FewShotPromptTempalte
在我们的提示词中增加一些实例 用于规范大模型的输出
from langchain_core.prompts import FewShotPromptTemplate, PromptTemplate
# 示例数据 Q&A
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
""",
},
]
#基础的prompt
example_prompt = PromptTemplate.from_template("Question: {question}\n{answer}")
# 实例化 few-shot prompt
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()
)
通过上面这种方式 我们就可以在给大模型的提示词中增加一些实例数据 加强大模型对问题的理解 规范化大模型的输出
partially format prompt templates
有的时候我们可能需要在提示词中告诉大模型当前世界的时间 或者是一些其他动态获取的数据 但是又不想 通过入参的方式每次都传递进来 那么我们可以使用下面这种方式
from datetime import datetime
from langchain_core.prompts import PromptTemplate
def _get_datetime():
now = datetime.now()
return now.strftime("%Y-%m-%d %H:%M:%S")
# 定义一个提示词模板
prompt = PromptTemplate(
template="Tell me a {adjective} joke about the day {date}",
input_variables=["adjective", "date"],
)
# 定义partial字段 以及需要提供一个callable 方法
partial_prompt = prompt.partial(date=_get_datetime)
print(partial_prompt.format(adjective="funny"))
或者在构建prompt 的时候 作为入参传给promptTemplate
prompt = PromptTemplate(
template="Tell me a {adjective} joke about the day {date}",
input_variables=["adjective"],
partial_variables={"date": _get_datetime},
)
print(prompt.format(adjective="funny"))
输出:
Tell me a funny joke about the day 2024-07-05 19:08:52
compose prompt
- chatComposeTemplate
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
prompt = SystemMessage(content="你的名字叫做bob 你是一个AI助手")
new_prompt = (
prompt + HumanMessage(content="hello") + AIMessage(content="hi") + "{input}"
)
print(new_prompt.invoke({"input": "你的名字叫什么？"}))
可以看到 可以用这种方式 来构建组合形式的MessageTemplate string类型的入参会被直接包装为HumanMessage
- piplineTemplate
我们可以通过piplinePromptTemplate 来进行多个prompt的流程式处理
from langchain_core.prompts import PipelinePromptTemplate, PromptTemplate
full_template = """{introduction}
{example}
{start}"""
full_prompt = PromptTemplate.from_template(full_template)
introduction_template = """You are impersonating {person}."""
introduction_prompt = PromptTemplate.from_template(introduction_template)
example_template = """Here's an example of an interaction:
Q: {example_q}
A: {example_a}"""
example_prompt = PromptTemplate.from_template(example_template)
start_template = """Now, do this for real!
Q: {input}
A:"""
start_prompt = PromptTemplate.from_template(start_template)
input_prompts = [
("introduction", introduction_prompt),
("example", example_prompt),
("start", start_prompt),
]
# 构建PipelinePromptTemplate
pipeline_prompt = PipelinePromptTemplate(
# final_prompt 最终的prompt
# pipeline_prompts List<Tuple<str,BasePromptTemplate>>
final_prompt=full_prompt, pipeline_prompts=input_prompts
)
print(
pipeline_prompt.format(
person="Elon Musk",
example_q="What's your favorite car?",
example_a="Tesla",
input="What's your favorite social media site?",
)
)
输出:
You are impersonating Elon Musk.
Here's an example of an interaction:
Q: What's your favorite car?
A: Tesla
Now, do this for real!
Q: What's your favorite social media site?
A:
总结
langchain 提供了比较多的prompt模板管理的方法 能够让我们更加规范的使用prompt 更多的方法使用需要大家去探索 **以上文章中的示例 大多来自官网示例 **
