Pensando

Los modelos de pensamiento se entrenan para generar el "proceso de pensamiento" que sigue el modelo como parte de su respuesta. Por lo tanto, los modelos de razonamiento pueden ofrecer respuestas con capacidades de razonamiento más sólidas que los modelos base equivalentes.

El proceso de reflexión está habilitado de forma predeterminada. Cuando usas Vertex AI Studio, puedes ver todo el proceso de razonamiento junto con la respuesta generada por el modelo.

Modelos admitidos

La función Pensar está disponible en los siguientes modelos:

Usar un modelo de pensamiento

Para usar la función de reflexión con un modelo compatible, haz lo siguiente:

Consola

  1. Abre Vertex AI Studio > Crear petición.
  2. En el panel Modelo, haz clic en Cambiar modelo y selecciona uno de los modelos admitidos del menú.
    • (Solo Gemini 2.5 Flash) El presupuesto de razonamiento se define como Automático de forma predeterminada cuando se carga el modelo.
  3. (Opcional) Da al modelo instrucciones detalladas sobre cómo debe dar formato a sus respuestas en el campo Instrucciones del sistema.
  4. Escribe una petición en el campo Escribe tu petición.
  5. Haz clic en Ejecutar.

Gemini devuelve una respuesta después de generarla. En función de la complejidad de la respuesta, la generación puede tardar varios segundos:

(Solo Gemini 2.5 Flash) Para desactivar la función, asigna el valor Desactivado a Presupuesto de la función.

Python

Instalar

pip install --upgrade google-genai

Para obtener más información, consulta la documentación de referencia del SDK.

Define variables de entorno para usar el SDK de IA generativa con 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",
    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).

Go

Consulta cómo instalar o actualizar Go.

Para obtener más información, consulta la documentación de referencia del SDK.

Define variables de entorno para usar el SDK de IA generativa con 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

import (
	"context"
	"fmt"
	"io"

	"google.golang.org/genai"
)

// generateThinkingWithText shows how to generate thinking using a text prompt.
func generateThinkingWithText(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	resp, err := client.Models.GenerateContent(ctx,
		"gemini-2.5-flash",
		genai.Text("solve x^2 + 4x + 4 = 0"),
		nil,
	)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)
	// Example response:
	// To solve the quadratic equation $x^2 + 4x + 4 = 0$, we can use a few methods:
	//
	// **Method 1: Factoring (Recognizing a Perfect Square Trinomial)**
	// **1. The Foundation: Data and Algorithms**
	//
	// Notice that the left side of the equation is a perfect square trinomial.
	// ...

	return nil
}

Pensamiento de modelo de control

Puedes controlar la cantidad de reflexión que realiza el modelo antes de devolver una respuesta. El método para controlar el pensamiento varía en función de la versión del modelo.

Modelos de Gemini 3 y posteriores

Los modelos de Gemini 3 introducen el parámetro thinking_level, que simplifica la configuración del presupuesto de pensamiento en niveles. De forma predeterminada, Gemini 3 Pro usa el razonamiento dinámico para analizar las peticiones. Para obtener respuestas más rápidas y con menor latencia cuando no se requiere un razonamiento complejo, puedes restringir la thinking_leveldel modelo.

  • LOW: limita el uso de tokens del modelo para pensar y es adecuado para tareas más sencillas en las que no se requiere un razonamiento exhaustivo. LOW es ideal para tareas de alto rendimiento en las que la velocidad es esencial:

    from google import genai
    from google.genai import types
    
    client = genai.Client()
    
    response = client.models.generate_content(
        model="gemini-3-pro-preview",
        contents="How does AI work?",
        config=types.GenerateContentConfig(
            thinking_config=types.ThinkingConfig(
                thinking_level=types.ThinkingLevel.LOW
            )
        ),
    )
    print(response.text)
    
  • HIGH: permite que el modelo use más tokens para pensar y es adecuado para peticiones complejas que requieren un razonamiento profundo, como la planificación de varios pasos, la generación de código verificado o escenarios avanzados de llamadas a funciones. Este es el nivel predeterminado de Gemini 3 Pro. Usa esta configuración cuando sustituyas tareas para las que antes usabas modelos de razonamiento especializados:

    from google import genai
    from google.genai import types
    
    client = genai.Client()
    
    response = client.models.generate_content(
        model="gemini-3-pro-preview",
        contents="Find the race condition in this multi-threaded C++ snippet: [code here]",
        config=types.GenerateContentConfig(
            thinking_config=types.ThinkingConfig(
                thinking_level=types.ThinkingLevel.HIGH
            )
        ),
    )
    print(response.text)
    

La función de razonamiento no se puede desactivar en Gemini 3 Pro.

