พรอมต์สำหรับโมเดลการคิดของ Gemini

คู่มือนี้จะอธิบายแนวทางปฏิบัติบางอย่างในการใช้งานโมเดลการคิดของ Gemini โมเดลเหล่านี้ช่วยให้นักพัฒนาแอปจัดการปัญหาที่ซับซ้อนได้โดยแบ่งปัญหาออกเป็นขั้นตอนเล็กๆ ที่จัดการได้ง่ายขึ้น แนวทางแบบทีละขั้นตอนนี้ไม่เพียงช่วยเพิ่มประสิทธิภาพในงานที่ท้าทาย แต่ยังให้ข้อมูลเชิงลึกที่มีคุณค่าเกี่ยวกับกระบวนการใช้เหตุผลของ Gemini แก่นักพัฒนาซอฟต์แวร์ ซึ่งแสดงใน UI ของ Google AI Studio ปัจจุบันโมเดลที่มีความสามารถในการคิด ได้แก่ Gemini 2.0 Flash Thinking และ Gemini 2.5 Pro Experimental ที่มีความสามารถในการคิดเวอร์ชันทดลอง

เทคนิคการเขียนพรอมต์

การพรอมต์ที่มีประสิทธิภาพเป็นสิ่งสําคัญในการเพิ่มประโยชน์สูงสุดของโมเดลการคิดของ Gemini เทคนิคที่ควรพิจารณามีดังนี้

เริ่มต้นใช้งาน

เริ่มต้นด้วยวิธีการทั่วไปที่อธิบายถึงผลลัพธ์ที่ต้องการ เริ่มต้นด้วยพรอมต์ง่ายๆ แล้วสังเกตความคิดเริ่มต้นของนายแบบ/นางแบบเกี่ยวกับวิธีรับมือกับปัญหา

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.
<...>
  

ระบุวิธีการทีละขั้นตอน

หากความพยายามครั้งแรกไม่ได้ผลลัพธ์ที่ต้องการ ให้ปรับแต่งพรอมต์โดยระบุวิธีการทีละขั้นตอนที่ชัดเจนมากขึ้นเพื่อนำทาง Gemini ผ่านกระบวนการแก้ปัญหาเพื่อให้แนวทางมีความมุ่งเน้นมากขึ้น ซึ่งช่วยให้คุณกำหนดความเข้าใจเบื้องต้นของโมเดลเกี่ยวกับงานด้วยคำแนะนำและแนวทางที่ชัดเจน

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.
<...>
  

พรอมต์แบบหลายช็อตที่มีการคิด

การใช้พรอมต์ภาพหลายภาพร่วมกับฟีเจอร์การคิดจะช่วยเพิ่มความเข้าใจของ Gemini และปรับปรุงความแม่นยำของคำตอบได้ ระบุตัวอย่างคู่อินพุต-เอาต์พุตหลายรายการที่แสดงลักษณะการทำงานและรูปแบบเอาต์พุตที่ต้องการในพรอมต์

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
  

การกําหนดเอาต์พุตและลักษณะการทํางาน

เมื่อสร้างแอปพลิเคชันที่ผู้ใช้จะโต้ตอบกับโมเดลโดยตรง คุณอาจต้องให้คําแนะนําเกี่ยวกับลักษณะและรูปแบบของเอาต์พุตและคําตอบของ Gemini

วิธีการของระบบ

คำสั่งของระบบคือชุดคำสั่งที่โมเดลประมวลผลก่อนที่จะประมวลผลพรอมต์ ระบบจะเรียกใช้ข้อมูลเหล่านี้ทุกครั้งที่ระบบแสดงข้อความแจ้งให้โมเดลแสดง และบอกให้โมเดลทราบว่าคุณต้องการให้ทํางานและตอบสนองอย่างไร เช่น คุณสามารถใส่ข้อมูลต่างๆ เช่น บทบาทหรือบุคลิก ข้อมูลตามบริบท และวิธีการจัดรูปแบบ

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.
  

การยืนยันและการไตร่ตรอง

ระบุขั้นตอนการยืนยันที่เฉพาะเจาะจงในวิธีการของระบบหรือพรอมต์ของคุณโดยตรง เช่น ขอให้ Gemini ยืนยันแหล่งที่มา ตรวจสอบเหตุผล ระบุข้อผิดพลาดที่อาจเกิดขึ้น และตรวจสอบคำตอบสุดท้าย

    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.
  

