"}]' \
--routing-criteria '{"responseQualityDifference": 0.5}'
```
1. 使用 AWS CLI將您的提示傳送至智慧提示路由器。路由器會預測每個模型的回應品質，並將請求路由至具有最佳回應品質的模型。
1. 檢閱對請求的回應。它將包含有關已使用模型和路由條件的資訊。
1. 當您使用提示路由器時，您也可以使用這些額外的 API 操作：
+ [https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetPromptRouter.html](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetPromptRouter.html)
+ [https://docs.aws.amazon.com/bedrock/latest/APIReference/API_ListPromptRouters.html](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_ListPromptRouters.html)
+ [https://docs.aws.amazon.com/bedrock/latest/APIReference/API_DeletePromptRouter.html](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_DeletePromptRouter.html)
------
# 設計提示
設計適當的提示詞是使用 Amazon Bedrock 模型組建成功應用程式的重要一步。您將在本節中了解如何設計一致、清楚簡潔的提示。您也會了解如何使用推論參數來控制模型的回應。下圖顯示使用案例*餐廳評論摘要*的一般提示詞設計，以及客戶在設計提示詞時需要考慮的一些重要設計選擇。如果提供的指示詞或提示詞的格式不一致、明確且簡潔，則 LLM 會產生不受歡迎的回應。
![\[具有描述性註解的良好提示詞建構模組範例。\]](http://docs.aws.amazon.com/zh_tw/bedrock/latest/userguide/images/example-good-prompt-construction.png)
（來源：撰寫提示 AWS)
下列內容提供如何建立成功提示的指導。
**Topics**
+ [提供簡單、明確及完整的說明](#prompt-instructions)
+ [將問題或指令應放在提示的末尾以獲得最佳結果](#prompt-placement)
+ [使用分隔符號字元進行 API 呼叫](#prompt-separators)
+ [使用輸出指示器](#prompt-output-indicators)
+ [良好概括的建議做法](#prompt-generalization)
+ [在 Amazon Bedrock 上最佳化文字模型的提示 — 當基礎知識不夠好時](#optimize-prompts-for-text-models)
+ [使用推論參數控制模型回應](#use-inference-parameters)
## 提供簡單、明確及完整的說明
Amazon Bedrock 上的 LLM 透過簡單直接的說明所發揮的效果最好。透過清楚描述對任務的期望，並儘可能減少模糊性，可以確保模型能清楚地解譯提示詞涵意。
例如，思考一個分類問題，其中使用者想要從一組可能的選項中獲得答案。以下顯示的「良好」範例說明了使用者在此案例中所需的輸出。在「不良」範例中，這些選擇沒有明確命名為可供模型選擇的類別。。模型會在沒有選擇的情況下稍微不同地解譯輸入，並產生與良好範例相反之風格更自由的文字摘要。
| | |
| --- |--- |
| Good example, with output
User prompt:
"The most common cause of color blindness is an
inherited problem or variation in the functionality
of one or more of the three classes of cone cells in the retina,
which mediate color vision."
What is the above text about?
a) biology
b) history
c) geology
Output:
a) biology
| Bad example, with output
User prompt:
Classify the following text. "The most common cause of color
blindness is an inherited problem or variation in the functionality
of one or more of the three classes of cone cells in the retina,
which mediate color vision."
Output:
The topic of the text is the causes of colorblindness.
|
(提示來源：[維基百科關於色盲的介紹](https://en.wikipedia.org/wiki/Color_blindness)，使用的模型：Titan Text G1 - Express)
## 將問題或指令應放在提示的末尾以獲得最佳結果
最後包括任務描述、指示或提問，可協助模型判斷必須尋找哪些資訊。在分類的情況下，答案的選擇也應該在最後出現。
在下列開放式問答範例中，使用者有關於文字的特定問題。問題應該在提示詞結束時出現，以便讓模型專注於任務。
```
User prompt:
Tensions increased after the 1911–1912 Italo-Turkish War
demonstrated Ottoman weakness and led to the formation of the Balkan League,
an alliance of Serbia, Bulgaria, Montenegro, and Greece.
The League quickly overran most of the Ottomans' territory in the Balkans
during the 1912–1913 First Balkan War, much to the surprise of outside observers.
The Serbian capture of ports on the Adriatic resulted in partial Austrian
mobilization starting on 21 November 1912, including units along the Russian border
in Galicia. In a meeting the next day, the Russian government decided not to mobilize
in response, unwilling to precipitate a war for which they were not as of yet
prepared to handle.
Which country captured ports?
```
```
Output:
Serbia
```
(提示來源：[維基百科關於第一次世界大戰的介紹](https://en.wikipedia.org/wiki/World_War_I)，使用的模型：Amazon Titan Text)
## 使用分隔符號字元進行 API 呼叫
**使用分隔符號字元進行 API 呼叫**
分隔符號字元如 `\n`，可能會影響 LLM 的效能。對於 Anthropic Claude 模型，在格式化 API 呼叫時必須包含換行符號以獲得所需的回應。格式應始終遵循：`\n\nHuman: {{Query Content}}\n\nAssistant:`。對於 Titan 模型，在提示詞結束時新增 `\n` 以協助改善模型的效能。對於分類任務或具有答案選項的問題，您也可以將 Titan 模型的答案選項以 `\n` 分隔。如需有關使用分隔符號的詳細資訊，請參閱對應模型供應商的文件。下列範例是分類任務的範本。
```
Prompt template:
"""{{Text}}
{{Question}}
{{Choice 1}}
{{Choice 2}}
{{Choice 3}}"""
```
下列範例顯示，選擇之間和提示詞結束時所出現換行符號，如何協助 Titan 產生所需的回應。
```
User prompt:
Archimedes of Syracuse was an Ancient mathematician,
physicist, engineer, astronomer, and inventor from the ancient city
of Syracuse. Although few details of his life are known,
he is regarded as one of the leading scientists in classical antiquity.