Si especificas tanto thinking_level como thinking_budget en la misma solicitud de un modelo de Gemini 3, el modelo devuelve un error.

Modelos de Gemini 2.5 y versiones anteriores

En los modelos anteriores a Gemini 3, puedes controlar el razonamiento mediante el parámetro thinking_budget, que establece un límite superior en el número de tokens que el modelo puede usar en su proceso de pensamiento. De forma predeterminada, si thinking_budget no se define, el modelo controla automáticamente la cantidad que cree que es necesaria,hasta un máximo de 8192 tokens. Para usar el presupuesto dinámico a través de la API, asigna el valor -1 a thinking_budget.

Puedes definir manualmente thinking_budget en un límite de tokens específico en situaciones en las que necesites pensar más o menos que el valor predeterminado. Define un límite de tokens inferior para las tareas menos complejas o un límite superior para las más complejas. Si la latencia es más importante, usa un presupuesto más bajo o inhabilita la función de reflexión asignando el valor 0 al presupuesto.

En la siguiente tabla se muestran los importes mínimos y máximos que puede definir para thinking_budget en cada modelo admitido:

Modelo Importe mínimo de tokens Cantidad máxima de tokens
Gemini 2.5 Flash 1 24.576
Gemini 2.5 Pro 128 32.768
Gemini 2.5 Flash-Lite 512 24.576

Si ajustas thinking_budget en 0 al usar Gemini 2.5 Flash y Gemini 2.5 Flash-Lite, la función de reflexión se desactiva. No se puede desactivar en Gemini 2.5 Pro.

Si usas el parámetro thinking_level con un modelo anterior a Gemini 3, el modelo devuelve un error.

Consola

  1. Abre Vertex AI Studio > Crear petición.
  2. En el panel Modelo, haz clic en Cambiar modelo y selecciona uno de los modelos admitidos del menú.
  3. Selecciona Manual en el menú desplegable Presupuesto de reflexión y, a continuación, usa el control deslizante para ajustar el límite del presupuesto de reflexión.

Python

Instalar

pip install --upgrade google-genai

Para obtener más información, consulta la documentación de referencia del SDK.

Define variables de entorno para usar el SDK de IA generativa con 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
from google.genai.types import GenerateContentConfig, ThinkingConfig

client = genai.Client()

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="solve x^2 + 4x + 4 = 0",
    config=GenerateContentConfig(
        thinking_config=ThinkingConfig(
            thinking_budget=1024,  # Use `0` to turn off thinking
        )
    ),
)

print(response.text)
# Example response:
#     To solve the equation $x^2 + 4x + 4 = 0$, you can use several methods:
#     **Method 1: Factoring**
#     1.  Look for two numbers that multiply to the constant term (4) and add up to the coefficient of the $x$ term (4).
#     2.  The numbers are 2 and 2 ($2 \times 2 = 4$ and $2 + 2 = 4$).
#     ...
#     ...
#     All three methods yield the same solution. This quadratic equation has exactly one distinct solution (a repeated root).
#     The solution is **x = -2**.

# Token count for `Thinking`
print(response.usage_metadata.thoughts_token_count)
# Example response:
#     886

# Total token count
print(response.usage_metadata.total_token_count)
# Example response:
#     1525

Node.js

Instalar

npm install @google/genai

Para obtener más información, consulta la documentación de referencia del SDK.

