Gemini-Denken anwenden

Bei den Modellen Gemini 2.5 Pro Experimental und Gemini 2.0 Flash Thinking Experimental wird bei der Generierung von Antworten ein interner „Denkprozess“ verwendet. Dieser Prozess trägt zu verbesserten Argumentationsfähigkeiten bei und ermöglicht es ihnen, komplexe Aufgaben zu lösen. In diesem Leitfaden erfahren Sie, wie Sie Gemini-Modelle mit Denkfunktionen verwenden.

Denkmodelle verwenden

Modelle mit Denkfunktionen sind in Google AI Studio und über die Gemini API verfügbar. Der Denkprozess ist in Google AI Studio sichtbar, wird aber nicht als Teil der API-Ausgabe bereitgestellt.

Einfache Anfrage senden

from google import genai

client = genai.Client(api_key="GEMINI_API_KEY")
prompt = "Explain the concept of Occam's Razor and provide a simple, everyday example."
response = client.models.generate_content(
    model="gemini-2.5-pro-exp-03-25",  # or gemini-2.0-flash-thinking-exp
    contents=prompt
)

print(response.text)
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
  const prompt = "Explain the concept of Occam's Razor and provide a simple, everyday example.";

  const response = await ai.models.generateContent({
    model: "gemini-2.5-pro-exp-03-25",  // or gemini-2.0-flash-thinking-exp
    contents: prompt,
  });

  console.log(response.text);
}

main();
// import packages here

func main() {
  ctx := context.Background()
  client, err := genai.NewClient(ctx, option.WithAPIKey(os.Getenv("GEMINI_API_KEY")))
  if err != nil {
    log.Fatal(err)
  }
  defer client.Close()

  model := client.GenerativeModel("gemini-2.5-pro-exp-03-25")  // or gemini-2.0-flash-thinking-exp
  resp, err := model.GenerateContent(ctx, genai.Text("Explain the concept of Occam's Razor and provide a simple, everyday example."))
  if err != nil {
    log.Fatal(err)
  }
  fmt.Println(resp.Text())
}
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro-exp-03-25:generateContent?key=$YOUR_API_KEY" \
 -H 'Content-Type: application/json' \
 -X POST \
 -d '{
   "contents": [
     {
       "parts": [
         {
           "text": "Explain the concept of Occam\''s Razor and provide a simple, everyday example."
         }
       ]
     }
   ]
 }'
 ```

Unterhaltungen mit mehreren Antworten

Wenn Sie den bisherigen Chatverlauf berücksichtigen möchten, können Sie Multi-Turn-Unterhaltungen verwenden.

Mit den SDKs können Sie eine Chatsitzung erstellen, um den Status der Unterhaltung zu verwalten.

from google import genai

client = genai.Client(api_key='GEMINI_API_KEY')

chat = client.aio.chats.create(
    model='gemini-2.5-pro-exp-03-25',  # or gemini-2.0-flash-thinking-exp
)
response = await chat.send_message('What is your name?')
print(response.text)
response = await chat.send_message('What did you just say before this?')
print(response.text)
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });

async function main() {
    const chat = ai.chats.create({
        model: 'gemini-2.5-pro-exp-03-25'  // or gemini-2.0-flash-thinking-exp
    });

    const response = await chat.sendMessage({
        message: 'What is your name?'
    });
    console.log(response.text);

    response = await chat.sendMessage({
        message: 'What did you just say before this?'
    });
    console.log(response.text);
}

main();

Tools mit Denkmodellen verwenden

Denkmodelle können Tools verwenden, um Aktionen auszuführen, die über die Textgenerierung hinausgehen. So können sie mit externen Systemen interagieren, Code ausführen oder auf Echtzeitinformationen zugreifen und die Ergebnisse in ihre Argumentation und endgültige Antwort einbeziehen.

Suchtool

Mit dem Suchtool kann das Modell externe Suchmaschinen abfragen, um aktuelle Informationen oder Informationen zu finden, die über die Trainingsdaten hinausgehen. Das ist nützlich für Fragen zu aktuellen Ereignissen oder sehr spezifischen Themen.

Informationen zum Konfigurieren des Suchtools finden Sie unter Suchtool konfigurieren.

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

...
  

Codeausführung

Mit dem Tool zur Codeausführung kann das Modell Python-Code generieren und ausführen, um Berechnungen durchzuführen, Daten zu manipulieren oder Probleme zu lösen, die sich am besten algorithmisch bearbeiten lassen. Das Modell empfängt die Ausgabe des Codes und kann sie in seiner Antwort verwenden.

Informationen zum Konfigurieren der Codeausführung finden Sie unter Codeausführung für das Modell aktivieren.

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.

Strukturierter Datenoutput

Mit der strukturierten Ausgabe können Sie Gemini dazu zwingen, mit JSON zu antworten, einem strukturierten Ausgabeformat, das für die automatisierte Verarbeitung geeignet ist. Dies ist besonders nützlich, um die Ausgabe des Modells in Anwendungen einzubinden.

Sie können das Format direkt in der Aufforderung angeben oder ein Schema über die Modellkonfiguration bereitstellen.

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"
}
]
```

Techniken zur Anregung von Denkmodellen

Effektive Prompts sind entscheidend, um die Vorteile der Gemini-Denkmodelle zu maximieren. In diesem Abschnitt werden einige Anregungen für Denkmodelle beschrieben.