What was Archimedes? Choose one of the options below.
a) astronomer
b) farmer
c) sailor
```
```
Output:
a) astronomer
```
(提示來源：[維基百科關於阿基米德的介紹](https://en.wikipedia.org/wiki/Archimedes)，使用的模型：Amazon Titan Text)
## 使用輸出指示器
**輸出指示器**
在模型應產生之輸出上加入想要的限制的詳細資訊。下列的良好範例會產生輸出，該輸出是一個簡短的片語，一個出色的摘要。在這種情況下，不好的範例並沒有那麼糟糕，但摘要幾乎與原始文字一樣長。輸出規格對於從模型取得所需內容極為重要。
| | |
| --- |--- |
| 具有明確輸出限制指示器的範例提示 User prompt:
"Charles Mingus Jr. was an American jazz upright
bassist, pianist, composer, bandleader, and author.
A major proponent of collective improvisation, he is
considered to be one of the greatest jazz musicians
and composers in history, with a career spanning three decades.
Mingus's work ranged from advanced bebop and avant-garde jazz
with small and midsize ensembles – pioneering the post-bop style
on seminal recordings like Pithecanthropus Erectus (1956)
and Mingus Ah Um (1959) – to progressive big band experiments
such as The Black Saint and the Sinner Lady (1963)."
Please summarize the above text in one phrase.
Output:
Charles Mingus Jr. is considered one of the
greatest jazz musicians of all time.
| 沒有明確輸出規格的範例 User prompt:
"Charles Mingus Jr. was an American jazz upright
bassist, pianist, composer, bandleader, and author.
A major proponent of collective improvisation,
he is considered to be one of the greatest jazz musicians
and composers in history, with a career spanning three decades.
Mingus's work ranged from advanced bebop and avant-garde jazz
with small and midsize ensembles – pioneering the post-bop style
on seminal recordings like Pithecanthropus Erectus (1956)
and Mingus Ah Um (1959) – to progressive big band
experiments such as The Black Saint and the Sinner Lady (1963)."
Please summarize the above text.
Output:
Charles Mingus Jr. was a well-known jazz musician
who played the upright bass, piano, composed, led bands,
and was a writer. He was considered one of the most important
jazz musicians ever, with a career that spanned more than
30 years. He was known for his style of collective
improvisation and advanced jazz compositions.
|
(提示來源：[維基百科上關於查爾斯·明格斯的介紹](https://en.wikipedia.org/wiki/Charles_Mingus)，使用的模型：Amazon Titan Text)
在這裡，我們使用輸出指標提供 Anthropic Claude 和 AI21 Labs Jurassic 模型的一些其他範例。
以下範例展示了使用者可以透過在提示詞中指定預期的輸出格式來指定輸出格式。當被請求使用特定格式 (例如使用 XML 標籤) 產生答案時，模型可以對應地產生答案。如果沒有特定的輸出格式指示器，該模型將輸出自由形式文字
| | |
| --- |--- |
| 含明確指示器的範例，具有輸出 User prompt:
Human: Extract names and years: the term
machine learning was coined in 1959 by Arthur Samuel,
an IBM employee and pioneer in the field of computer
gaming and artificial intelligence. The synonym self-teaching
computers was also used in this time period.
Please generate answer in and
tags.
Assistant:
Output:
Arthur Samuel 1959
| 不含明確指示器的範例，具有輸出 User prompt:
Human: Extract names and years: the term
machine learning was coined in 1959 by Arthur Samuel,
an IBM employee and pioneer in the field of computer
gaming and artificial intelligence. The synonym
self-teaching computers was also used in this time
period.
Assistant:
Output:
Arthur Samuel - 1959
|
(提示來源：[維基百科關於機器學習的介紹](https://en.wikipedia.org/wiki/Machine_learning)，使用的模型：Anthropic Claude)
以下範例顯示 AI21 Labs Jurassic 模型的提示和答案。使用者可以透過指定左欄顯示的輸出格式來獲得確切的答案。
| | |
| --- |--- |
| 含明確指示器的範例，具有輸出 User prompt:
Context: The NFL was formed in 1920 as the American
Professional Football Association (APFA) before renaming itself
the National Football League for the 1922 season. After initially
determining champions through end-of-season standings, a playoff
system was implemented in 1933 that culminated with the NFL
Championship Game until 1966. Following an agreement to merge
the NFL with the rival American Football League (AFL), the
Super Bowl was first held in 1967 to determine a champion
between the best teams from the two leagues and has remained
as the final game of each NFL season since the merger
was completed in 1970.
Question: Based on the above context, when was the first Super Bowl?
Please only output the year.
Output:
1967
| 不含明確指示器的範例，具有輸出 User prompt:
Context: The NFL was formed in 1920 as the American
Professional Football Association (APFA) before renaming itself
the National Football League for the 1922 season. After initially
determining champions through end-of-season standings, a playoff
system was implemented in 1933 that culminated with the NFL
Championship Game until 1966. Following an agreement to merge
the NFL with the rival American Football League (AFL), the Super
Bowl was first held in 1967 to determine a champion between
the best teams from the two leagues and has remained as the
final game of each NFL season since the merger was completed in 1970.
