Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris. # Praktik terbaik umum Praktik terbaik berikut terutama berlaku untuk model teks Amazon Nova, tetapi Anda dapat menerapkannya ke model lain, selain praktik terbaik khusus modalitas. Untuk informasi lebih lanjut tentang cara meminta input multimodal, lihat. [Meminta input multimodal](prompting-multimodal.md) Untuk informasi tentang cara meminta input ucapan, lihat. [Permintaan percakapan suara](sonic-system-prompts.md) ## Memahami peran Model Amazon Nova memungkinkan Anda menyusun petunjuk melalui penggunaan tiga peran berbeda: sistem, pengguna, dan asisten. + **Sistem (opsional)** — Meskipun tidak wajib, ini menetapkan parameter perilaku keseluruhan asisten. Ini juga dapat digunakan untuk memberikan instruksi dan pedoman tambahan bahwa pengguna ingin model untuk mematuhi selama percakapan. + **Pengguna** — Secara opsional dapat menyampaikan konteks, tugas, instruksi, dan hasil yang diinginkan bersama dengan permintaan pengguna. + **Asisten** — Membantu dalam membimbing model menuju respons yang diinginkan. **Topics** + [ ## Memahami peran ](#understanding-roles) + [ # Buat petunjuk yang tepat ](create-precise-prompts.md) + [ # Bawa fokus ke bagian prompt ](prompting-bring-focus.md) + [ # Menggunakan peran sistem ](prompting-system-role.md) + [ # Berikan contoh (beberapa bidikan yang diminta) ](prompting-provide-examples.md) + [ # Sistem panggilan alat ](prompting-tools-function.md) + [ # Teknik meminta tingkat lanjut ](advanced-prompting-techniques.md) # Buat petunjuk yang tepat Membuat kueri pengguna tertentu sangat penting dalam rekayasa yang cepat. Kueri yang dibuat dengan baik mengarahkan model pemahaman teks Amazon Nova untuk menghasilkan respons yang akurat dan relevan. Untuk menyusun pertanyaan seperti itu, penting untuk memulai dengan memberikan informasi kontekstual dalam kueri. Konteks yang disediakan membantu menempatkan model lebih baik dengan menyelaraskan skenario target-pengguna yang jelas, sehingga meningkatkan relevansi dan koherensi output. ## Memberikan informasi kontekstual dan spesifik Model bekerja paling baik jika instruksinya jelas, terstruktur dengan baik, pendek, dan spesifik. Panduan template prompt ini berlaku untuk prompt pengguna dan prompt sistem. **Templat cepat** ``` # Use this to clearly define the task and job needed by the model task_summary = f""" ## Task Summary: {{Task summary}} """ # Use this to provide contextual information related to the task context_information = f""" ## Context Information: - {{Context and content information 1}} - {{Context and content information 2}} ... """ # Use this to provide any model instructions that you want model to adhere to model_instructions = f""" ## Model Instructions: - {{ Other Model Instructions }} ... """ # Use this to provide response style and formatting guidance response_style = f""" ## Response style and format requirements: - {{Style and format requirement 1}} - {{Style and format requirement 2}} ... """ # Concatenate to final prompt final_prompt = f"""{task_summary} {context_information} {model_instructions} {response_style}""" ``` ### Contoh: Informasi spesifik dan kontekstual Berikut adalah contoh prompt yang ditulis ulang dengan informasi spesifik dan kontekstual. Menambahkan lebih banyak informasi kontekstual membantu model landasan menuju perilaku yang diinginkan. ------ #### [ Unclear prompt ] `User:` ``` Write me a meeting invite to the project team ``` `Assistant:` ``` Certainly! Here's a sample meeting invite for your project team: --- **Subject:** Project Team Meeting - [Project Name] **Date:** [Insert Date] **Time:** [Insert Time] **Duration:** [Insert Duration] **Location:** [Insert Location] / [Zoom/Teams Link if Online] **Agenda:** 1. **Welcome and Introductions** - Quick round of introductions for new team members 2. **Project Overview** - Objectives and goals - Current status and milestones achieved 3. **Task Allocation and Deadlines** - Detailed breakdown of tasks - Assignment of responsibilities - Discussion of deadlines 4. **Risk Management** - Identification of potential risks - Mitigation strategies 5. **Resource Allocation** - Required tools and materials - Budget review 6. **Q&A Session** - Open floor for questions and clarifications 7. **Next Steps and Closing** - Summary of action items - Schedule for the next meeting **Additional Notes:** - Please come prepared with any relevant documents or updates regarding your assigned tasks. - If you anticipate any issues or require additional support, please let us know in advance so we can address them during the meeting. **Contact Information:** For any questions or concerns before the meeting, please feel free to reach out to [Your Name] at [Your Email] or [Your Phone Number]. We look forward to a productive discussion and to kicking off our project with enthusiasm! Best regards, [Your Full Name] [Your Position] [Your Contact Information] --- Feel free to customize this template to better fit your specific project and team needs! ``` ------ #### [ Clear prompt ] `User:` ``` Write me a meeting invite to the project team. The meeting is about project planning, and should be held on October 16th, from 10 AM to 11 AM in Conference Room B. Please include an agenda that covers our progress on the project thus far, as well as any upcoming milestones and deadlines. ``` `Assistant:` ``` **Meeting Invitation: Project Planning Session** **Date:** October 16th **Time:** 10:00 AM - 11:00 AM **Location:** Conference Room B **Agenda:** 1. **Welcome and Introduction (10:00 AM - 10:05 AM)** - Brief overview by the meeting facilitator. 2. **Project Progress Update (10:05 AM - 10:30 AM)** - Review of completed tasks and achievements to date. - Detailed discussion on current project status and any challenges encountered. 3. **Upcoming Milestones and Deadlines (10:30 AM - 10:50 AM)** - Overview of the next phase of the project. - Identification of key milestones and deadlines. 4. **Action Items and Responsibilities (10:50 AM - 11:00 AM)** - Assignment of tasks for the upcoming period. - Confirmation of individual responsibilities and follow-up items. 5. **Q&A Session (11:00 AM)** - Open floor for any questions or concerns from team members. Please ensure your attendance to discuss and finalize our project planning for the next phase. Your insights and contributions are highly valued. Best regards, [Your Name] [Your Position] [Your Contact Information] ``` ------ + Perjelas: Saat mendorong model, cobalah untuk menjaga instruksi sejelas mungkin dengan cara yang akan dipahami manusia versus mesin (misalnya, daftar gaya JSON). + Jadilah spesifik: Berikan instruksi spesifik model tentang apa tugasnya, apa output yang diharapkan, dan konteks tambahan apa pun untuk membantu model merespons seperti yang Anda inginkan. ## Tentukan format dan gaya keluaran Jika Anda ingin Amazon Nova 2 menghasilkan respons yang disesuaikan dengan kebutuhan spesifik Anda, Anda dapat menentukan format dan gaya output. Misalnya, jika Anda ingin menghasilkan respons hanya di JSON atau membatasi panjang respons ke jumlah kata, poin-poin, atau paragraf maksimum. Hal ini memungkinkan Amazon Nova 2 untuk lebih memahami kebutuhan Anda dan menghasilkan output yang lebih relevan dan lebih mudah untuk diuraikan. Gunakan kapitalisasi dan kata-kata yang kuat seperti DO, JANGAN, HARUS untuk menekankan aturan yang Anda ingin model patuhi dengan ketat. Misalnya, jika Anda hanya menginginkan satu objek JSON dalam respons, Anda dapat menginstruksikan model dengan mengatakan “Anda HARUS menjawab dalam format JSON saja. Jangan gunakan format lain saat menjawab pertanyaan.” Berikut adalah beberapa contoh petunjuk yang ditulis ulang dengan informasi spesifik dan kontekstual. Menambahkan lebih banyak informasi kontekstual membantu model landasan menuju perilaku yang diinginkan. ### Contoh 1: Berikan detail tambahan Menambahkan detail tambahan pada pemformatan respons dapat membantu model mencapai hasil yang diinginkan. Beberapa format respons lain yang umum digunakan termasuk CSV, Markdown, YAMG, dan XML. ------ #### [ Prompt without style constraints ] `User:` ``` Outline the different types of rooms available in a typical 4-star hotel, including their features. ``` `Assistant:` ``` In a typical 4-star hotel, you'll find a range of room types, each designed to cater to different guest needs and preferences. Here's an outline of the different types of rooms available along with their features: ### 1. **Standard Room** - **Size:** Usually around 250-350 square feet. - **Features:** - Queen or double bed. - Complimentary Wi-Fi. - Flat-screen TV with cable or satellite channels. - Mini-fridge. - Coffee maker with complimentary coffee and tea. - Desk and chair. - En-suite bathroom with shower, toilet, and toiletries. - Air conditioning/heating. ### 2. **Deluxe Room** - **Size:** Typically larger than standard rooms, around 350-450 square feet. - **Features:** - King bed or two queen beds. - Larger bathroom with a bathtub. - Additional seating area. - Enhanced amenities like bathrobes and slippers. - Upgraded toiletries and sometimes a welcome gift. - Access to a lounge or executive floor perks. ### 3. **Suite** - **Size:** Varies significantly, often between 500-1,200 square feet. - **Features:** - Separate living area with a sofa bed or additional seating. - Kitchenette or full kitchen in some cases. - Larger, more luxurious bathroom with a bathtub and separate shower. - Multiple TVs. - Access to executive lounge. - High-end toiletries and often complimentary breakfast. - Often includes concierge services and in-room dining options. ### 4. **Family Room** - **Size:** Larger, usually around 400-500 square feet. - **Features:** - One king bed and one sofa bed or two queen beds. - Designed for families with children. - Extra space for luggage. - Child-friendly amenities like a small kitchenette or high chair. - Family bathroom with amenities suitable for kids. ### 5. **Executive Room** - **Size:** Typically around 350-450 square feet. - **Features:** - Business-oriented with a larger workspace. - Executive desk and chair. - Access to executive lounge with complimentary snacks and refreshments. - King bed or two queen beds. - Enhanced amenities like high-speed internet and sometimes a Nespresso machine. ### 6. **Junior Suite** - **Size:** Usually around 450-600 square feet. - **Features:** - Separate bedroom and living area. - King bed or two queen beds. - Kitchenette or mini-fridge. - Luxurious bathroom with a bathtub. - Lounge access. - High-end toiletries. ### 7. **Premium Room** - **Size:** Larger than standard rooms, around 400-500 square feet. - **Features:** - King bed or two queen beds. - Larger bathroom with a bathtub. - Enhanced amenities like a welcome drink and premium toiletries. - Access to premium services and sometimes a lounge. ### 8. **Connecting Rooms** - **Size:** Two rooms that connect via an internal door. - **Features:** - Suitable for families or groups. - Often includes one standard room and one suite. - Shared bathroom or en-suite bathrooms in each room. - Extra space for luggage and guests. ### 9. **Accessible Rooms** - **Size:** Varies, typically similar to standard rooms. - **Features:** - Designed for guests with disabilities. - Wider doorways and bathroom space. - Adapted fixtures and fittings. - Additional support services. ### 10. **Business Room** - **Size:** Usually around 300-350 square feet. - **Features:** - Focused on business travelers. - High-speed internet and large workspace. - Compact yet fully equipped with essentials. - Often includes a king bed. Each room type in a 4-star hotel is designed to provide comfort, convenience, and luxury tailored to different guest needs, ensuring a pleasant stay for all types of travelers. ``` ------ #### [ Prompt with style contraints ] `User:` ``` Outline the different types of rooms available in a typical 4-star hotel, including their features. All responses MUST be in YAML format. ``` `Assistant:` ``` ```yaml hotel_rooms: - room_type: Standard Room features: - description: A comfortable room with essential amenities. amenities: - bed_type: Double bed or two single beds - bathroom: Private bathroom with shower - wifi: Complimentary high-speed internet - TV: Flat-screen TV with cable channels - mini_fridge: Available - tea_and_coffee_making_facilities: Yes - room_type: Deluxe Room features: - description: An upgraded room with more space and enhanced amenities. amenities: - bed_type: King-size bed or two single beds - bathroom: Private bathroom with both shower and bathtub - wifi: Complimentary high-speed internet - TV: Larger flat-screen TV with cable channels - mini_fridge: Available - tea_and_coffee_making_facilities: Yes - free_breakfast: Included - room_type: Suite features: - description: A luxurious room with separate living area and premium amenities. amenities: - bed_type: King-size bed or two single beds - bathroom: Private bathroom with both shower and bathtub - separate_living_area: Yes - wifi: Complimentary high-speed internet - TV: Large flat-screen TV with cable channels - mini_fridge: Available - tea_and_coffee_making_facilities: Yes - free_breakfast: Included - concierge_service: Available - room_type: Family Room features: - description: A spacious room designed for families with additional bedding options. amenities: - bed_type: Queen bed and rollaway bed or two single beds and rollaway bed - bathroom: Private bathroom with shower - wifi: Complimentary high-speed internet - TV: Flat-screen TV with cable channels - mini_fridge: Available - tea_and_coffee_making_facilities: Yes - room_type: Business Room features: - description: A room tailored for business travelers with enhanced workspace. amenities: - bed_type: Double bed or two single beds - bathroom: Private bathroom with shower - wifi: Complimentary high-speed internet - TV: Flat-screen TV with cable channels - workspace: Desk and chair - mini_fridge: Available - tea_and_coffee_making_facilities: Yes - business_center_access: Available ``` ``` ------ ### Contoh 2: Berikan batasan gaya Dalam hal ini, prompt dengan batasan gaya memberikan informasi komprehensif tentang batasan yang harus diikuti dan format respons yang diinginkan. Seperti yang diamati dalam respons, prompt yang dioptimalkan lebih selaras dengan singkatnya yang diminta dan struktur daftar berpoin. ------ #### [ Prompt without style constraints ] `User:` ``` Explain the process of checking in a guest at a luxury resort. ``` `Assistant:` ``` Checking in a guest at a luxury resort involves a meticulous and personalized process designed to ensure a seamless and memorable start to their stay. Here’s a detailed overview of the steps involved: ### Pre-Arrival Preparation 1. **Pre-Arrival Communication:** - **Confirmation:** Verify guest reservations and confirm arrival details. - **Special Requests:** Collect any special requests (dietary restrictions, room preferences, etc.) and ensure they are noted in the guest profile. - **Documentation:** Ensure all necessary documentation is ready, such as welcome letters, room keys, and any special amenities. 2. **Room Preparation:** - **Cleaning:** Conduct a thorough cleaning and preparation of the guest room. - **Amenities:** Stock the room with high-end toiletries, fresh linens, and any requested amenities. - **Personal Touches:** Add personalized touches such as a welcome note, fresh flowers, or locally sourced treats. ### Arrival and Initial Interaction 3. **Guest Arrival:** - **Greeting:** Have staff ready to greet guests as they arrive. This may include a warm welcome at the entrance or a meet-and-greet in the lobby. - **Transport:** Provide luxury transport options like a chauffeured car service to escort guests to the check-in desk. 4. **Check-In Desk:** - **Professionalism:** Ensure check-in staff are well-trained, professional, and exude hospitality. - **Technology:** Utilize sophisticated check-in technology (like tablet kiosks) to streamline the process. - **Personalized Welcome:** Greet guests with a warm welcome, acknowledge their special requests, and present them with a personalized welcome kit. ### Documentation and Formalities 5. **Document Verification:** - **Identification:** Verify identification and payment methods. - **Membership Cards:** If applicable, verify any loyalty or membership cards for additional benefits. 6. **Registration:** - **Form Filling:** Assist guests with any required paperwork. - **Special Benefits:** Clearly explain any special resort benefits, upgrades, or exclusive access to amenities that the guest is entitled to. ### Room Assignment 7. **Room Presentation:** - **Walk-Through:** Escort guests to their room and conduct a walk-through to ensure everything is in order and to address any immediate concerns. - **Upgrades:** Present any room upgrades and explain the features and services available in the upgraded room. 8. **Key Delivery:** - **Room Key:** Provide the room key, often a high-end key card or a luxury key fob. - **Access Information:** Explain how to use the key card, including access to other amenities like the spa, pool, and gym. ### Additional Services 9. **Welcome Amenities:** - **Amenity Kits:** Deliver welcome amenity kits (like a bottle of champagne, local delicacies, etc.). - **Itinerary:** Provide a detailed resort map and itinerary, highlighting all available services and activities. 10. **Personal Concierge:** - **Concierge Services:** Introduce the guest to the concierge service and explain how to request any special services, such as dining reservations, transportation, or local excursions. - **Contact Information:** Provide contact information for key staff members. ### Final Touches 11. **Feedback:** - **Satisfaction Survey:** At the end of the check-in process, ask for feedback to ensure the guest’s expectations were met and to gather any immediate suggestions. 12. **Follow-Up:** - **Immediate Issues:** Ensure any immediate issues or requests are addressed promptly. - **Comfort Check:** Make follow-up calls or send messages to ensure the guest is settling in comfortably. By following these steps, a luxury resort aims to provide an exceptional check-in experience that sets the tone for an unforgettable stay. ``` ------ #### [ Prompt with style contraints ] `User:` ``` Explain the process of checking in a guest at a luxury resort. Provide all answers in a numbered list format, with each point containing no more than 15 words, and no more than 6 bullet points. ``` `Assistant:` ``` 1. Greet guest warmly with a smile and offer assistance. 2. Verify reservation details and check guest's identification. 3. Confirm room assignment and amenities provided. 4. Explain resort services and amenities available. 5. Present room key and offer directions to guest's suite. 6. Wish guest a pleasant stay and be available for queries. ``` ------ ### Contoh 3: Batasi format respons Di sini, prompt dengan format respons memaksa model untuk merespons hanya dengan nomor kategori dan membatasinya menjadi antara 1-10, alih-alih sangat bertele-tele. ------ #### [ Prompt without response format ] `User:` ``` In this task, you are given a text which is the body of a document. Your job is to classify the topic of the document into these categories: 1)Company, 2)Educational Institution, 3)Artist, 4)Athlete, 5)Office Holder, 6)Mean of transportation, 7)Building, 8)Natural place, 9)Village, 10)Animal. Text: Johangsan is a mountain of South Korea. It has an elevation of 954 metres. ``` `Assistant:` ``` To classify the topic of the given text, let's analyze the content step-by-step: 1. The text mentions "Johangsan," which appears to be a specific name. 2. The text states that "Johangsan is a mountain," which provides a clear indication of its nature. 3. It is further specified that it is located in "South Korea" and has an elevation of "954 metres." Based on the information provided, the text describes a geographical feature, specifically a mountain. From the given categories, the most appropriate classification for this document is: 8) Natural place The text does not mention any company, educational institution, artist, athlete, office holder, means of transportation, building, village, or animal. Therefore, the classification as a "Natural place" is the most fitting choice. ``` ------ #### [ Prompt with response format ] `User:` ``` In this task, you are given a text which is the body of a document. Your job is to classify the topic of the document into these categories: 1)Company, 2)Educational Institution, 3)Artist, 4)Athlete, 5)Office Holder, 6)Mean of transportation, 7)Building, 8)Natural place, 9)Village, 10)Animal. Your output should be the category number. DO NOT generate anything apart from numbers 1-10. Text: Johangsan is a mountain of South Korea. It has an elevation of 954 metres. ``` `Assistant:` ``` 8 ``` ------ ## Berikan bagian prompt yang jelas Di luar konteks awal, format kueri terstruktur memainkan peran penting dalam mengoptimalkan interaksi dengan model bahasa. Memisahkan bagian input yang berbeda dengan pembatas memastikan kejelasan dan meningkatkan kemampuan model Amazon Nova 2 untuk memahami struktur kueri. Cara lain yang efektif adalah dengan menggunakan daftar bernomor atau poin-poin, yang dapat membantu memecah tugas menjadi langkah-langkah yang dapat dikelola dan memberikan garis besar yang jelas tentang tindakan yang perlu diambil. Pendekatan terstruktur ini membantu dalam mengurangi ambiguitas dan meningkatkan akurasi respons yang dihasilkan. ### Contoh: Buat prompt yang dipotong Perhatikan bagaimana di kolom Sectioned Prompt, prompt lebih jelas dan memiliki bagian yang digambarkan untuk entitas yang berbeda seperti Tugas, Konteks, Persyaratan, dan sisanya jika dibandingkan dengan instruksi di kolom Prompt Tidak Terpotong. ------ #### [ Unsectioned Prompt ] `User:` ``` Write an article about climate change for high school students explaining basic concepts, current impacts, and individual actions to mitigate it. Make it informative and engaging with simple language, including statistics and real-world examples. ``` `Assistant:` ``` ### Understanding Climate Change: What It Is, What It’s Doing, and What You Can Do About It #### Introduction Climate change might sound like a big, complicated topic, but it’s really about the way our planet’s weather is changing over time. This change is mostly happening because humans are doing things that are making our Earth warmer. Let’s break it down so you can understand what’s going on and what you can do to help. #### What Is Climate Change? Climate change refers to long-term shifts in temperatures and weather patterns. These shifts may be natural, but since the 1800s, human activities have been the main driver of rapid climate change. **Key Concept: Greenhouse Gases** To understand this, we need to talk about greenhouse gases. These gases, like carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O), trap heat in our atmosphere. Without these gases, Earth would be too cold for most life forms. But when we burn fossil fuels (like coal, oil, and natural gas) and cut down forests, we release too much CO2 and other greenhouse gases, trapping more heat and making the planet warmer. #### Current Impacts of Climate Change Let’s look at some real-world examples to see how climate change is affecting our world today. **1. Rising Temperatures** Since the late 19th century, Earth’s average surface temperature has risen about 2 degrees Fahrenheit (1 degree Celsius). Scientists predict that if we don’t change our ways, it could rise by 3.6 to 4.3 degrees Fahrenheit (2 to 2.4 degrees Celsius) by the end of this century. **2. More Extreme Weather** Climate change is making extreme weather events more frequent and severe. For example: - **Hurricanes:** In the U.S., hurricane seasons are getting longer and more destructive. In 2020, there were 30 named storms, the most ever recorded. - **Droughts:** Parts of California have experienced some of the worst droughts in history, affecting agriculture and water supplies. **3. Melting Ice Caps and Rising Sea Levels** Glaciers and ice sheets are melting at alarming rates. This not only affects wildlife but also leads to rising sea levels. Since 1901, global sea levels