Define variables de entorno para usar el SDK de IA generativa con 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

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateWithThoughts(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'solve x^2 + 4x + 4 = 0',
    config: {
      thinkingConfig: {
        thinkingBudget: 1024,
      },
    },
  });

  console.log(response.text);
  // Example response:
  //  To solve the equation $x^2 + 4x + 4 = 0$, you can use several methods:
  //  **Method 1: Factoring**
  //  1.  Look for two numbers that multiply to the constant term (4) and add up to the coefficient of the $x$ term (4).
  //  2.  The numbers are 2 and 2 ($2 \times 2 = 4$ and $2 + 2 = 4$).
  //  ...
  //  ...
  //  All three methods yield the same solution. This quadratic equation has exactly one distinct solution (a repeated root).
  //  The solution is **x = -2**.

  // Token count for `Thinking`
  console.log(response.usageMetadata.thoughtsTokenCount);
  // Example response:
  //  886

  // Total token count
  console.log(response.usageMetadata.totalTokenCount);
  // Example response:
  //  1525
  return response.text;
}

Ver resúmenes de pensamientos

Los resúmenes de razonamiento son la versión abreviada del proceso de razonamiento que ha seguido el modelo para generar su respuesta. Puedes ver resúmenes de reflexiones tanto en Gemini 2.5 Flash como en Gemini 2.5 Pro. Para ver resúmenes de reflexiones, sigue estos pasos:

Consola

Los resúmenes de reflexiones están habilitados de forma predeterminada en Vertex AI Studio. Para ver el proceso de pensamiento resumido del modelo, despliega el panel Pensamientos.

Python

Instalar

pip install --upgrade google-genai

Para obtener más información, consulta la documentación de referencia del SDK.

Define variables de entorno para usar el SDK de IA generativa con 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
from google.genai.types import GenerateContentConfig, ThinkingConfig

client = genai.Client()
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents="solve x^2 + 4x + 4 = 0",
    config=GenerateContentConfig(
        thinking_config=ThinkingConfig(include_thoughts=True)
    ),
)

print(response.text)
# Example Response:
#     Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
#     ...
#     **Answer:**
#     The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

for part in response.candidates[0].content.parts:
    if part and part.thought:  # show thoughts
        print(part.text)
# Example Response:
#     **My Thought Process for Solving the Quadratic Equation**
#
#     Alright, let's break down this quadratic, x² + 4x + 4 = 0. First things first:
#     it's a quadratic; the x² term gives it away, and we know the general form is
#     ax² + bx + c = 0.
#
#     So, let's identify the coefficients: a = 1, b = 4, and c = 4. Now, what's the
#     most efficient path to the solution? My gut tells me to try factoring; it's
#     often the fastest route if it works. If that fails, I'll default to the quadratic
#     formula, which is foolproof. Completing the square? It's good for deriving the
#     formula or when factoring is difficult, but not usually my first choice for
#     direct solving, but it can't hurt to keep it as an option.
#
#     Factoring, then. I need to find two numbers that multiply to 'c' (4) and add
#     up to 'b' (4). Let's see... 1 and 4 don't work (add up to 5). 2 and 2? Bingo!
#     They multiply to 4 and add up to 4. This means I can rewrite the equation as
#     (x + 2)(x + 2) = 0, or more concisely, (x + 2)² = 0. Solving for x is now
#     trivial: x + 2 = 0, thus x = -2.
#
#     Okay, just to be absolutely certain, I'll run the quadratic formula just to
#     double-check. x = [-b ± √(b² - 4ac)] / 2a. Plugging in the values, x = [-4 ±
#     √(4² - 4 * 1 * 4)] / (2 * 1). That simplifies to x = [-4 ± √0] / 2. So, x =
#     -2 again – a repeated root. Nice.
#
#     Now, let's check via completing the square. Starting from the same equation,
#     (x² + 4x) = -4. Take half of the b-value (4/2 = 2), square it (2² = 4), and
#     add it to both sides, so x² + 4x + 4 = -4 + 4. Which simplifies into (x + 2)²
#     = 0. The square root on both sides gives us x + 2 = 0, therefore x = -2, as
#      expected.
#
#     Always, *always* confirm! Let's substitute x = -2 back into the original
#     equation: (-2)² + 4(-2) + 4 = 0. That's 4 - 8 + 4 = 0. It checks out.
#
#     Conclusion: the solution is x = -2. Confirmed.

