微信扫码
与创始人交个朋友
我要投稿
—1—
LangChain 6大模块是什么?
—2—
Chains 深度剖析
这种类型的 Chain 应用起来很简单也可以说是后续要介绍 Chain 的基础,但其功能是足够强大的。通过 LLMChain 可以直接将数据、Prompt、以及想要应用的大模型串到一起,以下是 LLMChain 的例子。
from langchain import PromptTemplate, OpenAI, LLMChain
prompt_template = "What is a good name for a company that makes {product}?"
llm = OpenAI(temperature=0)
chain = LLMChain(
llm=llm,
prompt=PromptTemplate.from_template(prompt_template)
)
print(chain("colorful socks"))
# 输出结果'Socktastic!'
在这个例子中,我们首先初始化了一个 Prompt 字符串模版,并初始化大模型,然后利用 Chain 将模型运行起来。在「Chain 将模型运行起来」这个过程中:Chain 将会格式化 Prompt,然后将它传递给 LLM。
不同于基本的 LLMChain,Sequential Chain(序列链)是由一系列的链组合而成的,序列链有两种类型,一种是单个输入输出,另一个则是多个输入输出。先来看第一种单个输入输出的示例代码:
在这个示例中,创建了两条 Chain,并且让第一条 Chain 接收一个虚构剧本的标题,输出该剧本的概要,作为第二条 Chain 的输入,然后生成一个虚构评论。通过 Sequential Chains 可以简单实现这一需求。
第一条 Chain:
# This is an LLMChain to write a synopsis given a title of a play.
from langchain import PromptTemplate, OpenAI, LLMChain
llm = OpenAI(temperature=.7)
template = """You are a playwright. Given the title of play, it is your job to write a synopsis for that title.
Title: {title}
Playwright: This is a synopsis for the above play:"""
prompt_template = PromptTemplate(input_variables=["title"], template=template)
synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)
第二条 Chain:
# This is an LLMChain to write a review of a play given a synopsis.
from langchain import PromptTemplate, OpenAI, LLMChain
llm = OpenAI(temperature=.7)
template = """You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.
Play Synopsis:
{synopsis}
Review from a New York Times play critic of the above play:"""
prompt_template = PromptTemplate(input_variables=["synopsis"], template=template)
review_chain = LLMChain(llm=llm, prompt=prompt_template)
最后利用 SimpleSequentialChain 即可将两个 Chains 直接串联起来:
from langchain.chains import SimpleSequentialChain
overall_chain = SimpleSequentialChain(chains=[synopsis_chain, review_chain], verbose=True)
print(review = overall_chain.run("Tragedy at sunset on the beach"))
可以看到对于单个输入输出的顺序链,就是将两个 Chain 作为参数传给 SimpleSequentialChain 即可,无需复杂的声明。
除了单个输入输出的模式,序列链还支持更为复杂的多个输入输出,对于多输入输出模式来说,最应该需要关注的就是输入关键字和输出关键字,它们需要十分的精准,才能够保证 Chain 的识别与应用,以一个 Demo 为例:
from langchain import PromptTemplate, OpenAI, LLMChain
llm = OpenAI(temperature=.7)
template = """You are a playwright. Given the title of play and the era it is set in, it is your job to write a synopsis for that title.
Title: {title}
Era: {era}
Playwright: This is a synopsis for the above play:"""
prompt_template = PromptTemplate(input_variables=["title", 'era'], template=template)
synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, output_key="synopsis")
#第一条chain
from langchain import PromptTemplate, OpenAI, LLMChain
llm = OpenAI(temperature=.7)
template = """You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.
Play Synopsis:
{synopsis}
Review from a New York Times play critic of the above play:"""
prompt_template = PromptTemplate(input_variables=["synopsis"], template=template)
review_chain = LLMChain(llm=llm, prompt=prompt_template, output_key="review")
#第二条chain
from langchain.chains import SequentialChain
overall_chain = SequentialChain(
chains=[synopsis_chain, review_chain],
input_variables=["era", "title"],
# Here we return multiple variables
output_variables=["synopsis", "review"],
verbose=True)
#第三条chain
overall_chain({"title": "Tragedy at sunset on the beach", "era": "Victorian England"})
对于每一个Chain在定义的时候,都需要关注其output_key 和input_variables,按照顺序将其指定清楚。最终在运行 Chain 时我们只需要指定第一个 Chain 中需要声明的变量。
再介绍一个经常会用到的场景,比如:我们目前有三类 Chain,分别对应三种学科的问题解答。我们的输入内容也是与这三种学科对应,但是随机的,比如:第一次输入数学问题,第二次有可能是历史问题......这时候期待的效果是:可以根据输入的内容是什么,自动将其应用到对应的子链中。RouterChain 就为我们提供了这样一种能力,它会首先决定将要传递下去的子链,然后把输入传递给那个链。并且在设置的时候需要为其设置默认 Chain,以兼容输入内容不满足任意一项时的情况。
physics_template = """You are a very smart physics professor. \
You are great at answering questions about physics in a concise and easy to understand manner. \
When you don't know the answer to a question you admit that you don't know.
Here is a question:
{input}"""
math_template = """You are a very good mathematician. You are great at answering math questions. \
You are so good because you are able to break down hard problems into their component parts, \
answer the component parts, and then put them together to answer the broader question.
Here is a question:
{input}"""
如上述有一个物理学和数学的 Prompt:
prompt_infos = [
{
"name": "physics",
"description": "Good for answering questions about physics",
"prompt_template": physics_template
},
{
"name": "math",
"description": "Good for answering math questions",
"prompt_template": math_template
}
]
然后需要声明这两个 Prompt 的基本信息。
from langchain import ConversationChain, LLMChain, PromptTemplate, OpenAI
llm = OpenAI()
destination_chains = {}
for p_info in prompt_infos:
name = p_info["name"]
prompt_template = p_info["prompt_template"]
prompt = PromptTemplate(template=prompt_template, input_variables=["input"])
chain = LLMChain(llm=llm, prompt=prompt)
destination_chains[name] = chain
default_chain = ConversationChain(llm=llm, output_key="text")
最后将其运行到 RouterChain 中即可,我们此时在输入的时候 Chain 就会根据 input 的内容进行相应的选择最为合适的 Prompt。
from langchain.chains.router.llm_router import LLMRouterChain, RouterOutputParser
from langchain.chains.router.multi_prompt_prompt import MULTI_PROMPT_ROUTER_TEMPLATE
# Create a list of destinations
destinations = [f"{p['name']}: {p['description']}" for p in prompt_infos]
destinations_str = "\n".join(destinations)
# Create a router template
router_template = MULTI_PROMPT_ROUTER_TEMPLATE.format(destinations=destinations_str)
router_prompt = PromptTemplate(
template=router_template,
input_variables=["input"],
output_parser=RouterOutputParser(),
)
router_chain = LLMRouterChain.from_llm(llm, router_prompt)
chain = MultiPromptChain(
router_chain=router_chain,
destination_chains=destination_chains,
default_chain=default_chain,
verbose=True,
)
print(chain.run('什么是黑体辐射'))
53AI,企业落地应用大模型首选服务商
产品:大模型应用平台+智能体定制开发+落地咨询服务
承诺:先做场景POC验证,看到效果再签署服务协议。零风险落地应用大模型,已交付160+中大型企业
2024-05-28
2024-04-26
2024-08-13
2024-08-21
2024-07-09
2024-08-04
2024-06-13
2024-04-11
2024-07-18
2024-07-01