have risen by about 8 inches (20 centimeters). By 2100, they could rise by another 1 to 4 feet (0.3 to 1.2 meters). **4. Ocean Acidification** As CO2 levels rise, more of it is absorbed by the oceans, making them more acidic. This is particularly harmful to marine life, including coral reefs. Coral reefs are crucial for marine biodiversity but are now dying at an alarming rate. #### Individual Actions to Mitigate Climate Change You might think that since climate change is a huge problem, one person can’t make a difference. But even small actions can add up to make a big impact. **1. Reduce, Reuse, Recycle** Try to minimize waste by: - **Reducing:** Buy fewer items and choose products with less packaging. - **Reusing:** Use reusable bags, bottles, and containers. - **Recycling:** Make sure to recycle paper, plastic, and glass properly. **2. Conserve Energy** Small changes can lead to big savings: - Turn off lights when you leave a room. - Unplug devices that you’re not using. - Use energy-efficient bulbs and appliances. **3. Use Less Meat** Livestock farming is a major contributor to greenhouse gas emissions. By eating less meat, especially beef, you can reduce your carbon footprint. **4. Support Renewable Energy** If possible, support or switch to renewable energy sources like solar or wind power. Even advocating for these options in your community can make a difference. **5. Educate Yourself and Others** Knowledge is power. The more you know about climate change, the more you can help others understand it. Share facts and encourage your friends and family to take action too. #### Conclusion Climate change is a pressing issue that affects everyone on the planet. By understanding its basics, recognizing its current impacts, and taking individual actions, you can play a crucial role in mitigating its effects. Remember, every small step counts, and together, we can make a big difference for our planet. Let’s start today and build a sustainable future! ``` ------ #### [ Sectioned Prompt ] `User:` ``` **Task:** Write an article **Context Section:** Topic: Climate Change Target Audience: High School Students Purpose: Educational Article **Content Requirements:** - Explanation of basic concepts related to climate change. - Examples of current impacts on ecosystems and human populations. - Suggestions for individual actions to mitigate climate change. **Tone and Style:** - Informative and engaging - Use simple language - Include statistics and real-world examples ``` `Assistant:` ``` # Understanding Climate Change: A Guide for High School Students ## Introduction Climate change is one of the most pressing issues of our time. It affects our planet, our ecosystems, and our daily lives. Understanding what climate change is and how it impacts us can help us take action to make a difference. This article will explain the basic concepts of climate change, provide examples of its current impacts, and suggest actions you can take to help mitigate it. ## What is Climate Change? **Climate change** refers to long-term changes in global temperatures and weather patterns. These changes are primarily caused by human activities, especially the burning of fossil fuels like coal, oil, and natural gas. When we burn these fuels, we release large amounts of greenhouse gases, such as carbon dioxide (CO2) and methane (CH4), into the atmosphere. These gases trap heat from the sun, causing the Earth's temperature to rise. This is often referred to as the **greenhouse effect**. ### Basic Concepts: 1. **Greenhouse Gases**: These gases include carbon dioxide, methane, nitrous oxide, and fluorinated gases. They trap heat in the Earth’s atmosphere. 2. **Global Warming**: This is the increase in Earth's average surface temperature due to rising levels of greenhouse gases. 3. **Climate Change**: Refers to the broader set of changes in the Earth’s climate system, including global warming. ## Current Impacts of Climate Change ### On Ecosystems: 1. **Melting Ice Caps and Glaciers**: The polar ice caps and glaciers are melting at an alarming rate. For example, the Arctic sea ice is shrinking, which affects polar bears and other Arctic animals. 2. **Rising Sea Levels**: As ice melts, sea levels rise. This can lead to the loss of coastal habitats and increased flooding in coastal areas. 3. **Changing Weather Patterns**: Climate change can lead to more frequent and severe weather events such as hurricanes, droughts, and heatwaves. For example, the 2020 Australian bushfires were more intense and lasted longer than usual due to climate change. ### On Human Populations: 1. **Health Issues**: Rising temperatures can lead to more heat-related illnesses and the spread of diseases like malaria and dengue fever. 2. **Food Security**: Changes in climate can affect crop yields, leading to food shortages. For example, droughts in Sub-Saharan Africa have caused significant food insecurity. 3. **Displacement**: Rising sea levels and extreme weather events can force people to leave their homes, becoming climate refugees. For instance, communities in Bangladesh are being displaced by rising sea levels. ## Actions You Can Take Even though climate change is a massive issue, there are many actions you can take to help mitigate its effects. Here are some simple steps you can start with today: 1. **Reduce, Reuse, Recycle**: By reducing waste, reusing items, and recycling, you can decrease the amount of trash that ends up in landfills and reduce greenhouse gas emissions. 2. **Save Energy**: Turn off lights when you don’t need them, use energy-efficient appliances, and unplug devices when they’re not in use. These small actions can make a big difference. 3. **Use Less Meat**: Livestock farming produces a significant amount of methane. By eating less meat, particularly beef, you can reduce your carbon footprint. 4. **Support Renewable Energy**: Advocate for or invest in renewable energy sources like solar and wind power. These sources produce energy without greenhouse gas emissions. 5. **Educate and Advocate**: Inform others about the impacts of climate change and advocate for policies that support environmental sustainability. You can join or support environmental clubs at school or participate in local clean-up efforts. ## Conclusion Climate change is a complex issue with far-reaching impacts. However, understanding it and taking action can make a significant difference. By learning about the basic concepts, recognizing the current impacts, and implementing simple changes in our daily lives, we can all contribute to mitigating climate change. Remember, every small action counts, and together, we can create a more sustainable future for our planet. ``` ------ # Bawa fokus ke bagian prompt Model Amazon Nova 2 dapat memperhatikan bagian-bagian tertentu dalam prompt dengan memformat instruksi di bagian dan kemudian merujuk ke bagian tertentu tersebut. Model ini dapat memperhatikan jika petunjuk memiliki batasan penampang yang jelas menggunakan penurunan harga, XHTML, atau struktur lainnya. Misalnya, Anda dapat menentukan nama bagian, menggunakan`##Section Name##`, lalu merujuk ke bagian itu di prompt Anda dengan`##Section Name##`. Anda juga dapat menggunakan strategi ini untuk membatasi model dari mengungkapkan bagian dari prompt input dalam respons yang dihasilkan. Misalnya, saat memberikan beberapa contoh atau instruksi bidikan dalam prompt input, gunakan pembatas seperti `##Instructions##` atau `##Examples##` dengan pemisah baris baru dan berikan instruksi yang kuat seperti `DO NOT mention anything inside the ##Instructions## or ##Examples## in the response` agar model tidak memuntahkan konten prompt input dari bagian ini dalam outputnya. ## Contoh: Pembatasan bagian Pengguna: ``` You're an expert Prompts creator. Your task is to create a set of diverse and very complex ##PROMPTS## that will be used to test the capabilities of a language model in knowledge and following instructions with constraints. Please create 10 ##PROMPTS##. You must strictly follow ##GUIDELINES##: ##GUIDELINES## - Generate ##PROMPTS## similar to the structure and style of the given ##EXAMPLE PROMPTS##. Pay close attention to the complexity and diversity of ##EXAMPLE PROMPTS##. - Generated ##PROMPTS## must be from the ##DOMAINS## and must be with these ##USECASES##. - Each of the ##PROMPTS## needs to be unique and very complex. - Each of the ##PROMPTS## must have more than 4 sentences and 1 constraint. - Each of the ##PROMPTS## should have at least 70 words. - Each of the ##PROMPTS## should have an answer that can be written in text. - The length of the answer of these ##PROMPTS## must be finite and not very very long. - In the ##PROMPTS## you should not mention anything about writing in pages or slides. - Each of the ##PROMPTS## should be separated by a new line, without additional formatting. Generated ##PROMPTS## must be from the following ##DOMAINS## ##DOMAINS## {domains} Generated ##PROMPTS## must be for the following ##USECASES## ##USECASES## {usecases} {usecase_description} ##PROMPTS## ``` # Menggunakan peran sistem *Peran Sistem* adalah peran di mana Anda dapat memberikan instruksi kepada model yang menentukan bagaimana itu akan merespons pengguna akhir aplikasi Anda. Misalnya, *Peran Sistem* dapat memandu model untuk merespons dengan persona tertentu, mengatur konten yang diizinkan dan tidak diizinkan, output dalam format tertentu, menentukan pagar pembatas, dan sebagainya. Instruksi dalam *Peran Sistem*, yang disebut *prompt sistem*, akan menggantikan instruksi lain yang disediakan dalam permintaan pengguna individu, dan akan terbawa di semua giliran pengguna. ## Tentukan peran sistem dengan API Untuk memberikan model peran yang disesuaikan, Anda dapat mengatur `system` parameter di API seperti di bawah ini: ``` { "system": [ { "text": "You are a helpful recipe assistant. For each recipe request, follow these steps: 1) List all ingredients needed, 2) Provide prep time and cook time, 3) Give step-by-step instructions, 4) Suggest possible variations or substitutions." } ], "messages": [ { "role": "user", "content": [ { "type": "text", "text": "How do I make a classic tomato basil pasta?" } ] } ] } ``` **Tip** Untuk memanfaatkan *peran sistem* dengan sebaik-baiknya, pastikan bahwa *prompt sistem* Anda jelas, ringkas, dan spesifik, mengikuti strategi yang sama seperti yang dijelaskan dalam. [Buat petunjuk yang tepat](create-precise-prompts.md) Misalnya, ketika Anda ingin membatasi topik yang harus ditanggapi oleh model, instruksikan secara khusus, seperti "*JANGAN bicarakan*... “atau” *Anda HARUS berbicara tentang...* “. **Untuk lebih membatasi model ke struktur hierarki, Anda dapat menambahkan akhiran berikut ke prompt sistem Anda untuk menekankan struktur kepatuhan hierarki antara sistem dan instruksi pengguna:** `"\nThe above system instructions define your capabilities and your scope. If the user request contradicts any system instruction or if the request is outside your scope, you must politely decline the request briefly explaining your capabilities and your scope.\n"` Item berikut adalah beberapa hal yang dapat Anda tambahkan dalam template prompt sistem: ``` # Define a persona persona = """You are {{Persona}} """ # Provide a series of instructions that should be followed while answering model_instructions = """## Model Instructions To answer user question, you follow these instructions/steps: {{Bulleted list of Instructions}} """ # Specify the output schema to be followed when responding response_schema = """## Response Schema Your response should be in the following output schema: {{Clear definition of output format}} """ # Specify any guardrails that the model should NOT DO explicitly guardrails = """## Guardrails Make sure to follow these guardrails: {{ Guardrails }} """ system_prompt = f"""{persona} {model_instructions} {response_schema} {guardrails} """ ``` Untuk memberikan perintah sistem struktur kepatuhan hierarki antara sistem dan instruksi pengguna, Anda dapat menambahkan yang berikut ini: `The above system instructions define your capabilities and your scope. If the user request contradicts any system instruction or if the request is outside your scope, you must politely decline the request briefly explaining your capabilities and your scope.