In this guide, we'll learn how to create a simple prompt template that provides the model with example inputs and outputs when generating. Providing the LLM with a few such examples is called few-shotting, and is a simple yet powerful way to guide generation and in some cases drastically improve model performance.
(在本指南中，我们将学习如何创建一个简单的提示模板，该模板在生成时为模型提供示例输入和输出。为 LLM 提供一些这样的示例称为少样本，这是一种简单但有效的指导生成的方法，在某些情况下可以显著提高模型性能。)
A few-shot prompt template can be constructed from either a set of examples, or from an Example Selector class responsible for choosing a subset of examples from the defined set. 几次提示模板可以从一组示例构建，也可以从负责从定义集中选择示例子集的示例选择器类构建。
This guide will cover few-shotting with string prompt templates. For a guide on few-shotting with chat messages for chat models, see here.
(本指南将介绍使用字符串提示模板进行的几次拍摄。有关聊天模型的聊天消息的少量拍摄指南，请参阅此处。)
Create a formatter for the few-shot examples
Configure a formatter that will format the few-shot examples into a string. This formatter should be a PromptTemplate object.
配置一个格式化程序，将少量示例格式化为字符串。该格式化程序应该是 PromptTemplate 对象。
from langchain_core.prompts import PromptTemplate
example_prompt = PromptTemplate.from_template("Question: {question}\n{answer}")
API Reference: PromptTemplate
Creating the example set
Next, we'll create a list of few-shot examples. Each example should be a dictionary representing an example input to the formatter prompt we defined above.
接下来，我们将创建一个少量示例的列表。每个示例都应该是一个字典，表示我们上面定义的格式化程序提示的示例输入。
examples = [
{
"question": "Who lived longer, Muhammad Ali or Alan Turing?",
"answer": """
Are follow up questions needed here: Yes.
Follow up: How old was Muhammad Ali when he died?
Intermediate answer: Muhammad Ali was 74 years old when he died.
Follow up: How old was Alan Turing when he died?
Intermediate answer: Alan Turing was 41 years old when he died.
So the final answer is: Muhammad Ali
""",
},
{
"question": "When was the founder of craigslist born?",
"answer": """
Are follow up questions needed here: Yes.
Follow up: Who was the founder of craigslist?
Intermediate answer: Craigslist was founded by Craig Newmark.
Follow up: When was Craig Newmark born?
Intermediate answer: Craig Newmark was born on December 6, 1952.
So the final answer is: December 6, 1952
""",
},
{
"question": "Who was the maternal grandfather of George Washington?",
"answer": """
Are follow up questions needed here: Yes.
Follow up: Who was the mother of George Washington?
Intermediate answer: The mother of George Washington was Mary Ball Washington.
Follow up: Who was the father of Mary Ball Washington?
Intermediate answer: The father of Mary Ball Washington was Joseph Ball.
So the final answer is: Joseph Ball
""",
},
{
"question": "Are both the directors of Jaws and Casino Royale from the same country?",
"answer": """
Are follow up questions needed here: Yes.
Follow up: Who is the director of Jaws?
Intermediate Answer: The director of Jaws is Steven Spielberg.
Follow up: Where is Steven Spielberg from?
Intermediate Answer: The United States.
Follow up: Who is the director of Casino Royale?
Intermediate Answer: The director of Casino Royale is Martin Campbell.
Follow up: Where is Martin Campbell from?
Intermediate Answer: New Zealand.
So the final answer is: No
""",
},
]
Let's test the formatting prompt with one of our examples:
print(example_prompt.invoke(examples[0]).to_string())
Question: Who lived longer, Muhammad Ali or Alan Turing?
Are follow up questions needed here: Yes.
Follow up: How old was Muhammad Ali when he died?
Intermediate answer: Muhammad Ali was 74 years old when he died.
Follow up: How old was Alan Turing when he died?
Intermediate answer: Alan Turing was 41 years old when he died.
So the final answer is: Muhammad Ali
Pass the examples and formatter to FewShotPromptTemplate
Finally, create a FewShotPromptTemplate object. This object takes in the few-shot examples and the formatter for the few-shot examples. When this FewShotPromptTemplate is formatted, it formats the passed examples using the example_prompt, then and adds them to the final prompt before suffix:
最后，创建一个 FewShotPromptTemplate 对象。此对象接收少样本示例和少样本示例的格式化程序。格式化此 FewShotPromptTemplate 时，它会使用 example_prompt 格式化传递的示例，然后将它们添加到后缀之前的最终提示中：
from langchain_core.prompts import FewShotPromptTemplate
prompt = FewShotPromptTemplate(
examples=examples,
example_prompt=example_prompt,
suffix="Question: {input}",
input_variables=["input"],
)
print(
prompt.invoke({"input": "Who was the father of Mary Ball Washington?"}).to_string()
)
API Reference: FewShotPromptTemplate
Question: Who lived longer, Muhammad Ali or Alan Turing?
Are follow up questions needed here: Yes.