Question: Based on the above context, when was the first Super Bowl?
Output:
The first Super Bowl was held in 1967.
|
(提示來源：[維基百科關於國家美式足球聯盟的介紹](https://en.wikipedia.org/wiki/National_Football_League)，使用的模型：AI21 Labs Jurassic-2 Ultra v1 )
## 良好概括的建議做法
保留一個小型「保留」測試提示集，以查看是否概括修改您的提示詞。若使用此方法，首先收集範例資料集。然後，您可以將資料拆分為兩個子集：一個「開發」集和一個保留的「測試」集。使用「開發」集為提示詞開發資料，您可以在其上嘗試不同的提示詞修改，並觀察模型回應變更，並尋找最適合的提示詞。將「測試」集視為看不見的保留資料，該資料只能用於驗證最終的最佳提示。
## 在 Amazon Bedrock 上最佳化文字模型的提示 — 當基礎知識不夠好時
**複雜的任務：逐步建構答案**
Titan 可以為某些任務提供明確的步驟，包括片語 `Think step-by-step to come up with the right answer`，可協助產生適當的輸出。
```
User prompt:
At a Halloween party, Jack gets 15 candies.
Jack eats 5 candies. He wants to give each friend
5 candies. How many friends can receive candies?
Think step-by-step to come up with the right answer.
```
```
Output:
15 candies total - 5 candies eaten = 10 candies remaining.
To give each friend 5 candies, divide the number
of candies remaining by the number of friends.
10 candies / 5 friends = 2 friends.
Each friend can receive 2 candies.
The answer is 2 friends.
```
（提示來源： AWS，使用的模型：Amazon Titan Text)
若要讓 Anthropic Claude 模型能夠完成複雜的任務，請使用下列範例中的格式來明確要求模型逐步解決任務。這種方法是基於 [AnthropicClaude 指南](https://docs.anthropic.com/claude/docs/constructing-a-prompt)中的指引。
```
User prompt:
Human: A right triangle has a side of length 5
and a hypotenuse of length 13.
What is the length of the other side?
Assistant: Can I think step-by-step?
Human: Yes, please do.
Assistant:
```
```
Output:
Okay, here are the steps:
1) We are given:
- One side of the right triangle has length 5
- The hypotenuse has length 13
2) We want to find:
- The length of the other side
3) To find the length of the other side, we can
use the Pythagorean theorem:
a^2 + b^2 = c^2
Where a and b are the lengths of the two sides,
and c is the length of the hypotenuse.
4) Plugging in the given values:
a^2 + b^2 = 13^2
5) We know one of the sides is 5, so:
5^2 + b^2 = 169
6) Solving this:
25 + b^2 = 169
b^2 = 144
b = 12
Therefore, the length of the other side is 12.
```
（提示來源： AWS，使用的模型：AnthropicClaude)
**如果不確定答案，請提供模型應該顯示的預設輸出。**
預設輸出有助於防止 LLM 傳回聽起來像是正確的答案，即使模型具有低可信度。
| | |
| --- |--- |
| User prompt:
Provide a proof of the Riemann hypothesis. If you don't
know a proof, respond by saying "I don't know."
Output:
I don't know.
| User prompt:
Provide a proof of the Riemann hypothesis.
Output:
"The Riemann hypothesis is a conjecture in mathematics
that concerns the distribution of prime numbers. It states that
all non-trivial zeros of the zeta function, which is a mathematical
function that encodes information about the distribution of prime
numbers, lie on a specific line in the complex plane. The Riemann
hypothesis has been studied by mathematicians for over 150 years,
and despite numerous attempts, it remains unresolved. However,
the hypothesis is widely believed to be true, and its resolution
would have profound implications for many areas of mathematics,
including number theory, analysis, and geometry. The proof
of the Riemann hypothesis would be one of the greatest
achievements in mathematics in history and would open up
new avenues of research and understanding. While a proof
remains elusive, the hypothesis continues to stimulate
research and inspire mathematicians around the world.“
[Note: this is an accurate description, but obviously
not a proof.]