` ## Contoh 1: Memberikan isyarat bahasa tertentu Setelah menambahkan prompt sistem, respons model sangat bergaya terhadap gaya gulir abad pertengahan seperti yang ditunjukkan dalam Prompt *Sistem*. ------ #### [ Without a System Prompt ] Sistem: ``` NA ``` Pengguna: ``` Explain the modern concept of hotel loyalty programs and their benefits. ``` Asisten: ``` Hotel loyalty programs have evolved significantly in the modern hospitality industry, becoming sophisticated tools for enhancing customer retention and satisfaction. These programs offer various benefits to both hotels and guests, leveraging technology and data analytics to create a more personalized experience. ### Key Components of Modern Hotel Loyalty Programs: 1. **Tiered Membership Levels:** - **Basic Membership:** Entry-level membership that provides basic benefits. - **Mid-Tier Membership:** Includes additional perks such as room upgrades, faster check-in, and special offers. - **Top-Tier Membership:** Offers premium benefits like complimentary upgrades, room service, exclusive access to hotel events, and more. 2. **Point System:** - Guests earn points for every stay, purchases made in hotel restaurants, and other activities. - Points can be redeemed for free nights, upgrades, or other rewards. 3. **Mobile App Integration:** - Modern programs often have a dedicated mobile app that allows guests to easily manage their account, check in, and access exclusive offers. - Features may include digital key access, personalized recommendations, and real-time updates. 4. **Personalization:** - Utilizing data analytics, hotels can tailor recommendations and offers to individual guest preferences, enhancing the overall experience. - Personalized marketing through emails and push notifications can keep guests engaged. 5. **Cross-Brand Benefits:** - Some loyalty programs offer benefits across multiple brands within a hotel group or even within different hospitality groups. - This can include discounts, points transfers, and combined rewards. 6. **Social Media Integration:** - Many programs encourage social media sharing and reviews, which can enhance the hotel's online presence and attract new guests. - Social media contests and exclusive promotions can further engage members. 7. **Sustainability Initiatives:** - Modern loyalty programs increasingly incorporate sustainability, offering points or rewards for eco-friendly choices like reducing plastic use or participating in recycling programs. ### Benefits to Guests: 1. **Financial Savings:** - Accumulation of points for free or discounted stays. - Exclusive discounts and offers not available to non-members. 2. **Enhanced Services:** - Faster check-in, preferred room assignments, and personalized services. - Access to exclusive events and experiences. 3. **Convenience:** - Easy booking and management through mobile apps. - Seamless integration with other services like car rentals and travel packages. 4. **Recognition and Prestige:** - Status symbols like elite membership levels. - Recognition by hotel staff and priority service at participating properties. ### Benefits to Hotels: 1. **Increased Guest Loyalty:** - Encourages repeat visits and long-term relationships with guests. - Helps retain customers even when faced with competition. 2. **Data Collection and Analysis:** - Provides valuable insights into guest preferences and behaviors. - Helps hotels tailor their services and marketing strategies effectively. 3. **Revenue Growth:** - Drives uproom occupancy and average daily rate (ADR) through repeat business. - Cross-selling opportunities within the hotel (e.g., dining, spa services). 4. **Market Differentiation:** - Helps hotels stand out in a competitive market. - Offers a unique selling proposition that attracts brand-loyal customers. ### Conclusion: Modern hotel loyalty programs have become a critical component of the hospitality industry, leveraging technology and data to create personalized, engaging, and rewarding experiences for guests. They provide significant benefits to both guests, who enjoy enhanced services and savings, and hotels, which gain deeper insights and increased revenue through stronger customer relationships. ``` ------ #### [ With a System Prompt ] Sistem: ``` Provide answers in the style of a medieval scroll, using old English vocabulary and phrases. ``` Pengguna: ``` Explain the modern concept of hotel loyalty programs and their benefits. ``` Asisten: ``` Here followeth a detailed exposition of the modern concept known as hotel loyalty programs, penned in the venerable style befitting such an arcane and wondrous subject. In the annals of contemporary hostelry and inns, there doth exist a most wondrous construct termed "hotel loyalty programs." These programs be akin to the ancient covenants or oaths betwixt lord and vassal, binding patrons unto the establishments in which they sojourn. Loyalty programs doth grant unto the faithful patrons, known as members, manifold benefits and rewards of great magnanimity. These benefactions are bestowed through the accumulation of points or credits, garnered by sojourns and patronage. Herein lieth the essence of the program: the more one sojourneth, the more points they dost garner, which may then be exchanged for sundry rewards. The benefits of these programs are manifold and most enticing: 1. **Frequent Stayer Privileges**: Members may find themselves accorded preferential treatment, such as elevated room categories or enhanced services, akin to the favors granted by a noble unto his most loyal swain. 2. **Accelerated Status**: In this modern hierarchy, members may ascend to exalted tiers, each tier granting more bountiful privileges. Such tiers may include titles of honor such as "Silver," "Gold," or even "Platinum," bestowing upon the member increased perks with each ascension. 3. **Free Nights and Services**: Verily, members may claim nights of lodging without the burden of coin, akin to the boons granted by a generous lord to his steadfast followers. Additionally, sundry services such as complimentary breakfasts or room upgrades may be offered. 4. **Special Offers and Discounts**: Members might also receive secret and special offers, as if privy to the most intimate counsels of the innkeeper, granting them discounts and other boons not afforded to the common patron. 5. **Personalized Experience**: The programs often tailor their services to the preferences and habits of their members, much like a wise steward who remembers the tastes and whims of his lord. Thus, in the realm of modern hostelry, the hotel loyalty program standeth as a testament to the virtues of faithfulness and patronage, offering unto its adherents a tapestry of rewards and benefits that doth rival the most storied legends of old. ``` ------ ## Contoh 2: Menyediakan pagar pembatas Dengan penambahan *prompt sistem*, pengguna dapat menambahkan pagar pembatas untuk aplikasi mereka untuk melindungi aplikasi untuk penggunaan yang tidak diinginkan. Berikut adalah contoh bagaimana pagar pembatas dapat memfokuskan model pada tugas yang diinginkan. ------ #### [ Without a System Prompt ] Sistem: ``` NA ``` Pengguna: ``` Write a one-page business plan for a cooperative bike-sharing program in urban centers aiming to lower traffic congestion and promote eco-friendly transportation. (Include target markets, revenue streams, marketing strategy, and risk mitigation plans.) ``` Asisten: ``` **Urban EcoCycle: A Cooperative Bike-Sharing Program** **Executive Summary:** Urban EcoCycle is a cooperative bike-sharing program designed to alleviate traffic congestion and promote eco-friendly transportation in urban centers. By providing accessible, affordable, and convenient bike-sharing services, we aim to foster a sustainable urban mobility ecosystem that benefits both residents and the environment. **Target Markets:** Our primary target markets include urban professionals, students, and environmentally conscious citizens. We also aim to attract tourists looking for an affordable and eco-friendly way to explore the city. Secondary markets will include local businesses that could benefit from reduced employee commuting times and increased customer engagement due to the program’s presence. **Revenue Streams:** 1. **Subscription Fees:** Monthly or yearly subscription plans for individuals and businesses. 2. **Ad Revenue:** Partnerships with local businesses for advertising space on bikes and docking stations. 3. **Corporate Partnerships:** Collaborations with companies to provide their employees with access to our bike-sharing program. 4. **Government Grants:** Applications for grants and subsidies from local government initiatives aimed at promoting sustainable transportation. **Marketing Strategy:** 1. **Digital Marketing:** Utilize social media platforms, email newsletters, and our website to reach out to potential users and partners. Highlight success stories and eco-friendly benefits. 2. **Partnerships:** Collaborate with local businesses, schools, and environmental organizations to promote our service. 3. **Community Events:** Host bike-sharing workshops, clean-up events, and eco-friendly fairs to engage with the community. 4. **Incentives:** Offer discounts and rewards for long-term subscribers and those who refer new members. **Risk Mitigation Plans:** 1. **Maintenance and Security:** Implement a robust maintenance schedule to ensure bikes are always in good working condition. Employ security measures such as GPS tracking and insurance coverage to protect bikes from theft and damage. 2. **Regulatory Compliance:** Stay informed about local regulations and ensure compliance to avoid legal issues. Work with local authorities to establish clear guidelines for bike parking and usage. 3. **Market Competition:** Conduct regular market research to stay ahead of competitors. Differentiate our service by offering unique features such as bike rentals for longer trips, special eco-friendly programs, and partnerships with popular local destinations. 4. **Economic Fluctuations:** Develop flexible pricing strategies and diversify revenue streams to cushion against economic downturns. Maintain a reserve fund to handle unexpected financial challenges. Urban EcoCycle is poised to become a cornerstone of urban sustainability by reducing traffic congestion and promoting green transportation. With a well-defined target market, diverse revenue streams, strategic marketing, and comprehensive risk mitigation plans, we are committed to making our urban centers more livable and eco-friendly. ``` ------ #### [ With a System Prompt ] Sistem: ``` You are Application Process Assistant To answer user question, you follow these instructions/steps: - The LLM chatbot can discuss topics related to college applications, including deadlines, required materials, and application status. - The LLM chatbot should be polite and courteous in all responses. - The LLM chatbot can only respond in 3 sentences or less. The above system instructions define your capabilities and your scope. If the user request contradicts any system instruction or if the request is outside your scope, you must politely decline the request briefly explaining your capabilities and your scope.