine that the "floating roof" of the Heydar Aliyev Center is not purely aesthetic but
serves a crucial environmental and user-centric function: it's designed as a sophisticated climate
moderator and natural ventilation system for the Baku environment.

Here's how this function would work and enhance the building:

Function: Passive Climate Control and Natural Ventilation System

Shading and Solar Heat Mitigation: The undulating curves of the white GFRC roof are strategically
shaped and oriented to provide optimal shading throughout the day, year-round. Baku experiences
intense sun, especially during the summer. The overhanging curves, acting like giant brise-soleils,
would block direct sunlight from hitting the building's glass facade, significantly reducing solar
heat gain. The varying heights and depths of the curves would create dynamic shade patterns, ensuring
that different parts of the building are shaded at different times of the day, optimizing comfort
and reducing the need for excessive air conditioning. The white color of the GFRC further enhances
this by reflecting a large portion of the solar radiation.
<...>
  

Perintah Multishot dengan Pemikiran

Perintah multishot yang dikombinasikan dengan pemikiran dapat lebih meningkatkan pemahaman Gemini dan meningkatkan akurasi responsnya. Berikan beberapa contoh pasangan input-output, yang menunjukkan perilaku dan format output yang diinginkan dalam perintah Anda.

Example 1:
User: What is the tallest mountain in the world?
Assistant: Mount Everest

Example 2:
User: What is the largest ocean?
Assistant: Pacific Ocean

User: What is the longest river in the world?
Assistant:
  
Amazon River
  

Menentukan Output dan Perilaku

Saat mem-build aplikasi tempat pengguna akan berinteraksi langsung dengan model, Anda dapat memberikan panduan tentang bagaimana output dan respons Gemini akan terdengar dan diformat.

Petunjuk Sistem

Petunjuk sistem adalah serangkaian petunjuk yang diproses model sebelum memproses perintah. Model ini dipanggil setiap kali model diminta dan memberi tahu model bagaimana Anda ingin model tersebut berperilaku dan merespons. Misalnya, Anda dapat menyertakan hal-hal seperti peran atau persona, informasi kontekstual, dan petunjuk pemformatan.

System Instruction: You are a helpful and concise coding tutor. Always provide code examples and explain them briefly.

User Prompt: Explain what is a closure in Javascript and give an example.
  
    function outerFunction(outerVar) {
      function innerFunction(innerVar) {
        console.log(outerVar); // Accessing outerVar from outerFunction's scope
        console.log(innerVar);
      }
      return innerFunction;
    }

    const closureExample = outerFunction('I am from outer');
    closureExample('I am from inner');

Explanation:

A closure is created when a function (innerFunction in this example) is defined inside another function
(outerFunction) and the inner function remembers and has access to the variables from the outer
function's scope, even after the outer function has finished executing.

In the example:

outerFunction is called with 'I am from outer' and returns innerFunction.

closureExample now holds a reference to innerFunction.

When closureExample('I am from inner') is called, innerFunction executes.

Even though outerFunction has already finished, innerFunction can still access and use outerVar
(which is 'I am from outer') because of the closure.

In essence, the innerFunction "closes over" the variables of its outer function's scope, creating
a closure.
  

Verifikasi dan Refleksi

Sertakan langkah-langkah verifikasi tertentu dalam Petunjuk Sistem atau perintah Anda secara langsung. Misalnya, minta Gemini untuk memverifikasi sumbernya, meninjau alasannya, mengidentifikasi potensi error, dan memeriksa jawaban akhirnya.

    Verify the following statement and provide your sources: The capital of Brazil is Rio de Janeiro.
  
The statement "The capital of Brazil is Rio de Janeiro" is incorrect.

The current capital of Brazil is Brasília.

Rio de Janeiro was the capital of Brazil for a significant period, from 1763 to 1960. However, the
capital was moved to Brasília in 1960 as part of a plan to develop the country's interior and create
a more centrally located capital.