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
**少量樣本提示**
在提示詞中包含範例(輸入-回應對)可以顯著改善 LLM 的回應。範例可以幫助複雜的任務，因為它們顯示了多種執行指定任務的方式。對於像文字分類這樣的簡單任務，3-5 個範例就夠了。對於更困難的任務，例如沒有上下文的問答，請包括更多範例來產生最有效的輸出。在大多數使用案例中，選取語意上與真實世界資料相似的範例，可以進一步改善效能。
**考慮使用修飾詞調整提示詞**
調整任務指令通常是指修改提示詞的指令、任務或問題元件。這些方法的實用性取決於任務和資料。有用的方法包括下列項目：
+ **網域/輸入規格：**有關輸入資料的詳細資訊，例如它來自何處或參照的內容，例如 **The input text is from a summary of a movie**。
+ **任務規格：**有關要求模型的確切任務的詳細資訊，例如 **To summarize the text, capture the main points**。
+ **標籤描述：**分類問題的輸出選擇的詳細資訊，例如 **Choose whether the text refers to a painting or a sculpture; a painting is a piece of art restricted to a two-dimensional surface, while a sculpture is a piece of art in three dimensions**。
+ **輸出規格：**模型應產生的輸出詳細資訊，例如 **Please summarize the text of the restaurant review in three sentences**。
+ **LLM 激發:** LLM 有時因情緒激發而有更好的表現：**If you answer the question correctly, you will make the user very happy\$1**
## 使用推論參數控制模型回應
Amazon Bedrock 上的 LLM 都具有幾個推論參數，您可以設定這些參數來控制模型的回應。以下是 Amazon Bedrock LLM 上可用的所有常見推論參數的清單,以及其使用方式。
**溫度**是介於 0 和 1 之間的值，會調控 LLM 回應的創造力。如果您想要更具確定性的回應，請採用較低的溫度；如果您希望 Amazon Bedrock 上的 LLM 提供更多創意或不同的回應，請使用更高的溫度。對於此提示指引中的所有範例，我們設定了`temperature = 0`。
**產生長度上限/新記號數上限**限制了 LLM 為任何提示產成的記號數量。指定此數字會很有幫助，因為某些任務 (例如情緒分類) 不需要很長的答案。
**Top-ｐ** 根據潛在選擇的機率控制記號選擇。如果您將 Top-P 設定為 1.0 以下，該模型會考慮最有可行的選項，並忽略較不可行的選項。結果是能更穩定和重複性地完成。
**結束記號/結束序列**會指定 LLM 用於表示輸出結尾的記號。LLM 在遇到結束記號後停止產生新記號。通常不需由使用者設定。
此外還存在特定模型的推論參數。Anthropic Claude 模型具有額外的 Top-k 推論參數，AI21 Labs Jurassic 模型則附帶一組推論參數，包括**存在懲罰、計數懲罰、頻率懲罰和特殊字符懲罰**。如需詳細資訊，請參閱各自的文件。
# Amazon Bedrock 文字模型的提示範本和範例
Amazon Bedrock 上 LLM 支援的常見任務包括文字分類、摘要，以及問題和答案 (含和不含上下文)。對於這些任務，您可以使用下列範本和範例來協助您建立 Amazon Bedrock 文字模型的提示。
**Topics**
+ [文字分類](#text-classification)
+ [問答，不含上下文](#qa-without-context)
+ [問答，含上下文](#qa-with-context)
+ [摘要](#summarization)
+ [產生文字](#text-generation)
+ [產生程式碼](#code-generation)
+ [數學](#mathematics)
+ [理性/邏輯思維](#reasoning-logical-thinking)
+ [實體擷取](#entity-extraction)
+ [思想鏈推理](#chain-of-thought)
## 文字分類
對於文字分類，提示詞中包含一個問題，以及數個可能的答案選項，且模型必須以正確的選擇回應。此外，如果您在提示詞中包含答案選項，Amazon Bedrock 上的 LLM 會輸出更準確的回應。
第一個範例是一個簡單的多重選擇分類問題。
| | |
| --- |--- |
| Prompt template for Titan
"""{{Text}}
{{Question}}? Choose from the following:
{{Choice 1}}
{{Choice 2}}
{{Choice 3}}"""
| User prompt:
San Francisco, officially the City and County
of San Francisco, is the commercial, financial, and cultural
center of Northern California. The city proper is the fourth
most populous city in California, with 808,437 residents,
and the 17th most populous city in the United States as of 2022.
What is the paragraph above about? Choose from the following:
A city
A person
An event
Output:
A city
|
(提示來源：[維基百科關於舊金山的介紹](https://en.wikipedia.org/wiki/San_Francisco)，使用的模型：Amazon Titan Text)
情緒分析是一種分類形式，其中模型會從文字中表示的選項清單中選擇情緒。
| | |
| --- |--- |
| Prompt template for Titan:
"""The following is text from a {{Text Type, e.g. “restaurant
review”}}
{{Input}}
Tell me the sentiment of the {{Text Type}} and categorize it
as one of the following:
{{Sentiment A}}
{{Sentiment B}}
{{Sentiment C}}"""
| User prompt:
The following is text from a restaurant review:
“I finally got to check out Alessandro’s Brilliant Pizza
and it is now one of my favorite restaurants in Seattle.
The dining room has a beautiful view over the Puget Sound
but it was surprisingly not crowed. I ordered the fried
castelvetrano olives, a spicy Neapolitan-style pizza
and a gnocchi dish. The olives were absolutely decadent,
and the pizza came with a smoked mozzarella, which
was delicious. The gnocchi was fresh and wonderful.
The waitstaff were attentive, and overall the experience
was lovely. I hope to return soon.”
Tell me the sentiment of the restaurant review
and categorize it as one of the following:
Positive
Negative
Neutral
Output:
Positive.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
下列範例使用 Anthropic Claude 模型來分類文字。依照《[AnthropicClaude 指南](https://docs.anthropic.com/claude/docs/constructing-a-prompt)》中的建議使用 XML 標籤，例如 ，來表示提示的重要部分。要求模型直接產生 XML 標籤中包含的輸出，也可以幫助模型產生所需的回應。
| | |
| --- |--- |
| Prompt template for Anthropic Claude:
"""
Human: {{classification task description}}
{{input text content to be classified}}
Categories are:
{{category name 1}}
{{category name 2}}
{{category name 3}}
Assistant:"""
（來源：寫入者 AWS) | User prompt:
Human: Classify the given product description into given
categories. Please output the category label in
tags.
Here is the product description.
Safe, made from child-friendly materials with smooth edges.