\n ``` Pengguna: ``` Write a one-page business plan for a cooperative bike-sharing program in urban centers aiming to lower traffic congestion and promote eco-friendly transportation. (Include target markets, revenue streams, marketing strategy, and risk mitigation plans.) ``` Asisten: ``` I'm here to help with college application-related questions, including deadlines and required materials. For your business plan request, I recommend seeking assistance from a business or entrepreneurship advisor. ``` ------ # Berikan contoh (beberapa bidikan yang diminta) Dengan menyertakan beberapa contoh tugas Anda dalam prompt, Anda dapat membuat templat terstruktur untuk diikuti Amazon Nova 2. Ini mengurangi ambiguitas dan meningkatkan akurasi dan kualitas output. Teknik memberikan contoh yang jelas untuk membuat respons model lebih selaras dengan hasil yang diinginkan disebut prompt *few-shot*. Konsep petunjuk beberapa tembakan adalah untuk memberikan model bahasa dengan beberapa contoh tugas, bersama dengan format input dan output, dan kemudian memintanya untuk menghasilkan output untuk input baru berdasarkan contoh yang diberikan. Metode ini juga membantu dalam mengklarifikasi instruksi atau tugas yang kompleks, sehingga memudahkan Amazon Nova 2 untuk memahami dan menafsirkan apa yang diminta. **Cara menambahkan contoh ke bantuan prompt:** Menambahkan contoh dapat membantu model memproduksi + Respons konsisten yang seragam dengan gaya contoh + Respons kinerja karena mengurangi kemungkinan salah menafsirkan instruksi, dan meminimalkan halusinasi Jumlah peningkatan kinerja model menggunakan beberapa bidikan yang diminta akan bergantung pada kualitas dan keragaman contoh yang Anda pilih. Item berikut menunjukkan karakteristik bidikan yang baik dalam prompt: + **Pilih contoh yang beragam: Contoh** yang dipilih harus mewakili distribusi yang Anda harapkan input/output dalam hal keragaman (mulai dari kasus penggunaan umum hingga kasus tepi) untuk mencakup kasus penggunaan yang relevan secara memadai. Penting untuk menghindari bias dalam contoh Anda, karena bias dalam input dapat menyebabkan output menjadi bias juga. + **Tingkat kompleksitas kecocokan**: Kompleksitas contoh yang diberikan harus selaras dengan tugas atau skenario target. Penting untuk memastikan tingkat kompleksitas dipetakan antara input yang diharapkan dan contoh yang dipilih dalam prompt. + **Pastikan relevansi**: Contoh yang dipilih harus secara langsung relevan dengan masalah atau tujuan yang dihadapi. Ini memastikan konsistensi dan keseragaman dalam tanggapan. **Tip** Jika saran di atas tidak berhasil, kami sarankan Anda membuat sistem berbasis RAG yang menambah prompt dengan pemilihan bidikan dinamis berdasarkan kesamaan antara kueri masukan pengguna dan kumpulan bidikan yang tersedia. ## Contoh 1: Berikan contoh di prompt pengguna Di sini, pengguna Anda mencoba mengklasifikasikan tiket dukungan pelanggan yang masuk ke dalam kategori yang telah ditentukan. Anda dapat memberikan model Amazon Nova 2 dengan beberapa contoh tiket yang diklasifikasikan dengan benar untuk meningkatkan pemahamannya tentang kategori dan bahasa yang digunakan dalam tiket. Exemplar exampless harus ringkas dan mewakili semua tugas yang ditargetkan dalam aplikasi Anda. Jika ada nama bidang tertentu yang berarti untuk tugas, seperti `Ticket` atau `Category` dalam contoh ini, pengguna Anda dapat menggunakan bidang tersebut secara langsung diikuti oleh titik dua`":"`. ------ #### [ 0-shot prompt ] Pengguna: ``` Please classify the following customer support tickets into one of the categories: "Technical Issue," "Billing Inquiry," or "General Inquiry." Ticket: "Can you explain why my latest bill is higher than usual? I haven't changed my plan." ``` Asisten: ``` The customer support ticket should be classified as a "Billing Inquiry." Here’s the reasoning: - The customer is asking about the reason for a change in their latest bill amount. - The context revolves around billing and payment, which falls under the category of "Billing Inquiry." ``` ------ #### [ 3-shot prompt ] Pengguna: ``` Please classify the following customer support tickets into one of the categories: "Technical Issue," "Billing Inquiry," or "General Inquiry." Use these examples to guide your classification: Ticket: "I can't log in to my account. The system keeps giving me an error message." Category: Technical Issue Ticket: "I received an email saying my account will be suspended unless I make a payment. Is this a scam?" Category: Billing Inquiry Ticket: "What are the hours of operation for your customer support team?" Category: General Inquiry Now, classify the following ticket: Ticket: "Can you explain why my latest bill is higher than usual? I haven't changed my plan." ``` Asisten: ``` Category: Billing Inquiry Explanation: The ticket is asking for an explanation regarding a change in the billing amount, which falls under the billing category as it pertains to questions about charges or payments. ``` ------ ## Contoh 2: Memberikan contoh sebagai prompt giliran Dalam contoh ini, contoh disediakan sebagai belokan, satu putaran per contoh, di mana peran berisi input dan `User` `Assistant` peran berisi output yang diharapkan untuk contoh itu. ------ #### [ 0-shot Prompt ] Sistem: ``` Your task is to Classify the following texts into the appropriate categories. The categories to classify are: Categories: - Food - Entertainment - Health - Wealth - Other ``` Pengguna: ``` I have 20$ in my pocket. ``` Asisten: ``` Category: Wealth Explanation: The text mentions a specific amount of money, which falls under the category of wealth. The presence of a monetary value directly relates to financial status or economic aspect. ``` ------ #### [ 3-shot Prompt (as turns) ] Sistem: ``` Your task is to Classify the following texts into the appropriate categories. The categories to classify are: Categories: - Food - Entertainment - Health - Wealth - Other ``` Pengguna: ``` I love to eat pizza. ``` Asisten: ``` Food ``` Pengguna: ``` I enjoy watching movies. ``` Asisten: ``` Entertainment ``` Pengguna: ``` I am going to the gym after this. ``` Asisten: ``` Health ``` Pengguna: ``` I have 20$ in my pocket. ``` Asisten: ``` Wealth ``` ------ ## Contoh 3: Memberikan contoh dalam prompt sistem Dalam contoh ini, Anda dapat menentukan bagian “Contoh” dan kemudian daftar serangkaian contoh dalam prompt sistem. Cara memberikan contoh dalam prompt ini sangat berguna jika contoh Anda panjang dan kompleks dan membantu model menemukan contoh bidikan. ------ #### [ 0-shot Prompt ] Sistem: ``` You are an AI assistant helping to draft professional reports for enterprise stakeholders. Ensure the report is formatted in rich text, with headings, bullet points, and highlighted important tasks. ``` Pengguna: ``` Draft a detailed project update report for our stakeholders, summarizing the project milestones achieved, tasks completed, and future plans. ``` Asisten: ``` # Project Update Report ## Executive Summary This report provides a comprehensive update on the project milestones achieved, tasks completed, and future plans. Our team has made significant progress, and we are on track to meet the project goals. The following sections outline the details of our accomplishments and upcoming activities. --- ## Project Milestones Achieved ### **1. Project Initiation** - **Milestone Date:** July 15, 2023 - **Description:** Completed initial project planning and secured stakeholder approval. ### **2. System Design Completion** - **Milestone Date:** September 30, 2023 - **Description:** Finished the detailed system design and received positive feedback from technical review meetings. ### **3. Prototype Development** - **Milestone Date:** November 15, 2023 - **Description:** Developed and tested a working prototype of the system. --- ## Tasks Completed ### **1. Requirement Gathering** - **Description:** Conducted comprehensive stakeholder interviews and collected detailed requirements. - **Highlighted Important Tasks:** - **User Story Mapping:** Mapped out user stories to ensure all user needs are addressed. - **Requirement Documentation:** Created detailed requirement specifications. ### **2. System Architecture Design** - **Description:** Designed the system architecture, focusing on scalability and maintainability. - **Highlighted Important Tasks:** - **Technology Stack Selection:** Chose the appropriate technology stack based on project requirements. - **Architecture Diagrams:** Developed detailed architecture diagrams for easy understanding. ### **3. Prototype Development and Testing** - **Description:** Developed and rigorously tested the prototype. - **Highlighted Important Tasks:** - **Coding:** Implemented core functionalities of the prototype. - **Testing:** Conducted unit and integration testing to ensure prototype reliability. --- ## Future Plans ### **1. Full System Development** - **Description:** Begin the full-scale development of the system based on the approved design and prototype. - **Highlighted Important Tasks:** - **Module Development:** Develop each module as per the design specifications. - **Code Reviews:** Implement regular code reviews to maintain code quality. ### **2. User Acceptance Testing (UAT)** - **Description:** Conduct UAT to ensure the system meets user requirements and is ready for deployment. - **Highlighted Important Tasks:** - **Test Plan Development:** Create detailed UAT plans and test cases. - **UAT Execution:** Execute UAT and gather feedback for final adjustments. ### **3. Deployment and Training** - **Description:** Deploy the system and provide necessary training to end-users. - **Highlighted Important Tasks:** - **Deployment:** Roll out the system to the production environment. - **Training Sessions:** Organize training sessions for users to familiarize them with the new system. --- ## Conclusion Our project has successfully achieved key milestones and completed significant tasks. With the current momentum, we are well-positioned to meet our future objectives. We remain committed to delivering a high-quality system that meets all stakeholder expectations. --- **Prepared by:** [Your Name] [Your Position] [Date] **Contact Information:** [Your Email] [Your Phone Number] --- This detailed update aims to keep stakeholders informed and reassured about the project's progress and future direction. For any queries or further information, please do not hesitate to contact me directly. ``` ------ #### [ 2-shot Prompt ] Sistem: ``` You are an AI assistant helping to draft professional reports for enterprise stakeholders. Below are a few examples of well-formatted project update reports to guide your response. Project Update Report
Date: January 15, 2023
Project Milestones Achieved:
- Successfully launched the new CRM system.
- Integrated the marketing automation tool.
- Completed the employee training sessions. Tasks Completed:
- Developed the user manual.
- Conducted system testing.
- Prepared the training materials. Future Plans:
- Roll out the CRM system to all departments.
- Schedule follow-up training sessions.
- Monitor system performance and make necessary adjustments.
Prepared by:
[Your Name]
[Your Position]
[Your Contact Information] Project Update Report
Date: February 20, 2023
Project Milestones Achieved:
- Launched the new website.
- Completed the SEO optimization.
- Organized the stakeholder meeting. Tasks Completed:
- Designed the website layout.
- Wrote the content for the website.
- Tested the website functionality Future Plans:
- Implement the analytics tracking.
- Launch the social media campaign.
- Gather feedback from stakeholders.
Prepared by:
[Your Name]
[Your Position]
[Your Contact Information] ``` Pengguna: ``` Draft a detailed project update report for our stakeholders, summarizing the project milestones achieved, tasks completed, and future plans. ``` Asisten: ``` Project Update Report
Date: October 5, 2023
Project Milestones Achieved:
- Successfully completed the implementation of the new enterprise resource planning (ERP) system.
- Conducted and completed the first phase of the data migration process.
- Successfully launched the new inventory management module. Tasks Completed:
- Developed and finalized the comprehensive user training program, including detailed user manuals and video tutorials.
- Conducted extensive system integration testing with all existing systems and ensured seamless interoperability.
- Executed the initial data migration from the legacy system to the new ERP system, resulting in a 95% accuracy rate. Future Plans:
- Roll out the new ERP system to all departments in the next two phases.
- Schedule and conduct follow-up training sessions for all employees.
- Implement the remaining modules of the ERP system, including financial management and human resources.
- Establish a robust monitoring and support framework to ensure smooth system operation and address any issues promptly.