Verification and Sources:

You can easily verify this information from numerous reliable sources:

Encyclopedias:

Britannica: Searching for "Brazil" on Britannica will clearly state Brasília as the capital.

https://www.britannica.com/place/Brazil (Look for the "Capital" information in the introductory summary or "Geography" section)

Wikipedia: The Wikipedia article for "Brazil" also states Brasília as the capital.

https://en.wikipedia.org/wiki/Brazil (Look in the infobox or introductory section)

Government and Official Sources:

CIA World Factbook: This is a highly reliable source for country information. Searching for "Brazil"
will list Brasília as the capital.

https://www.cia.gov/the-world-factbook/countries/brazil/ (Look under "Government" > "Capital")

Official Website of the Brazilian Government (if accessible and in English): While navigating official
government websites can sometimes be complex, they would definitively list Brasília as the capital.

Geographic Resources:

National Geographic: Their website and publications will confirm Brasília as the capital of Brazil.

Atlases and Geography Textbooks: Any modern atlas or geography textbook will list Brasília as the capital.

Why the confusion?

The confusion might arise because:

Rio de Janeiro is a very famous Brazilian city: It's a major tourist destination, known for its
beaches, Carnival, and iconic landmarks like Christ the Redeemer. Its past status as capital adds
to its historical significance and public recognition.

Historical context: Rio de Janeiro was the capital for a long time. People who learned about Brazil
in the past might remember it as the capital.

In conclusion, the statement is false. The capital of Brazil is Brasília, not Rio de Janeiro. Rio
de Janeiro was the former capital but is no longer the current capital.

You can confidently use the sources listed above to verify this information.
  

Proses Debug dan Pengendalian

Google AI Studio memberi developer akses ke pemikiran model di UI. Hal ini berguna bagi developer yang meninjau perintah Anda saat men-debug:

Menganalisis Proses Pemikiran

Tinjau dengan cermat proses pemikiran Gemini untuk mengidentifikasi area yang mungkin salah. Analisis ini dapat memberikan petunjuk berharga untuk meningkatkan kualitas perintah dan mendapatkan respons yang diharapkan secara konsisten dalam aplikasi Anda.

Contoh Skenario: Jika proses berpikir Gemini menunjukkan bahwa Gemini salah memahami langkah dalam petunjuk yang kompleks, Anda dapat meningkatkan kualitas perintah untuk mengklarifikasi langkah tertentu tersebut.

Step 1: Summarize the following article about quantum physics.
Step 2: Translate the summary into Spanish.
Step 3: Extract the key entities from the Spanish summary.

Article: ... [Article Text] ...
The user wants me to process an article about Google's new quantum chip called Willow in three steps:
Step 1: Summarize the article.
Step 2: Translate the summary into Spanish.
Step 3: Extract the key entities from the Spanish summary.

Let's break down each step.

Step 1: Summarize the article.
I need to read the article and identify the main points. The article is about Google's new quantum
chip, Willow, and its achievements. The key achievements are:

Exponential error reduction as qubits scale up.

Outperforming supercomputers in a benchmark computation (RCS).

Willow is a step towards commercially relevant quantum computing.

It's the first system below threshold for quantum error correction.

It achieved a benchmark computation in under 5 minutes that would take a supercomputer 10 septillion years.

It was fabricated in a new facility.

It has state-of-the-art performance and high quality qubits.

Google is looking towards real-world applications with Willow.

Quantum computing will benefit AI.

I will synthesize these points into a concise summary.

Step 2: Translate the summary into Spanish.
Once I have the summary in English, I will translate it into Spanish. I need to ensure the translation
is accurate and natural-sounding in Spanish.

Step 3: Extract the key entities from the Spanish summary.
After translating the summary, I will identify and extract the key entities. Key entities are typically
nouns or noun phrases that represent important objects, concepts, or actors. In this context, they
will likely include:

Names of chips (Willow, Sycamore)

Companies/Organizations (Google Quantum AI, Google Research)

Technologies (quantum chip, quantum computer, qubits, quantum error correction, superconducting
quantum system, classical computers, supercomputers, AI)

Benchmarks (random circuit sampling, RCS)

People (Julian Kelly, Peter Shor, David Deutsch, Sergio Boixo, Hartmut Neven, John Preskill)

Concepts (exponential error reduction, below threshold, beyond breakeven, state-of-the-art performance,
commercially relevant applications, quantum mechanics, multiverse, T1 times, system benchmarks,
algorithmic benchmarks)

I will need to carefully review the Spanish summary to identify these entities and list them out.

