Ce guide présente quelques pratiques d'utilisation des modèles de pensée Gemini. Ces modèles permettent aux développeurs de résoudre des problèmes complexes en les décomposant en étapes plus petites et plus faciles à gérer. Cette approche par étapes permet non seulement d'améliorer les performances pour les tâches difficiles, mais aussi de fournir aux développeurs des insights précieux sur le processus de raisonnement de Gemini, visible dans l'interface utilisateur de Google AI Studio. Actuellement, les modèles avec des fonctionnalités de réflexion incluent Gemini 2.0 Flash Thinking et le Gemini 2.5 Pro Experimental with thinking expérimental.
Techniques de requête
Les requêtes efficaces sont essentielles pour maximiser les avantages des modèles de pensée Gemini. Voici quelques techniques à prendre en compte:
Premiers pas
Commencez par des instructions générales qui décrivent le résultat souhaité. Commencez par une requête simple et observez les premières réflexions du modèle pour relever le défi.
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. <...> |
Fournir des instructions détaillées
Si la première tentative ne donne pas le résultat souhaité, affinez votre invite en fournissant des instructions plus explicites par étapes pour guider Gemini dans le processus de résolution des problèmes afin d'adopter une approche plus ciblée. Vous pouvez ainsi orienter la compréhension initiale du modèle de la tâche à l'aide de suggestions et d'instructions explicites.
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. <...> |
Requêtes multiplans avec réflexion
Les requêtes multi-plans associées à la réflexion peuvent encore améliorer la compréhension de Gemini et la précision de ses réponses. Fournissez plusieurs exemples de paires d'entrée-sortie, illustrant le comportement et le format de sortie souhaités dans votre requête.
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 |
Définir la sortie et le comportement
Lorsque vous créez une application dans laquelle les utilisateurs interagiront directement avec le modèle, vous pouvez fournir des instructions sur la façon dont la sortie et les réponses de Gemini seront formatées et sonneront.
Instructions système
Les instructions système sont un ensemble d'instructions que le modèle traite avant de traiter les requêtes. Ils sont rappelés chaque fois que le modèle est invité et indiquent au modèle comment vous souhaitez qu'il se comporte et réponde. Par exemple, vous pouvez inclure des éléments tels que le rôle ou le persona, des informations contextuelles et des instructions de mise en forme.
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. |
Vérification et réflexion
Incluez des étapes de validation spécifiques dans les instructions système ou directement dans vos requêtes. Par exemple, demandez à Gemini de vérifier ses sources, d'examiner son raisonnement, d'identifier les erreurs potentielles et de vérifier sa réponse 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. |
Exploiter les outils avec la pensée
Les modèles de pensée Gemini peuvent exploiter des outils pour effectuer des actions au-delà de la génération de texte. Cela leur permet d'interagir avec des systèmes externes, d'exécuter du code ou d'accéder à des informations en temps réel, en intégrant les résultats à leur raisonnement et à leur réponse finale. Vous pouvez activer des outils via la configuration de l'API.
Outil de recherche
L'outil de recherche permet au modèle d'interroger des moteurs de recherche externes pour trouver des informations à jour ou des informations qui vont au-delà de ses données d'entraînement. Cela est utile pour les questions concernant des événements récents ou des sujets très spécifiques.
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.) |
Outil d'exécution de code
L'outil d'exécution du code permet au modèle d'écrire et d'exécuter du code (par exemple, Python) pour effectuer des calculs, manipuler des données ou résoudre des problèmes qui sont mieux gérés par algorithme. Le modèle reçoit la sortie du code et peut l'utiliser dans sa réponse.
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. |
Sortie structurée
Vous pouvez indiquer au modèle de mettre en forme sa sortie selon une structure spécifique, telle que JSON. Cela est particulièrement utile pour intégrer la sortie du modèle dans les applications. Vous pouvez spécifier le format et le schéma souhaités directement dans l'invite ou utiliser des paramètres d'API tels que "response_mime_type" pour un contrôle plus robuste, le cas échéant.
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" } ] ``` |
Débogage et orientation
Google AI Studio permet aux développeurs d'accéder aux pensées du modèle dans l'interface utilisateur. Cela est utile pour un développeur qui examine votre requête lors du débogage:
Analyser le processus de réflexion
Examinez attentivement le processus de réflexion de Gemini pour identifier les points où il a pu se tromper. Cette analyse peut vous fournir des indices précieux pour affiner vos invites et obtenir la réponse attendue de manière cohérente dans votre application.
Exemple de scénario: Si le processus de réflexion de Gemini montre qu'il a mal compris une étape d'une instruction complexe, vous pouvez affiner la requête pour clarifier cette étape spécifique.
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 |
Exploiter au mieux les résultats et la réflexion longs
La réflexion génère des "pensées" dans le cadre de la sortie de jeton qui présente le raisonnement détaillé de Gemini. Pour exploiter pleinement ces résultats:
Examiner le raisonnement
Examinez attentivement le processus de raisonnement de Gemini (disponible dans l'interface utilisateur de Google AI Studio), la façon dont il a décomposé la tâche et les choix qu'il a faits pour votre sortie. Cela peut vous aider à comprendre comment il est arrivé à cette conclusion.
Fournir des conseils pour le raisonnement
Si vous souhaitez que le résultat soit particulièrement long, vous pouvez fournir plus d'instructions dans votre requête pour limiter la quantité de réflexion nécessaire pour accomplir la tâche présentée dans la requête. Vous pouvez ainsi réserver une plus grande partie de la sortie du jeton pour votre réponse.
Exemple: Pour un rapport détaillé, vous pouvez spécifier des sections et des sous-sections dans votre requête afin d'orienter la réflexion de Gemini et de structurer efficacement le résultat.
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... <...> |
Détails techniques
- Modèles disponibles: Gemini 2.0 Flash Thinking, Gemini 2.5 Pro Experimental avec thinking
- Saisie multimodale: texte, audio, images et PDF (la compatibilité peut varier selon la version de modèle spécifique)
- Sortie: texte uniquement (réponse finale)
- Entrée de jetons: contexte long, pouvant atteindre un million de jetons (consultez la documentation du modèle spécifique)
- Sortie de jetons: jusqu'à 64 000 jetons (consultez la documentation spécifique du modèle)
REMARQUE: La sortie totale des jetons inclut à la fois les "pensées" du modèle et la réponse. La longueur maximale de la sortie de la réponse finale peut varier en fonction de la complexité de votre requête et de l'utilisation d'outils.
En implémentant ces techniques et en exploitant ces outils, les modèles de pensée Gemini peuvent vous aider à accomplir diverses tâches complexes et vous permettre d'améliorer vos résultats.
Étapes suivantes
- Maintenant que vous avez compris la conception des requêtes, essayez d'écrire vos propres requêtes à l'aide de Google AI Studio.
- Pour en savoir plus sur la conception des requêtes, consultez la section Stratégies d'invite.
- Pour en savoir plus sur les requêtes multimodales, consultez la section Requêtes avec des fichiers multimédias.