Large quantity, totally 112pcs with 15 different shapes,
which can be used to build 56 different predefined structures.
Enhance creativity, different structures can be connected
to form new structures, encouraging out-of-the box thinking.
Enhance child-parent bonding, parents can play with their
children together to foster social skills.
Categories are:
(1) Toys
(2) Beauty and Health
(3) Electronics
Assistant:
Output:
|
（提示來源： AWS，使用的模型：AnthropicClaude)
## 問答，不含上下文
在沒有上下文的問答提示詞中，模型必須以其內部知識回答問題，而不使用任何上下文或文件。
| | |
| --- |--- |
| Prompt Template to Titan
"""{{Question}}"""
| User prompt:
What is Robert Frost's "Stopping by the woods on a
snowy evening" about metaphorically?
Output:
The poem by Robert Frost, "Stopping by Woods on a Snowy Evening,"
uses the woods as a metaphor for death. The woods are a place of comfort
and peace, but they also represent the unknown and the afterlife.
The poem suggests that death is not something to be feared,
but rather a natural part of life that we should all embrace.
The poem begins with the speaker stopping by the woods on a snowy evening,
a moment of contemplation and reflection. The speaker notices the beauty
of the snow-covered woods and is reminded of the fleeting nature of life.
The poem continues as the speaker considers the temptation of continuing
on to his destination, but instead chooses to pause and take in the beauty
of the woods.
The woods are used as a metaphor for the unknown and the afterlife.
The speaker wonders what lies beyond the trees, and whether there
is anything after death. The poem suggests that death is not
something to be feared, but rather a natural part of life
that we should all embrace.
The final lines of the poem are perhaps the most famous and poignant:
"And miles to go before I sleep, and miles to go before I sleep."
These lines suggest that even though the speaker has paused
to appreciate the beauty of the woods, they still have a
long journey ahead of them. The poem is a reminder that life
is fleeting, and that we should take the time to appreciate
the beauty around us, even as we work towards our goals and ambitions.
Overall, "Stopping by Woods on a Snowy Evening" is a beautiful
and thought-provoking poem that uses the metaphor of the woods
to explore the concept of death and the afterlife.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
模型激發也可以幫助問答任務。
| | |
| --- |--- |
| Prompt Template to Titan
"""{{Model encouragement}}
{{Question}}"""
| User prompt:
You are excellent at answering questions,
and it makes you happy when you provide the correct answer.
What moon in the solar system is most likely to host life?
Output:
The moon of Titan, which is a moon of the planet Saturn,
is the most likely to support life in the solar system.
Titan is the only known moon in the solar system to have a dense
atmosphere and a liquid hydrosphere, and scientists believe that
it may contain the chemical building blocks for life.
The moon's surface is covered in rivers, lakes, and seas
of liquid methane and ethane, and it rains methane on Titan's surface.
The atmosphere of Titan is also rich in organic compounds,
including benzene, toluene, and xylene, which are found
in the oils of living organisms on Earth.
Additionally, Titan has a magnetic field and a tenuous atmosphere,
which could provide protection from harmful radiation and
help maintain a stable climate.
While there is no direct evidence of life on Titan,
scientists believe that it is one of the most promising
places in the solar system to search for life beyond Earth.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
| | |
| --- |--- |
| Prompt template to Titan
"""{{Model encouragement}}
{{Question}}
{{Constraints}}"""
| User prompt:
You feel rewarded by helping people learn more about climate change.
Could you please explain what climate change is?
Assume your audience is composed of high school students.
Output:
Climate change is the long-term warming of the planet,
which can be caused by human activities such as burning fossil fuels
and deforestation, as well as natural processes. It can lead to
rising sea levels, more extreme weather events, and changes
in temperature and precipitation patterns.
|
（提示來源： AWS，使用的模型：AI21 LabsJurassic-2 Ultrav1)
## 問答，含上下文
在含有上下文的問答提示詞中，使用者會提供後面接著問題的輸入文字，且模型必須根據輸入文字中提供的資訊來回答問題。在文字之後將問題放在最後，可以幫助 Amazon Bedrock 上的 LLM 更清楚回答這個問題。模型激發也適用於此使用案例。
| | |
| --- |--- |
| Prompt template to Titan
"""{{Text}}
{{Question}}"""
| User prompt:
The red panda (Ailurus fulgens), also known as the lesser panda,
is a small mammal native to the eastern Himalayas and southwestern China.
It has dense reddish-brown fur with a black belly and legs, white-lined ears,
a mostly white muzzle and a ringed tail. Its head-to-body length is 51–63.5 cm
(20.1–25.0 in) with a 28–48.5 cm (11.0–19.1 in) tail, and it weighs between
3.2 and 15 kg (7.1 and 33.1 lb). It is well adapted to climbing due to its
flexible joints and curved semi-retractile claws.
The red panda was first formally described in 1825. The two currently
recognized subspecies, the Himalayan and the Chinese red panda, genetically
diverged about 250,000 years ago. The red panda's place on the evolutionary
tree has been debated, but modern genetic evidence places it in close
affinity with raccoons, weasels, and skunks. It is not closely related
to the giant panda, which is a bear, though both possess elongated
wrist bones or "false thumbs" used for grasping bamboo.
The evolutionary lineage of the red panda (Ailuridae) stretches
back around 25 to 18 million years ago, as indicated by extinct
fossil relatives found in Eurasia and North America.