Follow up: How old was Muhammad Ali when he died?
Intermediate answer: Muhammad Ali was 74 years old when he died.
Follow up: How old was Alan Turing when he died?
Intermediate answer: Alan Turing was 41 years old when he died.
So the final answer is: Muhammad Ali
Question: When was the founder of craigslist born?
Are follow up questions needed here: Yes.
Follow up: Who was the founder of craigslist?
Intermediate answer: Craigslist was founded by Craig Newmark.
Follow up: When was Craig Newmark born?
Intermediate answer: Craig Newmark was born on December 6, 1952.
So the final answer is: December 6, 1952
Question: Who was the maternal grandfather of George Washington?
Are follow up questions needed here: Yes.
Follow up: Who was the mother of George Washington?
Intermediate answer: The mother of George Washington was Mary Ball Washington.
Follow up: Who was the father of Mary Ball Washington?
Intermediate answer: The father of Mary Ball Washington was Joseph Ball.
So the final answer is: Joseph Ball
Question: Are both the directors of Jaws and Casino Royale from the same country?
Are follow up questions needed here: Yes.
Follow up: Who is the director of Jaws?
Intermediate Answer: The director of Jaws is Steven Spielberg.
Follow up: Where is Steven Spielberg from?
Intermediate Answer: The United States.
Follow up: Who is the director of Casino Royale?
Intermediate Answer: The director of Casino Royale is Martin Campbell.
Follow up: Where is Martin Campbell from?
Intermediate Answer: New Zealand.
So the final answer is: No
Question: Who was the father of Mary Ball Washington?
Using an example selector
We will reuse the example set and the formatter from the previous section. However, instead of feeding the examples directly into the FewShotPromptTemplate object, we will feed them into an implementation of ExampleSelector called SemanticSimilarityExampleSelector instance. This class selects few-shot examples from the initial set based on their similarity to the input. It uses an embedding model to compute the similarity between the input and the few-shot examples, as well as a vector store to perform the nearest neighbor search.
我们将重用上一节中的示例集和格式化程序。但是，我们不会将示例直接输入到 FewShotPromptTemplate 对象中，而是将它们输入到名为 SemanticSimilarityExampleSelector 实例的 ExampleSelector 实现中。此类根据与输入的相似性从初始集合中选择少量样本示例。它使用嵌入模型来计算输入与少量样本示例之间的相似性，并使用向量存储来执行最近邻搜索。
To show what it looks like, let's initialize an instance and call it in isolation:
为了展示它的样子，让我们初始化一个实例并单独调用它：
from langchain_chroma import Chroma
from langchain_core.example_selectors import SemanticSimilarityExampleSelector
from langchain_openai import OpenAIEmbeddings
example_selector = SemanticSimilarityExampleSelector.from_examples(
# This is the list of examples available to select from.
examples,
# This is the embedding class used to produce embeddings which are used to measure semantic similarity.
OpenAIEmbeddings(),
# This is the VectorStore class that is used to store the embeddings and do a similarity search over.
Chroma,
# This is the number of examples to produce.
k=1,
)
# Select the most similar example to the input.
question = "Who was the father of Mary Ball Washington?"
selected_examples = example_selector.select_examples({"question": question})
print(f"Examples most similar to the input: {question}")
for example in selected_examples:
print("\n")
for k, v in example.items():
print(f"{k}: {v}")
API Reference: SemanticSimilarityExampleSelector | OpenAIEmbeddings
Examples most similar to the input: Who was the father of Mary Ball Washington?
answer:
Are follow up questions needed here: Yes.
Follow up: Who was the mother of George Washington?
Intermediate answer: The mother of George Washington was Mary Ball Washington.
Follow up: Who was the father of Mary Ball Washington?
Intermediate answer: The father of Mary Ball Washington was Joseph Ball.
So the final answer is: Joseph Ball
question: Who was the maternal grandfather of George Washington?
Now, let's create a FewShotPromptTemplate object. This object takes in the example selector and the formatter prompt for the few-shot examples.
现在，让我们创建一个 FewShotPromptTemplate 对象。该对象接受示例选择器和少数示例的格式化程序提示。
prompt = FewShotPromptTemplate(
example_selector=example_selector,
example_prompt=example_prompt,
suffix="Question: {input}",
input_variables=["input"],
)
print(
prompt.invoke({"input": "Who was the father of Mary Ball Washington?"}).to_string()
)
Question: Who was the maternal grandfather of George Washington?
Are follow up questions needed here: Yes.
Follow up: Who was the mother of George Washington?
Intermediate answer: The mother of George Washington was Mary Ball Washington.
Follow up: Who was the father of Mary Ball Washington?
Intermediate answer: The father of Mary Ball Washington was Joseph Ball.
So the final answer is: Joseph Ball
Question: Who was the father of Mary Ball Washington?
Next steps
You've now learned how to add few-shot examples to your prompts.
Next, check out the other how-to guides on prompt templates in this section, the related how-to guide on few shotting with chat models, or the other example selector how-to guides.