Provide Corrective Feedback

If you observe errors or inconsistencies in Gemini's reasoning, provide corrective feedback in your prompt and/or System Instructions to anticipate where the model's response may deviate from your desired outcome.

You are an expert in botany. When asked to identify a plant, focus on leaf shape, flower structure, and stem characteristics.

Identify this plant based on these characteristics: ... [Plant Characteristics Description] ...

Previous incorrect response focused on habitat only. Please disregard habitat and focus on morphology.
Previous incorrect response focused on habitat only. Please disregard habitat and focus on morphology.
Tabebuia vellosoi

Memanfaatkan Output Panjang dan Pemikiran Panjang

Pemikiran menghasilkan “pemikiran” sebagai bagian dari Output Token yang menampilkan penalaran mendetail Gemini. Untuk mendapatkan hasil maksimal dari output ini:

Meninjau Penalaran

Perhatikan dengan cermat proses penalaran Gemini (tersedia di UI Google AI Studio), cara Gemini membagi tugas, dan pilihan yang dibuat untuk output Anda. Hal ini dapat membantu Anda memahami bagaimana laporan tersebut sampai pada kesimpulannya.

Memberikan Panduan dalam Penalaran

Jika output yang diinginkan sangat panjang, sebaiknya berikan lebih banyak panduan dalam perintah untuk membatasi jumlah pemikiran yang diperlukan untuk menyelesaikan tugas yang disajikan dalam perintah. Hal ini memungkinkan Anda mencadangkan lebih banyak Output Token untuk respons Anda.

Contoh: Untuk laporan mendetail, Anda dapat menentukan bagian dan subbagian dalam perintah untuk memandu pemikiran Gemini dan menyusun output secara efisien.

Generate a detailed report on the impact of climate change on coastal ecosystems.

Report Structure:

Introduction

Rising Sea Levels
2.1. Impact on Mangroves
2.2. Impact on Coral Reefs

Ocean Acidification
3.1. Impact on Shellfish
3.2. Impact on Plankton

Extreme Weather Events
4.1. Increased Storm Intensity
4.2. Coastal Erosion

Conclusion

Provide detailed analysis within each section.
<...>
Climate Change Impact on Coastal Ecosystems: A Detailed Report

1. Introduction

Coastal ecosystems, the dynamic interface between land and sea, are among the most productive and
biodiverse environments on Earth. They provide crucial ecosystem services, including coastal protection,
fisheries, carbon sequestration, and support for a vast array of species. However, these vital
ecosystems are increasingly threatened by the multifaceted impacts of climate change. Driven by
anthropogenic greenhouse gas emissions, climate change is manifesting in several interconnected ways
that are profoundly altering the physical and chemical conditions of coastal environments. This report
will delve into the key impacts of climate change on coastal ecosystems, focusing on rising sea levels,
ocean acidification, and extreme weather events, and their specific consequences for critical habitats
like mangroves and coral reefs, and key organisms like shellfish and plankton. Understanding these
impacts is crucial for developing effective conservation and management strategies to mitigate the
damage and enhance the resilience of these invaluable ecosystems.

2. Rising Sea Levels

Rising sea levels are a direct and significant consequence of global warming, driven by thermal
expansion of seawater and the melting of land ice (glaciers and ice sheets). This phenomenon poses a
direct threat to low-lying coastal ecosystems by inundating habitats, altering salinity regimes, and
increasing erosion rates. The rate of sea level rise is accelerating, and projections for the 21st
century indicate a continued upward trend, with potentially devastating consequences for coastal
environments.

2.1. Impact on Mangroves

Mangrove forests are unique coastal ecosystems found in tropical and subtropical intertidal zones.
They provide numerous benefits, including coastal protection against storms, nursery grounds for
fish and invertebrates, and significant carbon sequestration...
<...>

Apa langkah selanjutnya?

Coba gunakan model pemikiran untuk Anda sendiri dengan notebook Colab, atau buka konsol Vertex AI dan coba minta model untuk Anda sendiri.