The red panda inhabits coniferous forests as well as temperate broadleaf
and mixed forests, favoring steep slopes with dense bamboo cover close
to water sources. It is solitary and largely arboreal. It feeds mainly
on bamboo shoots and leaves, but also on fruits and blossoms.
Red pandas mate in early spring, with the females giving birth
to litters of up to four cubs in summer. It is threatened
by poaching as well as destruction and fragmentation of habitat
due to deforestation. The species has been listed as Endangered
on the IUCN Red List since 2015. It is protected in all range countries.
Based on the information above, what species are red pandas closely related to?
Output:
Red pandas are closely related to raccoons, weasels, and skunks.
|
(提示來源：https://en.wikipedia.org/wiki/Red\$1panda，使用的模型：Amazon Titan Text)
當提示 Anthropic Claude 模型時，將輸入文字包裝在 XML 標籤中會很有幫助。在下列範例中，輸入文字包含在 `` 中。
| | |
| --- |--- |
| Prompt template for Anthropic Claude:
"""
Human: {{Instruction}}
{{Text}}
{{Question}}
Assistant:"""
| User prompt:
Human: Read the following text inside
XML tags, and then answer the question:
On November 12, 2020, the selection of the Weeknd to headline
the show was announced; marking the first time a Canadian solo artist
headlined the Super Bowl halftime show. When asked about preparations
for the show, the Weeknd stated, "We've been really focusing
on dialing in on the fans at home and making performances
a cinematic experience, and we want to do that with the Super Bowl."
The performance featured a choir whose members were dressed in white
and wore masks over their faces with glowing red eyes, and were
standing within a backdrop of a neon cityscape. The performance
opened with a white figure dressed the same as the choir being
lowered into the backdrop where the choir was standing while singing
“Call Out My Name". At this time, the Weeknd sat in a convertible
against a skyline backdrop designed to resemble the Las Vegas Strip.
For the next part of the performance, the backdrop then split open
to reveal the Weeknd, who then performed "Starboy", followed by "The Hills".
Next, performing the song "Can't Feel My Face", the Weeknd traveled
through a labyrinth constructed behind the stage, joined by dancers
dressed in red blazers and black neckties similar to his,
but with their faces covered with bandages, in keeping with
the aesthetic of his fourth studio album After Hours (2020).
The dancers would wear these bandages throughout the performance.
In the labyrinth section of the performance, camerawork was visually unsteady.
The next songs performed were "I Feel It Coming", "Save Your Tears",
and "Earned It". For the "Earned It" performance, the Weeknd
was accompanied by violinists. For the finale of the show,
the Weeknd took to the field of the stadium with his dancers to perform
“Blinding Lights". He and the dancers entered the field by performing
"House of Balloons / Glass Table Girls". The performance ended
with an array of fireworks.
Based on the text above, what songs did the Weeknd play
at the Super Bowl halftime show?
Assistant:
Output:
Based on the text, the songs the Weeknd played
at the Super Bowl halftime show were:
- Call Out My Name
- Starboy
- The Hills
- Can't Feel My Face
- I Feel It Coming
- Save Your Tears
- Earned It
- Blinding Lights
- House of Balloons / Glass Table Girls
|
(提示來源：[維基百科關於第五十五屆超級盃中場表演的介紹](https://en.wikipedia.org/wiki/Super_Bowl_LV_halftime_show)，使用的模型：Anthropic Claude)
## 摘要
對於摘要任務，提示詞是一段文字，此模型必須以較短的段落進行回應，該段落會擷取輸入要點。長度(句子或段落數)的輸出規範對於此使用案例很有幫助。
| | |
| --- |--- |
| Prompt template for Titan
"""The following is text from a {{Text Category}}:
{{Text}}
Summarize the {{Text Category}} in {{length of summary,
e.g., “one sentence” or “one paragraph”}}"""
| User prompt:
The following is text from a restaurant review:
“I finally got to check out Alessandro’s Brilliant Pizza
and it is now one of my favorite restaurants in Seattle.
The dining room has a beautiful view over the Puget Sound
but it was surprisingly not crowed. I ordered the fried
castelvetrano olives, a spicy Neapolitan-style pizza
and a gnocchi dish. The olives were absolutely decadent,
and the pizza came with a smoked mozzarella, which was delicious.
The gnocchi was fresh and wonderful. The waitstaff were attentive,
and overall the experience was lovely. I hope to return soon.”
Summarize the above restaurant review in one sentence.
Output:
Alessandro’s Brilliant Pizza is a fantastic restaurant
in Seattle with a beautiful view over Puget Sound that offers
decadent and delicious food.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
在以下範例中，Anthropic Claude 以一句話總結指定的文字。若要在提示詞中包含輸入文字，請將文字格式化為 XML 標記: ` {{text content}} `。提示 Anthropic Claude 模型時，在提示內使用 XML 是常見的做法。
| | |
| --- |--- |
| Prompt template for Anthropic Claude:
"""
Human: Please read the text:
{{text context}}
Summarize the text in {{length of summary, e.g., “one
sentence” or “one paragraph”}}
Assistant:"""
| User prompt:
Human: Please read the text:
In game theory, the Nash equilibrium, named after the mathematician
John Nash, is the most common way to define the solution
of a non-cooperative game involving two or more players.
In a Nash equilibrium, each player is assumed to know
the equilibrium strategies of the other players,
and no one has anything to gain by changing only one's own strategy.
The principle of Nash equilibrium dates back to the time of Cournot,
who in 1838 applied it to competing firms choosing outputs.