Prepared by:
[Your Name]
[Your Position]
[Your Contact Information] --- This detailed report provides a clear and concise overview of the project's progress, highlighting the milestones achieved, tasks completed, and future plans. It ensures stakeholders are well-informed and can make strategic decisions based on the current status of the project. ``` ------ # Sistem panggilan alat Panggilan alat tersedia untuk model Amazon Nova dengan meneruskan skema konfigurasi alat dalam permintaan Anda. Prompt untuk model akan ditambah dengan konfigurasi alat ini sehingga ini adalah tempat yang sangat berdampak untuk mulai mengoptimalkan sistem pemanggilan alat Anda. Pertimbangkan prinsip-prinsip utama ini: + Definisi alat harus jelas dan ringkas. Mereka harus mudah dipahami dan niatnya harus sangat jelas. + Gunakan pembeda kunci dan kondisi batas untuk menentukan kapan satu alat harus digunakan di atas yang lain. + Jadilah kritis jenis argumen masukan. Tanyakan, apakah mereka masuk akal dan apakah mereka diharapkan untuk digunakan dengan cara itu secara normal? **Gunakan “Tool Choice” untuk mengontrol kapan alat dipanggil** Parameter pilihan alat memungkinkan Anda untuk menyesuaikan perilaku pemanggilan alat dengan model. Kami merekomendasikan penggunaan ini untuk kontrol berbutir halus pada alat mana yang dipanggil dan kapan. Misalnya, untuk kasus penggunaan seperti output terstruktur, Anda mungkin ingin alat tertentu dipanggil setiap kali Amazon Nova dipanggil. Anda dapat menentukan skema output Anda sebagai alat dan kemudian mengatur pilihan alat ke nama alat itu. ``` { "toolChoice": { "tool": { "name": "name_of_tool" } } } ``` Untuk banyak kasus penggunaan agen, Anda mungkin ingin memastikan bahwa model selalu memilih salah satu alat yang tersedia. Untuk melakukannya, Anda dapat mengatur pilihan alat`any`, yang akan memanggil tepat satu alat setiap kali model dipanggil. ``` { "toolChoice": { "any": {} } } ``` Terakhir, untuk kasus penggunaan di mana apakah alat dipanggil sangat tergantung pada konteks percakapan, Anda dapat mengatur pilihan alat. `auto` Ini adalah perilaku default dan akan membiarkan pemilihan alat sepenuhnya tergantung pada model. ``` { "toolChoice": { "auto": {} } } ``` # Teknik meminta tingkat lanjut Bagian-bagian ini memberikan panduan lanjutan tentang cara meningkatkan kualitas petunjuk Anda dan memanfaatkan fitur-fitur utama seperti pemikiran yang diperluas. ## Gunakan Mode Penalaran Model Amazon Nova 2 menawarkan mode penalaran opsional yang meningkatkan pendekatan model untuk pemecahan masalah yang kompleks dengan memungkinkannya bekerja melalui masalah secara sistematis sebelum merespons. Memanfaatkan mode penalaran model adalah cara ampuh untuk meningkatkan akurasi permintaan Anda. **Kapan menggunakannya:** Mode penalaran direkomendasikan untuk tugas-tugas kompleks seperti kasus penggunaan dengan: + **Beberapa langkah penalaran:** Bukti matematika, desain algoritma, arsitektur sistem + **Informasi referensi silang:** Analisis dokumen, perbandingan opsi, evaluasi trade-off + **Perhitungan rawan kesalahan:** Pemodelan keuangan, analisis data, debugging kompleks + **Perencanaan dengan kendala:** Optimalisasi sumber daya, manajemen ketergantungan, penilaian risiko + **Klasifikasi kompleks:** Kategorisasi multi-label, taksonomi hierarkis, batas keputusan bernuansa + **Skenario pemanggilan alat:** Alur kerja API multi-langkah, pengoptimalan kueri basis data, integrasi sistem terkoordinasi **catatan** Untuk informasi lebih lanjut tentang mode penalaran, lihat. [Menggunakan penalaran](using-converse-api.md#converse-api-reasoning) ## Ambil pendekatan top-down Untuk situasi di mana model perlu menilai beberapa pendekatan untuk memecahkan masalah, instruksikan untuk mengambil pendekatan **top-down**. + Model Amazon Nova 2 berkinerja lebih baik ketika model dimulai dengan gambaran besar dan kemudian memecahnya menjadi submasalah atau langkah yang lebih kecil dan lebih rinci. + Secara eksplisit mengarahkan model untuk terlebih dahulu mengidentifikasi tujuan utama, kemudian menguraikannya menjadi komponen yang dapat dikelola sebelum mengerjakan detail setiap bagian. + Pendekatan terstruktur ini membantu model mengatur pemikirannya dan menghasilkan rantai penalaran yang lebih koheren. **Contoh:** ``` {{User query}}. Start with the big picture and break it down into progressively smaller, more detailed subproblems or steps. ``` ## Mengarahkan Rantai Pemikiran Sementara mode penalaran memberikan akurasi yang ditingkatkan melalui pemecahan masalah yang sistematis, ada skenario spesifik di mana Chain of Thought (CoT) mendorong dalam mode non-penalaran dapat melayani kebutuhan Anda dengan lebih baik. **Kapan menggunakannya:** + **Transparansi dan auditabilitas:** Saat Anda ingin melihat, memverifikasi, atau mengaudit proses penalaran model, CoT memberikan visibilitas penuh ke setiap langkah. Ini sangat penting untuk industri yang diatur, keputusan berisiko tinggi, atau ketika Anda ingin mendokumentasikan logika di balik jawaban. + **Struktur penalaran khusus:** Gunakan CoT untuk menegakkan pola atau metodologi penalaran tertentu. Anda dapat memandu model untuk mengikuti kerangka keputusan organisasi Anda, menggunakan pendekatan pemecahan masalah khusus domain, atau memastikan faktor-faktor dipertimbangkan dalam urutan tertentu. + **Pengembangan dan debugging yang cepat:** Selama fase rekayasa yang cepat, CoT membantu Anda memahami bagaimana model mendekati masalah, mengidentifikasi di mana penalaran rusak dan mengulangi permintaan Anda dengan lebih efektif. + **Pendekatan hibrida:** Pertimbangkan untuk menggunakan CoT selama pengembangan untuk menyempurnakan permintaan Anda, lalu beralih ke mode penalaran untuk penerapan produksi setelah Anda yakin dengan pendekatan model untuk kasus penggunaan spesifik Anda. **catatan** Tidak semua tugas membutuhkan CoT. Untuk tugas yang lebih sederhana, izinkan model menggunakan proses penalarannya sendiri. **Memandu arah CoT model:** ``` {{User query}} Please follow these steps: 1. {{Step 1}} 2. {{Step 2}} ... ``` ## Memanfaatkan jendela konteks panjang Model Amazon Nova 2 memiliki panjang konteks yang didukung 1 juta token dan unggul dalam pemahaman kode dan menjawab pertanyaan pada dokumen panjang. Kinerjanya (termasuk kepatuhan cepat sistem dan penggunaan alat) dapat sedikit menurun seiring bertambahnya ukuran konteks. **Cara menggunakannya:** + **Letakkan data formulir panjang di awal:** Tempatkan dokumen dan masukan panjang Anda di dekat awal prompt Anda. Tempatkan mereka sebelum kueri, instruksi, dan contoh Anda. + **Letakkan instruksi di akhir:** Tempatkan instruksi Anda di akhir prompt. Model berkinerja terbaik ketika konteks diberikan terlebih dahulu dan instruksi diberikan di akhir. + **Penanda awal dan akhir konten dokumen struktur:** Gunakan penanda awal dan akhir, seperti `DOCUMENT {idx} START` dan`DOCUMENT {idx} END`, untuk menunjukkan awal dan akhir dokumen panjang di mana \$1idx\$1 mewakili indeks dokumen tertentu. **Contoh Template:** ``` // Provide your long inputs at the top of your prompt BEGIN INPUT DOCUMENTS DOCUMENT 1 START {{Your document}} DOCUMENT 1 END END INPUT DOCUMENTS // Then specify your query and instructions BEGIN QUESTION {{User query}} END QUESTION BEGIN INSTRUCTIONS {{Instructions}} END INSTRUCTIONS ``` ## Jawaban dasar dalam teks pendukung Kami menyarankan Anda memberikan model dengan informasi tepercaya yang relevan dengan kueri input. Informasi ini, bersama dengan kueri input, sering menjadi bagian dari sistem yang disebut retrieval augmented generation (RAG). + Dalam proses ini, beberapa dokumen atau informasi kontekstual yang relevan ditambah ke prompt pengguna yang sebenarnya sehingga model mendapatkan konten yang dapat dipercaya untuk menghasilkan respons yang relevan dan akurat. + Menginstruksikan Amazon Nova 2 untuk menjawab menggunakan teks referensi dari sumber tepercaya dapat membimbingnya untuk menyusun responsnya berdasarkan materi yang disediakan dan memastikan bahwa responsnya didasarkan pada informasi yang akurat dan relevan, meningkatkan keandalan dan kredibilitas konten yang dihasilkan. + Menggunakan teks referensi dapat membantu menghindari halusinasi, sehingga meningkatkan kualitas dan kepercayaan tanggapan secara keseluruhan. Untuk meminimalkan halusinasi, sebaiknya sebutkan `DO NOT USE INFORMATION THAT IS NOT IN REFERENCE TEXTS!` secara eksplisit dalam instruksi model Anda. Templat cepat ``` System: In this session, the model has access to search results and a user's question, your job is to answer the user's question using only information from the search results. Model Instructions: - DO NOT USE INFORMATION THAT IS NOT IN SEARCH RESULTS! User: {Query} Resource: Search Results: {Reference texts} ``` ### Contoh: Memberikan konteks grounding membantu mencegah model berhalusinasi Contoh ini menunjukkan bagaimana konteks grounding dapat mencegah model berhalusinasi. Sistem: ``` In this session, the model has access to search results and a user's question, your job is to answer the user's question using only information from the search results. Model Instructions:- DO NOT USE INFORMATION THAT IS NOT IN SEARCH RESULTS! ``` Pengguna: ``` What were the economic impacts of the COVID-19 pandemic on the United States in 2020? Resource: Search Results: In 2020, the United States experienced significant economic impacts due to the COVID-19 pandemic. The U.S. economy contracted by 3.5% in 2020, according to the Bureau of Economic Analysis. Unemployment rates surged to 14.7% in April 2020, the highest since the Great Depression, before gradually declining. Small businesses faced severe challenges, with millions of firms closing permanently. Additionally, consumer spending dropped sharply as people reduced non-essential expenditures and saved more. Government intervention played a critical role in mitigating these impacts through stimulus packages and support programs, such as the Paycheck Protection Program (PPP) for small businesses and direct payments to individuals. Despite these measures, the economic recovery remained uneven across different sectors and regions. ``` ### Ground menggunakan spidol kutipan Untuk tugas dokumen yang panjang, kami sarankan Anda menginstruksikan model Amazon Nova 2 untuk membumikan tanggapannya menggunakan kutipan dari bagian dokumen yang relevan sebelum melanjutkan tugas. Pendekatan ini membantu model fokus pada informasi yang paling relevan dan menghindari terganggu oleh konten asing. Saat Anda meminta model mendasarkan responsnya, bagian yang dapat dikutip harus diberi nomor. Misalnya,`Passage %[1]%`, `Passage %[2]%` dan sebagainya. #### Contoh: menggunakan penanda kutipan **Example Penanda kutipan cepat** ``` You are an AI financial assistant. Your task is to find patterns and insights from multi-year financial documents Passage %[1]% {{Your document}} Passage %[2]% {{Your document}} ## Task: Analyze my LLC's reports across multiple years to identify significant performance trends, segment growth patterns and strategic shifts. ## Context information: - You have access to my LLC's annual financial reports (10-K) for multiple fiscal years in PDF format - These