Node.js

Instalar

npm install @google/genai

Para obtener más información, consulta la documentación de referencia del SDK.

Define variables de entorno para usar el SDK de IA generativa con 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

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateWithThoughts(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await client.models.generateContent({
    model: 'gemini-2.5-pro',
    contents: 'solve x^2 + 4x + 4 = 0',
    config: {
      thinkingConfig: {
        includeThoughts: true,
      },
    },
  });

  console.log(response.text);
  // Example Response:
  //  Okay, let's solve the quadratic equation x² + 4x + 4 = 0.
  //  ...
  //  **Answer:**
  //  The solution to the equation x² + 4x + 4 = 0 is x = -2. This is a repeated root (or a root with multiplicity 2).

  for (const part of response.candidates[0].content.parts) {
    if (part && part.thought) {
      console.log(part.text);
    }
  }

  // Example Response:
  // **My Thought Process for Solving the Quadratic Equation**
  //
  // Alright, let's break down this quadratic, x² + 4x + 4 = 0. First things first:
  // it's a quadratic; the x² term gives it away, and we know the general form is
  // ax² + bx + c = 0.
  //
  // So, let's identify the coefficients: a = 1, b = 4, and c = 4. Now, what's the
  // most efficient path to the solution? My gut tells me to try factoring; it's
  // often the fastest route if it works. If that fails, I'll default to the quadratic
  // formula, which is foolproof. Completing the square? It's good for deriving the
  // formula or when factoring is difficult, but not usually my first choice for
  // direct solving, but it can't hurt to keep it as an option.
  //
  // Factoring, then. I need to find two numbers that multiply to 'c' (4) and add
  // up to 'b' (4). Let's see... 1 and 4 don't work (add up to 5). 2 and 2? Bingo!
  // They multiply to 4 and add up to 4. This means I can rewrite the equation as
  // (x + 2)(x + 2) = 0, or more concisely, (x + 2)² = 0. Solving for x is now
  // trivial: x + 2 = 0, thus x = -2.
  //
  // Okay, just to be absolutely certain, I'll run the quadratic formula just to
  // double-check. x = [-b ± √(b² - 4ac)] / 2a. Plugging in the values, x = [-4 ±
  // √(4² - 4 * 1 * 4)] / (2 * 1). That simplifies to x = [-4 ± √0] / 2. So, x =
  // -2 again – a repeated root. Nice.
  //
  // Now, let's check via completing the square. Starting from the same equation,
  // (x² + 4x) = -4. Take half of the b-value (4/2 = 2), square it (2² = 4), and
  // add it to both sides, so x² + 4x + 4 = -4 + 4. Which simplifies into (x + 2)²
  // = 0. The square root on both sides gives us x + 2 = 0, therefore x = -2, as
  //  expected.
  //
  // Always, *always* confirm! Let's substitute x = -2 back into the original
  // equation: (-2)² + 4(-2) + 4 = 0. That's 4 - 8 + 4 = 0. It checks out.
  //
  // Conclusion: the solution is x = -2. Confirmed.

  return response.text;
}

Firmas de pensamientos

Las firmas de pensamiento son representaciones cifradas del proceso de pensamiento interno del modelo que conservan el estado de razonamiento de Gemini durante las conversaciones de varias interacciones, especialmente cuando se usa la llamada a funciones.

Para asegurarte de que el modelo mantiene el contexto completo en varias interacciones de una conversación, debes devolver las firmas de pensamiento de las respuestas anteriores en tus solicitudes posteriores. Si usas el SDK oficial de Gen AI de Google (Python, Node.js, Go o Java) y las funciones estándar del historial de conversaciones o añades la respuesta completa del modelo al historial, las firmas de pensamientos se gestionan automáticamente.

Para obtener más información, consulta Firmas de pensamientos.

Técnicas de peticiones

Para maximizar las ventajas de los modelos de razonamiento de Gemini, es fundamental crear peticiones eficaces. En esta sección se describen algunas prácticas de peticiones para modelos de pensamiento.