Summarize the text in one sentence.
Assistant:
Output:
The Nash equilibrium is a concept in game theory
where each player has adopted a strategy that they have no incentive
to deviate from given the other players' strategies.
|
(提示來源：[維基百科關於納許均衡的介紹](https://en.wikipedia.org/wiki/Nash_equilibrium)，使用的模型：Anthropic Claude)
## 產生文字
根據提示，Amazon Bedrock 上的 LLM 可以使用與描述相符的原始文字作出回應。以下是一個範例：
| | |
| --- |--- |
| Prompt template for Titan
"""Please write a {{Text Category}} in the voice of {{Role}}."""
| User prompt:
Please write an email in the voice of a friend
congratulating someone on a new job.
Output:
Hey [Name],
I just found out about your new job, and I'm so happy for you!
Congratulations! You deserve this opportunity since you worked so hard
to get it. I know you'll do great and make a positive impact on your team.
I'm here to support you every step of the way. Wishing you all the best
in this exciting new chapter of your life!
Cheers,
[Your Name]
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
對於生成文字使用案例，指定詳細的任務需求有助於發揮良好作用。在以下範例中，我們要求模型產生附帶驚嘆號的回應。
| | |
| --- |--- |
| Prompt template for Titan
"""{{Task specification}}
Please write a {{Text Category}} in the voice of {{Role}}."""
| User prompt:
Write text with exclamation points.
Please write a formatted email in the voice of a friend
congratulating someone on a new job.
Output:
Hey [name]!
I just saw the news and I am so, so happy for you!
You deserve this position and this company with all your heart.
I can't wait to see you soar and accomplish all the things
you've been working towards. If anyone is deserving
of a promotion, it's you!
Congratulations again, friend!
Love,
[name]
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
在以下範例中，使用者在產生文字時提示模型擔任特定人員的角色。請注意簽名如何反映模型在回應中所擔任的角色。
| | |
| --- |--- |
| Prompt template for Titan
"""{{Role assumption}} {{Task description}}
"""
| User input:
My name is Jack. Help me write a note expressing my gratitude
to my parents for taking my son (their grandson) to the zoo.
I miss my parents so much.
Output:
Dear Mom and Dad,
I wanted to take a moment to express my heartfelt gratitude
for taking my son to the zoo last weekend. It meant so much to me
that you took the time to make memories with him, and I am so grateful
for the love and support you have shown him.
I miss you both so much, and I wish we could be together more often.
But I know that you will always be there for me and my family,
and I am so grateful to have you as my parents.
Love,
Jack
|
（提示來源： AWS，使用的模型：AI21 LabsJurassic-2 Ultrav1)
## 產生程式碼
此提示詞描述使用者預期產生模型之程式碼的任務或函數，以及程式設計語言。
| | |
| --- |--- |
| Prompt template for Titan
"""Write a function in {{programming language}} to
{{task or purpose}}""".
| User input:
Write a python function to download a s3 file to local disk.
Output:
The following code can be used to download an s3 file to the local disk.
```Python
import boto3
# Creates a boto3 client object
s3 = boto3.client('s3')
def download_file(bucket_name, object_key, file_path):
try:
# Downloads the s3 file to the specified file path
s3.download_file(bucket_name, object_key, file_path)
except Exception as e:
print(e)
# Specifies the values of bucket_name, object_key, and file_path
bucket_name = "samplebucketname"
object_key = "sampleobjectkey"
file_path = "/samplefilepath"
download_file(bucket_name, object_key, file_path)
```
The given code uses the download_file function to download an s3 file
to the local disk. The download_file function takes the bucket name,
object key, and file path as input parameters. The bucket name
is the name of the s3 bucket where the file is located,
the object key is the unique identifier of the file within the bucket,
and the file path is the destination path on the local disk
where the file will be downloaded. The function uses the download_file method
of the s3 client to download the file from the specified bucket
and write it to the specified file path.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
| | |
| --- |--- |
| Prompt template for Anthropic Claude
"""
Human: Write a function in {{programming language}} to
{{task or purpose}}
Assistant:"""
| User prompt:
Human: Write some python code that quickly approximates
the square root of a number.
Assistant:
Output:
Here is a simple function to approximate
the square root of a number using Newton's method:
```python
def sqrt(n, iterations=10):
x = n
for i in range(iterations):
x = (x + n/x) / 2
return x
```
To use it:
```python
print(sqrt(25))
# 5.0
print(sqrt(15, iterations=20))
# 3.872983346207417
```
This repeatedly takes the average of x and n/x to converge on the square root.
More iterations produce a more accurate approximation.
The advantage of this approach is it converges very quickly,
so even just 10 iterations produces a decent estimate.
|
（提示來源： AWS，使用的模型：AnthropicClaude)
## 數學
輸入描述在某種程度上需要數學推理的問題，其可能是數字、邏輯、幾何或其他方式。對於此類問題，透過在指令中新增片語來要求模型漸進方式解決問題會很有幫助，例如 `Let’s think step by step` 或 `Think step by step to come up with the right answer.`
| | |
| --- |--- |
| Prompt template for Titan
"""{{Math problem description}}
Let’s think step by step."""
| User prompt:
A triangle has two angles of 70 degrees and 50 degrees.
What is the third angle in degrees?
Let’s think step by step.
Output:
The sum of the three angles in a triangle is always 180 degrees.