ใช้ประโยชน์จากเครื่องมือร่วมกับการคิด

โมเดลการคิดของ Gemini สามารถใช้เครื่องมือเพื่อดำเนินการนอกเหนือจากการสร้างข้อความได้ ซึ่งช่วยให้สามารถโต้ตอบกับระบบภายนอก เรียกใช้โค้ด หรือเข้าถึงข้อมูลแบบเรียลไทม์ รวมถึงนําผลลัพธ์มาใช้ในการหาเหตุผลและคำตอบสุดท้าย คุณเปิดใช้เครื่องมือได้ผ่านการกําหนดค่า API

เครื่องมือค้นหา

เครื่องมือค้นหาช่วยให้โมเดลสามารถค้นหาเครื่องมือค้นหาภายนอกเพื่อค้นหาข้อมูลล่าสุดหรือข้อมูลนอกเหนือจากข้อมูลที่ใช้ฝึก ซึ่งจะเป็นประโยชน์สำหรับคำถามเกี่ยวกับเหตุการณ์ล่าสุดหรือหัวข้อที่เฉพาะเจาะจงมาก

What were the major scientific breakthroughs announced last week?
  
Based on recent search results, here are some highlights from the past week in science:

*   **[Specific Breakthrough 1]:** [Brief description based on search results, e.g., A new study published in Nature details advancements in battery technology...]
*   **[Specific Breakthrough 2]:** [Brief description based on search results, e.g., Researchers at MIT announced progress in understanding dark matter...]
*   **[Specific Breakthrough 3]:** [Brief description based on search results, e.g., The James Webb Space Telescope captured new images revealing...]

(Note: The model would use the search tool to find relevant news and articles from the specified timeframe and synthesize the information. Grounding metadata citing the sources would also typically be available via the API.)
  

เครื่องมือการเรียกใช้โค้ด

เครื่องมือการเรียกใช้โค้ดช่วยให้โมเดลเขียนและเรียกใช้โค้ดได้ (เช่น Python) เพื่อทําการคํานวณ จัดการข้อมูล หรือแก้ปัญหาที่จัดการด้วยอัลกอริทึมได้ดีที่สุด โมเดลจะได้รับเอาต์พุตของโค้ดและนำไปใช้ในคำตอบได้

What is the sum of the first 50 prime numbers?
Generate and run Python code for the calculation, and make sure you get all 50.
Provide the final sum clearly.
  
Okay, I can calculate that. I will generate Python code to find the first 50 prime numbers and sum them up.

```python
def is_prime(num):
    if num < 2:
        return False
    for i in range(2, int(num**0.5) + 1):
        if num % i == 0:
            return False
    return True

primes = []
num = 2
while len(primes) < 50:
    if is_prime(num):
        primes.append(num)
    num += 1

total_sum = sum(primes)
print(total_sum)
```

Running the code...

Code Execution Result:
Outcome: OK
Output:

5117
Use code with caution.
The sum of the first 50 prime numbers is 5117.

Structured Output

คุณสามารถสั่งให้โมเดลจัดรูปแบบเอาต์พุตตามโครงสร้างที่เฉพาะเจาะจง เช่น JSON ซึ่งจะมีประโยชน์อย่างยิ่งสำหรับการผสานรวมเอาต์พุตของโมเดลเข้ากับแอปพลิเคชัน คุณสามารถระบุรูปแบบและสคีมาที่ต้องการในพรอมต์ได้โดยตรง หรือจะใช้พารามิเตอร์ API เช่น `response_mime_type` เพื่อการควบคุมที่มีประสิทธิภาพมากขึ้นก็ได้ (หากมี)

Provide a list of 3 famous physicists and their key contributions
in JSON format.
Use this JSON schema:

Physicist = {'name': str, 'contribution': str, 'era': str}
Return: list[Physicist]
```json
[
{
"name": "Albert Einstein",
"contribution": "Theory of Relativity (Special and General)",
"era": "Early 20th Century"
},
{
"name": "Isaac Newton",
"contribution": "Laws of Motion and Universal Gravitation",
"era": "Late 17th / Early 18th Century"
},
{
"name": "Marie Curie",
"contribution": "Pioneering research on radioactivity",
"era": "Late 19th / Early 20th Century"
}
]
```

การแก้ไขข้อบกพร่องและการควบคุม

Google AI Studio ช่วยให้นักพัฒนาแอปเข้าถึงความคิดของโมเดลใน UI ได้ ข้อมูลนี้มีประโยชน์เมื่อนักพัฒนาซอฟต์แวร์ตรวจสอบพรอมต์ของคุณขณะแก้ไขข้อบกพร่อง

