AWS nova documentation change
Summary
Complete restructuring of the document - removed detailed prompting techniques and examples, replaced with a simplified 'Understanding the roles' section and topic links. Removed content about GDPR compliance examples, system role guardrails, and advanced tool calling implementations.
Security assessment
The changes are organizational/structural rather than addressing security vulnerabilities. While the previous version contained GDPR compliance examples and system role guardrail implementations, their removal appears to be part of content restructuring rather than security remediation. No CVEs, vulnerabilities, or security incidents are mentioned in the diff.
Diff
diff --git a/nova/latest/nova2-userguide/prompting-best-practices.md b/nova/latest/nova2-userguide/prompting-best-practices.md index 9ad69f2ab..da9bc5bf0 100644 --- a//nova/latest/nova2-userguide/prompting-best-practices.md +++ b//nova/latest/nova2-userguide/prompting-best-practices.md @@ -5 +5 @@ -Create precise promptsBring focus to sections of the promptUse a system roleProvide examples (few-shot prompting)Advanced prompting techniques +Understanding the roles @@ -11 +11 @@ The following best practices mainly apply to the Amazon Nova text models, but yo -For more information on how to prompt multimodal inputs, content generation, or speech inputs, refer to [Prompting multimodal inputs](./prompting-multimodal.html) +For more information on how to prompt multimodal inputs, refer to [Prompting multimodal inputs](./prompting-multimodal.html). For information on how to prompt speech inputs, refer to [Voice conversation prompts](./sonic-system-prompts.html). @@ -13,459 +13 @@ For more information on how to prompt multimodal inputs, content generation, or -###### Topics - - * Create precise prompts - - * Bring focus to sections of the prompt - - * Use a system role - - * Provide examples (few-shot prompting) - - * Advanced prompting techniques - - - - -## Create precise prompts - -Clear, specific instructions eliminate ambiguity and produce better outputs. - -**Best practices:** - - * **Provide contextual information in the query** – The context provided helps situate the model better by aligning clear target-user scenarios, thereby enhancing the relevance and coherence of the output. - - * **Provide explicit instructions without assumptions** – Specify instructions about the task, what the expected output is and any additional context that can help the model respond the way you want. - - * **Specify the output format** – XML, JSON, Markdown - - * **Use action verbs** – Analyze, Extract, Generate, Classify, Compare, Summarize, Translate, Identify, List, Recommend - - * **Define format requirements in the schema itself** – Such as "dates in YYYY/MM/DD format" - - * **For simple JSON (10 or less keys)** – Define schema in prompt or use tools - - * **For complex schemas** – We recommend using tools with constrained decoding - - * **Use capitalization for critical requirements** – DO, DO NOT, MUST - - * **Separate distinct parts of the input with delimiters** – This ensures clarity and enhances Amazon Nova models' ability to understand the query's structure. - - * **Use numbered lists or bullet points** – This can help to break down the task into manageable steps and provide a clear outline of the actions that must be taken. - - - - -### Prompt template - -Use this template to structure your prompts: - - - ## Task Summary: - {Task summary} - - ## Context Information: - - {Context and content information 1} - - {Context and content information 2} - - ## Model Instructions: - - {Other Model Instructions} - - ## Response style and format requirements: - - {Style and format requirement 1} - - {Style and format requirement 2} - -### Examples - -Adding more contextual information helps the model ground towards the desired behavior. - -Role | Unclear Prompt | Clear Prompt ----|---|--- -User | Write me a meeting invite to the project team | 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 | Certainly! Here's a sample meeting invite for your project team: \--- **Subject:** Project Team Meeting - [Project Name] **Date:** [Insert Date] **Time:** [Insert Time] ... | **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. - 3. **Upcoming Milestones and Deadlines (10:30 AM - 10:50 AM)** \- Overview of the next phase of the project. - 4. **Action Items and Responsibilities (10:50 AM - 11:00 AM)** \- Assignment of tasks for the upcoming period. - - - -Notice how in the Sectioned Prompt column, the prompt is clearer and has delineated sections for different entities like Tasks, Context, Requirements and the rest when compared to the instructions in the Unsectioned Prompt column. - -Role | Unsectioned Prompt | Sectioned 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. | **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: 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... | # 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... ## What is Climate Change? **Climate change** refers to long-term changes in global temperatures and weather patterns... - -Adding extra details on the response formatting can help the model accomplish the desired result. Some of the other commonly used response formats include CSV, Markdown, YAML and XML. - -Role | Prompt without any Style constraints | Prompt with Style constraints ----|---|--- -User | Outline the different types of rooms available in a typical 4-star hotel, including their features. | Outline the different types of rooms available in a typical 4-star hotel, including their features. All responses must be in YAML format. -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. - -| - - - 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 - - free_breakfast: Included - -In this case, the prompt with style constraints provides comprehensive information on the constraints to follow and the desired response format. As observed in the response, the optimized prompt aligns more closely with the requested brevity and bulleted list structure. - -Role | Prompt without any Style constraints | Prompt with Style constraints ----|---|--- -User | Explain the process of checking in a guest at a luxury resort. | 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 | 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... - -| - - 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. - - - -Here, the prompt with the specified response format forces the model to return only a category number between 1-10 instead of being highly verbose. - -Role | Prompt without any response format | 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. Text: Johangsan is a mountain of South Korea. It has an elevation of 954 metres. | 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 | 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 | 8 - -## Bring focus to sections of the prompt - -Amazon Nova models can pay close attention to specific parts in the prompt by formatting instructions in sections and then referring to those specific sections. - -The model can pay attention if prompts have clear sectional delimitation using markdown, XML, or other structure. For example, you can define the name of the section, use `##Section Name##`, then refer to that section in your prompt with `##Section Name##`. - -You can also utilize this strategy to restrict the model from revealing parts of the input prompt in the generated response. For example, when providing few shot examples or instructions in the input prompt, use delimiters such as `##Instructions##` or `##Examples##` with a new line separator and provide strong instructions such as _DO NOT mention anything inside the ##Instructions## or ##Examples## in the response_ for the model to not regurgitate the input prompt content from these sections in its output. - -Role | Prompt with Sectional Delimitation ----|--- -User | 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##