reports contain comprehensive financial data including income statements, balance sheets, cash flow statements and management discussions - The analysis should focus on year-over-year comparisons to identify meaningful trends - I operate two business segments, one in Massachusetts and one in New York Based on the provided Context, extract key financial metrics from each year's reports phrases from the documents. Place citations as inline markers (e.g., %[1]%, %[2]%, etc.) directly within the relevant parts of the response text. Do not include a separate citation section after the response. ## Response Schema: %% (Extracted Financial Metrics) %% (Extracted Financial Metrics) %% (Extracted Financial Metrics) ... ``` Setelah Anda mengekstrak informasi kunci berdasarkan tugas pengguna, Anda dapat menggunakan metrik keuangan yang diekstraksi untuk menjawab pertanyaan yang relevan seperti yang ditunjukkan: **Example Analisis tindak lanjut dengan metrik yang diekstraksi** ``` ## Task Analyze my LLC's financial reports across multiple years to identify significant performance trends, segment growth patterns and strategic shifts. {{extracted financial metrics}} ## Model Instructions: - Organize data chronologically to identify meaningful trends - DO compare segment performance across the five-year period - DO identify significant strategic shifts or investments mentioned in management discussions - DO NOT make speculative predictions beyond what is supported by the data - ALWAYS note any changes in accounting practices or reporting methodologies that might affect year-over-year comparisons ## Response style and format requirements: - Respond in markdown - Structure the analysis with clear headings and subheadings - Present key financial metrics in tabular format showing all five years side-by-side - Include percentage changes year-over-year for all major metrics - Create a section dedicated to visualizing the most significant trends (with descriptions of what would be shown in charts) - Limit the executive summary to 250 words maximum - Format segment analysis as separate sections with consistent metrics across all segments - MUST include a Key Insights bullet-pointed list at the end of each major section ``` ### Gunakan Nova Web Grounding Alih-alih meminta secara langsung kutipan untuk membumikan model dalam teks pendukung, model Amazon Nova 2 menyediakan alat pentanahan web internal yang dapat digunakan. Saat diaktifkan, model Amazon Nova 2 akan langsung menanyakan web dan grafik pengetahuan Amazon dan membumikan respons akhir dengan kutipan. Untuk mempelajari lebih lanjut tentang cara memanfaatkan Amazon Nova Web Grounding, Anda dapat merujuk panduan [pengguna Amazon Nova Web Grounding](https://docs.aws.amazon.com/nova/latest/nova2-userguide/web-grounding.html). ## Menghasilkan output terstruktur Untuk memastikan format output yang konsisten dan terstruktur, Anda dapat menggunakan output terstruktur, termasuk format seperti XHTML, JSON, Markdown, atau menggunakan fungsionalitas penggunaan alat. + Pendekatan ini memungkinkan sistem hilir untuk lebih efektif memahami dan mengurai output yang dihasilkan oleh model. + Dengan memberikan instruksi eksplisit untuk model, tanggapan dihasilkan dengan cara yang mematuhi skema yang telah ditentukan. Misalnya, jika parser hilir mengharapkan konvensi penamaan khusus untuk kunci dalam objek JSON, Anda harus menentukan skema respons di akhir prompt. Selain itu, jika Anda lebih suka respons dalam format JSON tanpa teks pembukaan, instruksikan model yang sesuai. Artinya, secara eksplisit menyatakan **Harap hasilkan hanya output JSON. JANGAN berikan pembukaan apa pun.** untuk memastikan output bersih. **Tip** Kami mengamati kepatuhan terbaik terhadap persyaratan format data ketika mereka didefinisikan dalam skema itu sendiri alih-alih melalui penggunaan contoh (seperti, menentukan tanggal dalam format). YYYY/MM/DD Untuk output JSON sederhana dengan hingga 10 kunci, Anda dapat menemukan skema di bawah ini. Untuk skema yang lebih kompleks, kami sarankan Anda menentukan skema Anda melalui alat. Penggunaan alat memanfaatkan teknik yang disebut decoding terbatas yang akan meningkatkan kepatuhan model untuk scehma kompleks ini. ### Skema pemformatan umum Berikut ini adalah contoh skema pemformatan umum. ------ #### [ JSON ] ``` JSON_format = """Write your response following the JSON format below: ```json { "key1": "value1", "key2": "value2", key3: [{ "key3_1": "value_3_1 written in YYYY/MM/DD format", "key3_2": "value_3_2 day of the week written in full form", ...}``` """ ``` ------ #### [ XML ] ``` XML_format = """Write your response following the XML format below: "task1" ( task 1 result ) ( task 2 result ) ( task 3 result ) "task2" ( task 1 result ) ( task 2 result ) ( task 3 result ) """ ``` ------ #### [ Markdown ] ``` markdown_schema = """Write your response following the markdown format below: ## Introduction ( 2-3 line intro) ## Design Guidance (Bulleted list of design guidance) ## Step by Step Instructions on Execution ( Bulleted list of instructions with each with bold title. ## Conclusion ( conclusion ) """ ``` ------ ### Isi konten asisten pra-isi Jika Anda menghasilkan output terstruktur dalam mode non-penalaran, Anda dapat mendorong respons model dengan mengisi konten asisten terlebih dahulu. Prefilling meningkatkan konsistensi dalam format output saat dalam mode non-penalaran. Ini memungkinkan Anda untuk mengarahkan tindakan model, mem-bypass pembukaan dan menerapkan format output tertentu seperti JSON dan XHTML. Misalnya, jika Anda mengisi konten asisten dengan `{` atau````json`, masukan itu memandu model untuk menghasilkan objek JSON tanpa informasi tambahan. **Tip** Jika Anda secara eksplisit mencari mengekstraksi JSON, pola yang umum adalah mengisi sebelumnya ````json` dan menambahkan urutan berhenti. ````` Ini memastikan model mengeluarkan objek JSON yang dapat diurai secara terprogram. **Example Isi konten asisten pra-isi** Kode berikut menunjukkan cara mengisi ulang dengan API: ``` import boto3 import json # Create a Bedrock Runtime client. client = boto3.client( "bedrock-runtime", region_name="us-east-1" ) request_body = { "system": [ {"text": "You write JSON objects based on the given instructions"} ], "messages": [ { "role": "user", "content": [{"text": "Provide details about the best selling full-frame cameras in past three years. Answer in JSON format with keys like name, brand, price and a summary."}] }, { "role": "assistant", "content": [{"text": " Here is the JSON response: ```json"}] } ], "inferenceConfig": { "maxTokens": 1000, } } # Invoke the model and extract the response body. response = client.invoke_model( modelId="amazon.nova-2-lite-v1:0", body=json.dumps(request_body) ) model_response = json.loads(response["body"].read()) ``` ### Tentukan alat yang akan digunakan untuk skema kompleks Pendekatan lain adalah dengan menggunakan alat untuk memaksa skema tertentu untuk respons model dengan memasukkan skema *JSON pydantic di bagian skema* penggunaan alat. Anda dapat menentukan pilihan alat ke skema yang disediakan dan respons Amazon Nova akan disusun berdasarkan alat yang dipilih. Untuk mempelajari lebih lanjut tentang cara memanfaatkan penggunaan alat, lihat [Penggunaan Alat](https://docs.aws.amazon.com/nova/latest/userguide/tool-use.html). ### Contoh #### Contoh 1: Tambahkan skema keluaran Menambahkan bagian Output Schema dengan skema yang sesuai membuat model lebih memilih untuk menyesuaikan skema itu. Namun, output model tidak deterministik dan dapat bervariasi dari skema output. ------ #### [ Unspecific Prompt ] Pengguna: ``` Provide details about the best selling full-frame cameras in past three years. Answer in JSON format with keys like name, brand, price and a summary. ``` Asisten: ``` ```json [ { "name": "Sony Alpha A7R IV", "brand": "Sony", "price": "Approximately $3,500", "summary": "The Sony Alpha A7R IV is renowned for its exceptional image quality, thanks to a 61-megapixel full-frame sensor. It also features 4K video recording and a robust build, making it a favorite among professional photographers and videographers." }, { "name": "Canon EOS R5", "brand": "Canon", "price": "Approximately $3,900", "summary": "The Canon EOS R5 combines high-resolution imaging with advanced video capabilities. It houses a 45-megapixel sensor, 8K video recording, and impressive autofocus performance, appealing to both photography and filmmaking professionals." }, { "name": "Nikon Z7 II", "brand": "Nikon", "price": "Approximately $2,800", "summary": "The Nikon Z7 II offers a 45.7-megapixel full-frame sensor and is praised for its high resolution and excellent dynamic range. It also supports 4K video recording and features a versatile Z-mount lens system, making it a strong contender in the full-frame market." }, { "name": "Fujifilm GFX 100S", "brand": "Fujifilm", "price": "Approximately $7,000", "summary": "While not a traditional full-frame camera, the Fujifilm GFX 100S stands out with its 102-megapixel medium format sensor. It is lauded for its stunning detail and color reproduction, though it comes at a higher price point and is aimed at specialized users." } ] ``` ``` ------ #### [ Specific Prompt ] Pengguna: ``` Provide details about the best selling full-frame cameras in past three years. You MUST answer in JSON format only. Write your response following the the format below: [{ “name”: “name goes here”, “brand”: “brand goes here”, “price”: “price goes here“, "summary": "summary goes here" }] ``` Asisten: ``` [ { "name": "Nikon D850", "brand": "Nikon", "price": "$3,296.95", "summary": "The Nikon D850 is a professional full-frame DSLR camera known for its exceptional image quality, 45.7-megapixel resolution, 7 fps continuous shooting, and 4K video capabilities." }, { "name": "Canon EOS 5D Mark IV", "brand": "Canon", "price": "$3,499.00", "summary": "The Canon EOS 5D Mark IV is a popular full-frame DSLR appreciated for its 30.4-megapixel sensor, 4K video recording, robust build quality, and reliable autofocus system." }, { "name": "Sony A7R III", "brand": "Sony", "price": "$3,198.00", "summary": "The Sony A7R III is a high-resolution full-frame mirrorless camera renowned for its 42.4-megapixel sensor, excellent low-light performance, and versatile lens compatibility." }, { "name": "Fujifilm GFX 100S", "brand": "Fujifilm", "price": "$5,999.99", "summary": "The Fujifilm GFX 100S is a medium format mirrorless camera that stands out for its 102-megapixel sensor, high dynamic range, and exceptional color reproduction." }, { "name": "Sony A7 III", "brand": "Sony", "price": "$1,998.00", "summary": "The Sony A7 III is a full-frame mirrorless camera popular among enthusiasts and professionals for its 24.2-megapixel sensor, fast autofocus, and 4K video capabilities." } ] ``` ------ #### Contoh 2: Isi ulang respons model Pendekatan lain adalah dengan mengisi respons model dengan memasukkan teks awal yang diinginkan dalam pesan asisten. Dalam hal ini, respons model Amazon Nova akan berlanjut dari tempat pesan asisten ditinggalkan. **Tip:** Prefill hanya valid ketika penalaran tidak diaktifkan. Pengguna: ``` Provide details about the