Empieza con instrucciones generales que describan el resultado que prefieres. Empieza con una solicitud de baja complejidad y observa las primeras ideas del modelo sobre cómo responder.

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.
<...>
  

Proporcionar instrucciones detalladas

Si el primer intento no da el resultado esperado, perfecciona tu petición proporcionando instrucciones paso a paso más explícitas para guiar a Gemini en el proceso de resolución de problemas y conseguir un enfoque más específico. De esta forma, puedes dirigir la comprensión inicial de la tarea por parte del modelo con sugerencias y orientación explícitas.

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.
<...>
  

Peticiones de varios intentos con razonamiento

Las peticiones de varios intentos junto con el pensamiento pueden mejorar aún más la comprensión de Gemini y la precisión de sus respuestas. Proporciona varios ejemplos de pares de entrada-salida que demuestren el comportamiento y el formato de salida preferidos en tu petición.

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
  

Definir la salida y el comportamiento

Cuando crees una aplicación en la que los usuarios interactúen directamente con el modelo, puede que quieras proporcionar directrices sobre el tono y el formato de las respuestas y los resultados de Gemini.

Instrucciones del sistema

Las instrucciones del sistema son un conjunto de instrucciones que el modelo procesa antes de procesar las peticiones. Se recuerdan cada vez que se le pide algo al modelo y le indican cómo quieres que se comporte y responda. Por ejemplo, puedes incluir aspectos como el rol o el perfil, información contextual e instrucciones de formato.

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.
  

Verificación y reflexión

Incluye pasos de verificación específicos en las instrucciones del sistema o directamente en tus peticiones. Por ejemplo, puedes pedirle a Gemini que verifique sus fuentes, revise su razonamiento, identifique posibles errores y compruebe su respuesta final.

    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.
  

Depuración y control

Vertex AI Studio ofrece a los desarrolladores acceso a las reflexiones del modelo en la interfaz de usuario. Esto resulta útil para los desarrolladores que revisan sus peticiones al depurar:

Analizar el proceso de razonamiento

Revisa detenidamente el proceso de reflexión de Gemini para identificar las áreas en las que se haya desviado. Este análisis puede proporcionarte información valiosa para mejorar tus peticiones y obtener la respuesta esperada de forma coherente en tu aplicación.

Ejemplo: Si el proceso de reflexión de Gemini muestra que no ha entendido un paso de una instrucción compleja, puedes modificar la petición para aclarar ese paso concreto.

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 the 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

Aprovechar al máximo las respuestas largas y el pensamiento extenso

El pensamiento genera "pensamientos" como parte de la salida de tokens que muestra el razonamiento detallado de Gemini. Para sacar el máximo partido a estos resultados, sigue estos pasos:

Revisa el razonamiento

Presta mucha atención al proceso de razonamiento de Gemini (disponible en la interfaz de usuario de Vertex AI Studio), a cómo ha desglosado la tarea y a las decisiones que ha tomado para generar el resultado. Esto puede ayudarte a entender cómo ha llegado a esa conclusión.

Proporcionar orientación en el razonamiento

Si quieres que el resultado sea especialmente largo, puedes proporcionar más instrucciones en tu petición para limitar la cantidad de razonamiento necesaria para llevar a cabo la tarea presentada en la petición. De esta forma, puedes reservar más tokens para tu respuesta.

*Ejemplo: Para obtener un informe detallado, puedes especificar secciones y subsecciones en tu petición para guiar el proceso de reflexión de Gemini y estructurar el resultado de forma eficiente.

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...
<...>

Precios

Se te cobra por los tokens que se generan durante el proceso de reflexión de un modelo. En algunos modelos, como Gemini 3 Pro y Gemini 2.5 Pro, el pensamiento está habilitado de forma predeterminada y se te cobra por estos tokens.

Para obtener más información, consulta los precios de Vertex AI. Para saber cómo gestionar los costes, consulta Controlar el presupuesto de pensamiento.

Siguientes pasos

Prueba a usar un modelo de razonamiento con nuestro notebook de Colab o abre la consola de Vertex AI y prueba a pedirle algo al modelo.