วิเคราะห์กระบวนการคิด

ตรวจสอบกระบวนการคิดของ Gemini อย่างละเอียดเพื่อหาจุดที่อาจผิดพลาด การวิเคราะห์นี้ให้เบาะแสที่เป็นประโยชน์ในการปรับแต่งพรอมต์และรับคำตอบที่คาดหวังอย่างสม่ำเสมอในแอปพลิเคชัน

ตัวอย่างสถานการณ์: หากกระบวนการคิดของ Gemini แสดงให้เห็นว่าเข้าใจขั้นตอนในวิธีการที่ซับซ้อนผิดไป คุณสามารถปรับแต่งพรอมต์เพื่อชี้แจงขั้นตอนนั้นๆ ได้

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

การใช้เนื้อหาแบบยาวและแนวคิดแบบยาวให้เกิดประโยชน์สูงสุด

การคิดจะสร้าง "ความคิด" เป็นส่วนหนึ่งของเอาต์พุตโทเค็นที่แสดงเหตุผลโดยละเอียดของ Gemini วิธีใช้เอาต์พุตเหล่านี้ให้เกิดประโยชน์สูงสุด

ตรวจสอบเหตุผล

โปรดสังเกตกระบวนการใช้เหตุผลของ Gemini (มีอยู่ใน UI ของ Google AI Studio) วิธีแยกย่อยงาน และตัวเลือกที่ Gemini เลือกสำหรับเอาต์พุต ซึ่งจะช่วยให้คุณเข้าใจว่าระบบทําให้ได้ข้อสรุปดังกล่าวได้อย่างไร

ให้คําแนะนําในการให้เหตุผล

หากต้องการให้เอาต์พุตมีความยาวมาก คุณอาจต้องให้คําแนะนําเพิ่มเติมในพรอมต์เพื่อจำกัดปริมาณการคิดที่จําเป็นในการทํางานในพรอมต์ให้เสร็จสมบูรณ์ ซึ่งจะช่วยให้คุณจองเอาต์พุตโทเค็นได้มากขึ้นสําหรับการตอบกลับ

ตัวอย่าง: สําหรับรายงานแบบละเอียด คุณอาจระบุส่วนและส่วนย่อยในพรอมต์เพื่อแนะนําแนวทางการทํางานของ Gemini และจัดโครงสร้างเอาต์พุตอย่างมีประสิทธิภาพ

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...
<...>

รายละเอียดทางเทคนิค

  • โมเดลที่ใช้ได้: Gemini 2.0 Flash Thinking, Gemini 2.5 Pro Experimental ที่มี Thinking
  • อินพุตหลายรูปแบบ: ข้อความ เสียง รูปภาพ และ PDF (การรองรับอาจแตกต่างกันไปตามเวอร์ชันของโมเดล)
  • เอาต์พุต: ข้อความเท่านั้น (คำตอบสุดท้าย)
  • การป้อนโทเค็น: บริบทแบบยาว อาจมีโทเค็นได้สูงสุด 1 ล้านรายการ (ดูเอกสารประกอบของโมเดลที่เฉพาะเจาะจง)
  • เอาต์พุตโทเค็น: โทเค็นสูงสุด 64,000 รายการ (ดูเอกสารประกอบของโมเดลที่เฉพาะเจาะจง)

หมายเหตุ: เอาต์พุตโทเค็นทั้งหมดจะรวมทั้ง "ความคิด" ของโมเดลและคำตอบ ความยาวสูงสุดของเอาต์พุตคำตอบสุดท้ายอาจแตกต่างกันไปโดยขึ้นอยู่กับความซับซ้อนของคำขอและการใช้เครื่องมือ

การใช้เทคนิคเหล่านี้และใช้ประโยชน์จากเครื่องมือต่างๆ จะช่วยให้โมเดลการคิดของ Gemini ช่วยคุณจัดการงานที่ซับซ้อนได้หลากหลายและอาจนำไปสู่ผลลัพธ์ที่ดีขึ้น

ขั้นตอนถัดไป

  • เมื่อเข้าใจการออกแบบพรอมต์แล้ว ให้ลองเขียนพรอมต์ของคุณเองโดยใช้ Google AI Studio
  • ดูการทำความเข้าใจการออกแบบพรอมต์อย่างละเอียดได้ที่หัวข้อกลยุทธ์พรอมต์
  • ดูข้อมูลเกี่ยวกับการแจ้งแบบหลายสื่อได้ที่หัวข้อการแจ้งด้วยไฟล์สื่อ