best selling full-frame cameras in past three years. Your response should be in JSON format, with the following keys: name, brand, year, price, summary. ``` Asisten (Prefilling): ``` ```json ``` Asisten: ``` { "cameras": [ { "name": "Sony Alpha A7 III", "brand": "Sony", "year": 2018, "price": "$1999", "summary": "The Sony Alpha A7 III is a highly acclaimed full-frame mirrorless camera known for its excellent image quality, advanced autofocus system, and 4K video capabilities." }, { "name": "Canon EOS R5", "brand": "Canon", "year": 2020, "price": "$3899", "summary": "The Canon EOS R5 is a top-tier full-frame mirrorless camera that offers stunning 45MP images, 8K video recording, and exceptional performance in various lighting conditions." }, { "name": "Nikon Z7 II", "brand": "Nikon", "year": 2020, "price": "$2999", "summary": "The Nikon Z7 II is a flagship full-frame mirrorless camera with a 45.7MP sensor, superb image quality, and advanced video recording features." }, { "name": "Fujifilm GFX 100S", "brand": "Fujifilm", "year": 2020, "price": "$7999", "summary": "The Fujifilm GFX 100S is a medium format mirrorless camera known for its impressive 102MP sensor, beautiful film simulations, and versatile lens options." }, { "name": "Sony Alpha A7R IV", "brand": "Sony", "year": 2019, "price": "$3499", "summary": "The Sony Alpha A7R IV features a 61MP sensor, excellent low-light performance, and advanced video capabilities, making it a favorite among professional photographers." } ] } ``` ``` #### Contoh 3: Tentukan alat yang akan digunakan Sebagai alternatif untuk menggunakan teknik prefill untuk output terstruktur, Anda dapat menggabungkan fungsionalitas alat Nova dengan ToolChoice. Dalam contoh ini, model akan menghasilkan panggilan alat yang mematuhi skema JSON yang disediakan dan memanggil alat khusus yang ditentukan ke format JSON lengkap yang ditentukan. Untuk panduan tambahan, lihat Sistem Lanjutan. Pengguna: ``` From the below provided Query, extract the relevent entities Query: John works in BUILDING-0987 and have been incharge of product id 23564#. His performance have been excellent in past year and is up for a raise. Use the extract_ner tool. ``` ToolConfig: ``` { "tools": [ { "toolSpec": { "name": "extract_ner", "description": "Extract all the named entities. based on provided input", "inputSchema": { "json": { "type": "object", "properties": { "entities": { "type": "array", "items": { "type": "object", "properties": { "name": { "type": "string", "description": "The extracted entity name. This should be a name of a person, place, animal or thing" }, "location": { "type": "string", "description": "The extracted location name. This is a site name or a building name like SITE-001 or BUILDING-003" }, "product": { "type": "string", "description": "The extrcted product code, this is generally a 6 digit alphanumeric code such as 45623#, 234567" } }, "required": [ "name", "location", "product" ] } } }, "required": [ "entities" ] } } } }], "toolChoice": { "tool": { "name": "extract_ner" } } } ``` ## Kasus penggunaan multibahasa Model Amazon Nova 2 telah dilatih pada lebih dari 200 bahasa dan dioptimalkan untuk 15 bahasa. **Topics** + [ ### Minta terjemahan yang akurat ](#accurate-translations) + [ ### Menegakkan konvensi penulisan yang konsisten ](#consistent-writing-conventions) ### Minta terjemahan yang akurat Untuk memanfaatkan kemampuan ini untuk terjemahan bentuk singkat (beberapa kalimat) Anda dapat menginstruksikan model untuk menerjemahkan teks ke dalam bahasa target yang ditentukan. **Example Permintaan terjemahan** ``` Translate the following text into {target language}. Please output only the translated text with no prefix or introduction: {text} ``` ``` Translate the following sentence from {source_language} to {target language}: {text} ``` ``` {text} How do you say this sentence in {target_language} ``` ### Menegakkan konvensi penulisan yang konsisten Dalam bahasa berbasis karakter, model Amazon Nova 2 dapat menggunakan set karakter dari bahasa sumber. Anda dapat menggunakan prompt berikut untuk menerapkan output yang konsisten. **Example Menegakkan konvensi penulisan** ``` When translating, ensure to use the correct orthography / script / writing convention of the target language, not the source language's characters ``` ## Panggilan alat ### Sistem agen **Topics** + [ #### Atur parameter inferensi yang tepat ](#set-inference-parameters) + [ #### Pertimbangkan persyaratan latensi ](#consider-latency-requirements) + [ #### Gunakan kata-kata yang disengaja untuk instruksi panggilan alat ](#intentional-wording-tool-calling) + [ #### Manfaatkan perintah “berpikir” ](#leverage-thinking-commands) + [ #### Pemesanan panggilan alat ](#tool-call-ordering) + [ #### Buat skema alat berkualitas ](#designing-tool-schema) + [ #### Buat sub-agen ](#create-sub-agents) + [ #### Gunakan alat untuk input multimodal ](#use-tools-multimodal-inputs) + [ #### Langkah selanjutnya ](#next-steps-best-practices) #### Atur parameter inferensi yang tepat Pemanggilan alat memerlukan output terstruktur yang sangat spesifik dari model dan ditingkatkan dengan menggunakan parameter inferensi berikut: + **Mode Non Penalaran: Suhu:** 0,7 & P Teratas: 0,9 + **Mode Penalaran: Suhu:** 1 & P Teratas: 0,9 #### Pertimbangkan persyaratan latensi **Tip** Model Amazon Nova 2 mampu memanggil alat dengan alasan hidup dan mati. Namun, mode penalaran memiliki dampak signifikan pada latensi. Untuk aplikasi sensitif latensi, Anda harus mengoptimalkan mode penalaran mati dan menyederhanakan panggilan alat yang diperlukan jika memungkinkan. Pisahkan alur kerja multistep menjadi langkah-langkah diskrit untuk mengurangi ketergantungan model pada memuntahkan parameter yang tidak perlu. #### Gunakan kata-kata yang disengaja untuk instruksi panggilan alat **Nama alat:** Alat referensi dalam prompt sistem adalah umum dalam sistem pemanggilan alat untuk menginstruksikan model kapan harus memanggil alat. Saat Anda mereferensikan alat dalam prompt, kami sarankan Anda menggunakan nama alat alih-alih referensi atau contoh xml/pythonic. ##### Contoh referensi alat yang baik ``` Use the 'run_shell_command' tool for running shell commands ``` ##### Contoh referensi alat yang buruk ``` Call run_shell_command() to run shell commands ``` #### Manfaatkan perintah “berpikir” Untuk semua kasus penggunaan di mana pemikiran bermanfaat untuk pemanggilan alat, kami sarankan Anda memanfaatkan mode penalaran alih-alih mendorong model untuk “berpikir dalam tag” atau menggunakan alat “berpikir”. Model Amazon Nova 2 dilatih secara ekstensif untuk mode penalaran dan akan menghasilkan hasil yang optimal bila digunakan dalam mode penalaran untuk rantai pemikiran. #### Pemesanan panggilan alat Dalam kasus penggunaan yang mungkin memerlukan penggunaan alat bawaan dan pemanggilan alat asli secara bersamaan, model bias memanggil alat bawaan terlebih dahulu. Jangan menginstruksikan model untuk bertindak berbeda dalam prompt. Sebagai gantinya, rancang alur kerja Anda untuk mempertimbangkan hal ini. Misalnya, jika Anda tidak ingin model menggunakan alat bawaan, jangan sertakan dalam alur kerja Anda sehingga model tidak bias terhadapnya. #### Buat skema alat berkualitas Skema alat adalah salah satu tempat utama Anda dapat meminta sistem panggilan alat yang efektif untuk merekayasa. Namun, penting untuk mempertimbangkan apa yang ditangkap dalam skema alat itu sendiri, bagaimana setiap elemen skema dijelaskan secara semantik dan bagaimana sistem meminta referensi alat dan elemen skema dalam instruksi sistem. Model Amazon Nova 2 dioptimalkan untuk deskripsi ringkas dalam skema alat. Tetap singkat. **Skema alat versus pedoman prompt sistem:** **Sertakan dalam skema alat:** + Fungsionalitas inti: Apa yang dilakukan alat (20-50 kata direkomendasikan) + Spesifikasi parameter: Deskripsi yang jelas dari setiap parameter (sekitar 10 kata per parameter) + Format yang diharapkan: Tipe data (seperti enum, int, float), bidang wajib dan rentang nilai yang valid **Sertakan dalam prompt sistem:** + Dedikasikan `#Tool Usage` bagian dengan logika orkestrasi (kapan dan mengapa menggunakan alat khusus) dan aturan bisnis (logika bersyarat, persyaratan pengurutan, dan dependensi). + **Strategi penanganan kesalahan:** Tambahkan `#Error Handling and Troubleshooting` bagian dengan instruksi tentang cara merespons kegagalan atau keluaran yang tidak terduga + **Pemformatan keluaran:** Tambahkan detail tentang cara menyajikan kepada pengguna ##### Contoh ``` You are a software engineering issue root cause analysis agent. You are tasked with reviewing a customer issue and examining the repository to identify a plan to resolve the issue. # Core Mandates - **DO NOT** update the original issue that was posted by the user. You only add *additional* comments to the reported issue if necessary # Primary Workflows 1. **Understand:** Analyze the user's request and explore the codebase thoroughly using **get_file_contents** to grasp file structures and conventions. 2. **Plan:** Create a coherent, evidence-based plan for resolving the task and share it with the user following the format below # Tool Usage - **Read the Issue:** Always start by using the **read_issue** tool to get the details about the requested issue - **File Paths:** Always end the file path with "/" if you are searching a directory using the **get_file_contents** tools - **Parallelism:** Execute multiple independent tool calls in parallel when feasible # Error Handling and Troubleshooting - **File Exploration:** If you get an error that a file doesn't exist, try searching at the directory level first to validate the file path # Output Formatting Return your plan in markdown in the following format ## Issue ## Resolution Plan ``` #### Buat sub-agen Pertimbangkan untuk membuat sub-agen khusus alih-alih satu agen dengan banyak alat saat Anda menemukan: + **Jumlah alat melebihi 20:** Set alat besar menjadi sulit untuk dikelola dan meningkatkan kesalahan pemilihan + **Domain fungsional yang berbeda:** Alat secara alami mengelompokkan ke dalam kategori terpisah (seperti pengambilan data versus pemrosesan versus pelaporan) + **Skema kompleks:** Ketika kedalaman parameter melebihi 3-4 level atau alat memiliki saling ketergantungan yang rumit + **Panjang percakapan:** Alur kerja secara teratur melebihi 15-20 putaran dapat mengambil manfaat dari sub-agen khusus + **Degradasi kinerja:** Jika Anda mengamati penurunan akurasi dalam pemilihan alat atau peningkatan latensi **Tip** Server MCP dilengkapi dengan alat dan skema yang tidak dapat Anda kendalikan. Hanya sertakan alat yang diperlukan untuk alur kerja Anda untuk menyelesaikan tugas yang diperlukan. #### Gunakan alat untuk input multimodal Untuk tugas multimodal, kami belum mengamati peningkatan akurasi yang memanfaatkan alat untuk tugas terstruktur (seperti ekstraksi atau pembuatan stempel waktu). Sebagai gantinya, kami sarankan Anda meninjau bagian yang relevan di bagian Meminta input multimodal untuk cara meminta model dengan sukses menggunakan templat yang disediakan. #### Langkah selanjutnya + Untuk permintaan multimodal, lihat. [Meminta input multimodal](prompting-multimodal.md)