Erste Schritte

Beginnen Sie mit allgemeinen Anweisungen, in denen das gewünschte Ergebnis beschrieben wird. Beginnen Sie mit einem einfachen Prompt und beobachten Sie die ersten Ideen des Modells, wie es die Herausforderung angehen könnte.

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.
<...>
  

Detaillierte Anleitung bereitstellen

Wenn der erste Versuch nicht das gewünschte Ergebnis liefert, optimieren Sie den Prompt. Geben Sie eine detailliertere Schritt-für-Schritt-Anleitung, um Gemini bei der Problemlösung zu unterstützen. So können Sie das anfängliche Verständnis des Modells für die Aufgabe mit expliziten Vorschlägen und Anleitungen steuern.

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.
<...>
  

Prompts für mehrere Aufnahmen mit Nachdenken

Multishot-Prompts in Verbindung mit dem Nachdenken können das Verständnis von Gemini weiter verbessern und die Genauigkeit seiner Antworten erhöhen. Geben Sie mehrere Beispiele für Eingabe-/Ausgabepaare an, die das gewünschte Verhalten und Ausgabeformat in Ihrem Prompt veranschaulichen.

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
  

Ausgabe und Verhalten definieren

Wenn Sie eine Anwendung entwickeln, in der Nutzer direkt mit dem Modell interagieren, sollten Sie angeben, wie die Ausgabe und Antworten von Gemini klingen und formatiert werden sollen.

Systemanweisungen

Systemanweisungen sind eine Reihe von Anweisungen, die vom Modell verarbeitet werden, bevor es Prompts verarbeitet. Sie werden jedes Mal aufgerufen, wenn das Modell einen Prompt erhält, und geben an, wie es sich verhalten und reagieren soll. Sie können beispielsweise die Rolle oder Identität, Kontextinformationen und Formatierungsanweisungen einfügen.

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.
  

Überprüfung und Reflexion

Fügen Sie entweder in der Anleitung für das System oder direkt in Ihren Prompts bestimmte Bestätigungsschritte ein. Sie können Gemini beispielsweise bitten, seine Quellen zu überprüfen, seine Begründung zu prüfen, potenzielle Fehler zu identifizieren und die endgültige Antwort zu prüfen.

    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.
  

Fehlerbehebung und Steuerung

In Google AI Studio haben Entwickler über die Benutzeroberfläche Zugriff auf die Gedanken des Modells. Das ist hilfreich, wenn Entwickler Ihren Prompt beim Debuggen überprüfen:

Denkprozesse analysieren

Sehen Sie sich den Denkprozess von Gemini genau an, um Bereiche zu identifizieren, in denen es möglicherweise in die Irre gegangen ist. Diese Analyse kann wertvolle Hinweise liefern, wie Sie Ihre Prompts optimieren und die gewünschte Antwort in Ihrer Anwendung konsistent erhalten.

Beispielszenario: Wenn Gemini einen Schritt in einer komplexen Anleitung falsch verstanden hat, können Sie den Prompt anpassen, um diesen Schritt zu klären.

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

Das Beste aus langen Outputs und dem Longform-Denken herausholen

Beim Denken werden „Gedanken“ als Teil der Tokenausgabe generiert, die die detaillierte Argumentation von Gemini zeigt. So nutzen Sie diese Ausgabeformate optimal:

Begründung prüfen

Achten Sie genau auf den Denkprozess von Gemini (verfügbar in der Google AI Studio-Benutzeroberfläche), wie er die Aufgabe in Teilaufgaben unterteilt hat und welche Entscheidungen er für die Ausgabe getroffen hat. So können Sie nachvollziehen, wie die Entscheidung zustande gekommen ist.

Leitfäden für die Argumentation bereitstellen

Wenn die gewünschte Ausgabe besonders lang sein soll, sollten Sie in Ihrem Prompt mehr Anleitungen geben, um die Denkarbeit einzuschränken, die für die Erledigung der im Prompt beschriebenen Aufgabe erforderlich ist. So kannst du mehr der Tokenausgabe für deine Antwort reservieren.

Beispiel: Für einen detaillierten Bericht können Sie in Ihrem Prompt Abschnitte und Unterabschnitte angeben, um Gemini bei der Entscheidungsfindung zu unterstützen und die Ausgabe effizient zu strukturieren.

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...
<...>

Nächste Schritte