Gemini 2.5 Pro Experimental e Gemini 2.0 Flash Thinking Experimental sono modelli che utilizzano un "processo di pensiero" interno durante la generazione di risposte. Questo processo contribuisce a migliorare le loro capacità di ragionamento e consente loro di risolvere attività complesse. Questa guida mostra come utilizzare i modelli Gemini con funzionalità di pensiero.
Prima di iniziare
Prima di chiamare l'API Gemini, assicurati di aver installato l'SDK che preferisci e di avere configurato e pronto all'uso una chiave API Gemini.
Utilizza modelli di pensiero
I modelli con funzionalità di pensiero sono disponibili in Google AI Studio e tramite l'API Gemini. Tieni presente che il processo di pensiero è visibile in Google AI Studio, ma non viene fornito nell'output dell'API.
Inviare una richiesta di base
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-preview-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-preview-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-preview-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."
}
]
}
]
}'
```
Conversazioni di pensiero a più turni
Per tenere conto della cronologia della chat precedente, puoi utilizzare le conversazioni a più turni.
Con gli SDK, puoi creare una sessione di chat per gestire lo stato della conversazione.
from google import genai
client = genai.Client(api_key='GEMINI_API_KEY')
chat = client.aio.chats.create(
model='gemini-2.5-pro-preview-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-preview-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();
Utilizzare strumenti con modelli di pensiero
I modelli di pensiero possono utilizzare strumenti per eseguire azioni diverse dalla generazione di testo. In questo modo, possono interagire con sistemi esterni, eseguire codice o accedere a informazioni in tempo reale, incorporando i risultati nel loro ragionamento e nella risposta finale.
Strumento di ricerca
Lo strumento di ricerca consente al modello di eseguire query su motori di ricerca esterni per trovare informazioni aggiornate o informazioni diverse da quelle dei suoi dati di addestramento. Questa opzione è utile per domande su eventi recenti o argomenti molto specifici.
Per configurare lo strumento di ricerca, consulta Configurare lo strumento di ricerca.
What were the major scientific breakthroughs announced last week? Based on recent search results, here are some highlights from the past week in science: ... |
Esecuzione di codice
Lo strumento di esecuzione del codice consente al modello di generare ed eseguire codice Python per eseguire calcoli, manipolare i dati o risolvere problemi che sono gestiti meglio in modo algoritmico. Il modello riceve l'output del codice e può utilizzarlo nella risposta.
Per configurare l'esecuzione del codice, consulta Attivare l'esecuzione del codice nel modello.
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. |
Output strutturato
Con l'output strutturato, puoi limitare Gemini a rispondere con JSON, un formato di output strutturato adatto all'elaborazione automatica. Questo è particolarmente utile per integrare l'output del modello nelle applicazioni.
Puoi specificare il formato direttamente nel prompt o fornire uno schema tramite la configurazione del modello.
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" } ] ``` |
Tecniche di impostazione di prompt per i modelli di pensiero
Un prompt efficace è fondamentale per massimizzare i vantaggi dei modelli di pensiero di Gemini. Questa sezione illustra alcune best practice per i prompt dei modelli di pensiero.
Per iniziare
Inizia con istruzioni generali che descrivono il risultato desiderato. Inizia con un prompt semplice e osserva le prime idee del modello su come affrontare la sfida.
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. <...> |
Fornisci istruzioni dettagliate
Se il tentativo iniziale non produce il risultato desiderato, perfeziona il prompt fornendo istruzioni passo passo più esplicite per guidare Gemini nella procedura di risoluzione dei problemi per un approccio più mirato. In questo modo, puoi indirizzare la comprensione iniziale del modello dell'attività con suggerimenti e indicazioni espliciti.
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. <...> |
Prompting multishot con Thinking
I prompt con più foto in combinazione con il pensiero possono migliorare ulteriormente la comprensione di Gemini e la precisione delle sue risposte. Fornisci diversi esempi di coppie di input-output che dimostrino il comportamento e il formato di output desiderati nel prompt.
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 |
Definizione di output e comportamento
Quando crei un'applicazione in cui gli utenti interagiranno direttamente con il modello, ti consigliamo di fornire indicazioni su come verranno formattate e su come verranno pronunciate le risposte e l'output di Gemini.
Istruzioni di sistema
Le istruzioni di sistema sono un insieme di istruzioni che il modello elabora prima di elaborare i prompt. Vengono richiamati ogni volta che viene richiesto al modello di rispondere e indicano al modello come vuoi che si comporti e risponda. Ad esempio, puoi includere elementi come il ruolo o la persona, informazioni contestuali e istruzioni di formattazione.
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. |
Verifica e riflessione
Includi passaggi di verifica specifici nelle istruzioni di sistema o direttamente nei prompt. Ad esempio, chiedi a Gemini di verificare le sue fonti, rivedere il suo ragionamento, identificare potenziali errori e controllare la sua risposta finale.
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. |
Debug e gestione
Google AI Studio fornisce agli sviluppatori l'accesso ai pensieri del modello nell'interfaccia utente. Questo è utile per gli sviluppatori che esaminano il prompt durante il debug:
Analizza il processo di pensiero
Esamina attentamente il ragionamento di Gemini per identificare eventuali aree in cui potrebbe aver sbagliato. Questa analisi può fornire indizi preziosi per perfezionare i prompt e ottenere la risposta prevista in modo coerente nella tua applicazione.
Scenario di esempio: se il processo di pensiero di Gemini mostra che non ha compreso un passaggio di un'istruzione complessa, puoi perfezionare il prompt per chiarire quel passaggio specifico.
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 |
Sfruttare al meglio i contenuti lunghi e il pensiero in formato lungo
Il pensiero genera "pensieri" nell'ambito dell'output del token che mostra il ragionamento dettagliato di Gemini. Per ottenere il massimo da questi output:
Esamina il ragionamento
Presta molta attenzione al processo di ragionamento di Gemini (disponibile nell'interfaccia utente di Google AI Studio), a come ha suddiviso l'attività e alle scelte che ha fatto per l'output. In questo modo puoi capire come è arrivata a questa conclusione.
Fornire indicazioni per il ragionamento
Se il risultato desiderato deve essere particolarmente lungo, ti consigliamo di fornire ulteriori indicazioni nel prompt per limitare la quantità di pensiero necessaria per completare l'attività presentata nel prompt. In questo modo puoi riservare più dell'output del token per la tua risposta.
Esempio: per un report dettagliato, puoi specificare sezioni e sottosezioni nel prompt per guidare il ragionamento di Gemini e strutturare l'output in modo efficiente.
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... <...> |
Passaggi successivi
- Prova la versione di anteprima di Gemini 2.5 Pro in Google AI Studio.
- Per saperne di più su Gemini 2.5 Pro Preview e Gemini Flash 2.0 Thinking, visita la pagina del modello.
- Prova altri esempi nel cookbook di Thinking.