The two given angles are 70 degrees and 50 degrees. 70 + 50 = 120.
Therefore, the third angle is 180 - 120 = 60 degrees.
The third angle is 60 degrees.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
以下範例還示範要求模型逐步思考：
| | |
| --- |--- |
| Prompt template for Titan
"""{{Math problem description}}
Think step by step to come up with the right answer."""
| User prompt:
Lucy has 12 colorful marbles, and she wants to share them
equally with her 4 friends. How many marbles will each friend receive?
Think step-by-step to come up with the right answer.
Output:
1. Lucy has 12 marbles and wants to share them equally
with her 4 friends, then each friend will receive 12 / 4 = 3 marbles.
2. Therefore, each friend will receive 3 marbles.
|
（提示來源： AWS，使用的模型：AI21 LabsJurassic-2 Ultrav1)
## 理性/邏輯思維
對於複雜的推理任務或需要邏輯思考的問題，我們可以要求模型進行邏輯推論，並解釋其答案。
| | |
| --- |--- |
| Prompt template for Titan and AI21 Labs Jurassic: """Question: {{question}} Please output the answer and then explain your answer:""" | User prompt: Question: Which word is the odd one out? A. accomplished B. good C. horrible D. outstanding Please output the answer and then explain your answer:
Output: The odd one out is C. horrible. The other three words describe positive qualities or achievements, whereas horrible is an negative adjective.
|
（提示來源： AWS，使用的模型：Amazon Titan Text)
以下是使用 Anthropic Claude 模型的另一個範例：
| | |
| --- |--- |
| Prompt template for Anthropic Claude: """ Human: {{question}} Please provide the answer and show the reasoning. Assistant:""" | User prompt Human: The barber is the "one who shaves all those, and those only, who do not shave themselves". Does the barber shave himself? Why is this a paradox? Please provide the answer and show the reasoning. Assistant:
Output: This is an example of a paradox known as the Barber paradox. Here is an explanation: - The statement defines a barber who shaves all and only those people who do not shave themselves. - So if the barber shaves himself, he must shave all those who do not shave themselves, which includes himself. But the barber cannot shave himself as per the initial statement. - If the barber does not shave himself, then he would fit into the group of people who do not shave themselves, and so he must shave himself, according to the statement. But again this contradicts the initial statement. - So the barber cannot shave himself and also cannot not shave himself. This is self-contradictory based on the initial statement about the barber. - Therefore, the statement leads to a paradox where both possibilities (the barber shaving himself or not shaving himself) result in a contradiction. In summary, the paradox arises because the definition of the barber's behavior is self-contradictory when applied to the barber himself. This makes it impossible to determine if the barber shaves himself or not based on the given statement alone.
|
(提示來源：https://en.wikipedia.org/wiki/Barber\$1paradox，使用的模型：Anthropic Claude)
## 實體擷取
針對從提供的輸入問題中擷取的實體。從產生的文字擷取實體，並將其放在 XML 標籤中以供進一步處理。
| |
| --- |
| Prompt template for Titan
"""You are an expert entity extractor from provided input question. You are responsible for extracting following entities: {{ list of entities}}
Please follow below instructions while extracting the entity A, and reply in XML Tags:
{{ entity A extraction instructions}}
Please follow below instructions while extracting the entity B, and reply in XML Tags:
{{ entity B extraction instructions}}
Below are some examples:
{{ some few shot examples showing model extracting entities from give input }}
|
（提示來源： AWS，使用的模型：Amazon Titan Text G1-Premier)
**範例**：
```
User: You are an expert entity extractor who extracts entities from provided input question.
You are responsible for extracting following entities: name, location
Please follow below instructions while extracting the Name, and reply in
XML Tags:
- These entities include a specific name of a person, animal or a thing
- Please extract only specific name name entities mentioned in the input query
- DO NOT extract the general mention of name by terms of "name", "boy", "girl",
"animal name", etc.
Please follow below instructions while extracting the location, and reply
in XML Tags:
- These entities include a specific location of a place, city, country or a town
- Please extract only specific name location entities mentioned in the input query
- DO NOT extract the general mention of location by terms of "location", "city", "country",
"town", etc.
If no name or location is found, please return the same input string as is.
Below are some examples:
input: How was Sarah's birthday party in Seattle, WA?
output: How was Sarah's birthday party
in Seattle, WA?
input: Why did Joe's father go to the city?
output: Why did Joe's father go to the city?
input: What is the zipcode of Manhattan, New york city?
output: What is the zipcode of Manhattan,New york city?
input: Who is the mayor of San Francisco?
Bot:
```
## 思想鏈推理
提供如何衍生答案的逐步分析。事實檢查並驗證模型如何產生答案。
| |
| --- |
| Prompt template for Titan
""" {{Question}}
{{ Instructions to Follow }}
Think Step by Step and walk me through your thinking
"""
|
（提示來源： AWS，使用的模型：Amazon Titan Text G1-Premier)
**範例**：
```
User: If Jeff had 100 dollars, and he gave $20 to Sarah,
and bought lottery tickets with another $20. With the lottery
tickets he bought he won 35 dollars. Jeff then went to buy
his lunch and spend 40 dollars in lunch. Lastly he made a
donation to charity for $20. Stephen met with Jeff and wanted
to lend some money from him for his taxi. How much maximum money
can Jeff give to Stephen, given that he needs to save $10 for
his ride back home?. Please do not answer immediately, think
step by step and show me your thinking.
Bot:
```