第四章 模型链¶

import os
import openai
from dotenv import load_dotenv, find_dotenv

# 读取本地/项目的环境变量。

# find_dotenv()寻找并定位.env文件的路径
# load_dotenv()读取该.env文件，并将其中的环境变量加载到当前的运行环境中  
# 如果你设置的是全局的环境变量，这行代码则没有任何作用。
_ = load_dotenv(find_dotenv())

# 获取环境变量 OPENAI_API_KEY
openai.api_key = os.environ['OPENAI_API_KEY']  

import pandas as pd
df = pd.read_csv('data/Data.csv')

from langchain_community.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate  
from langchain.chains.llm import LLMChain

prompt = ChatPromptTemplate.from_template(   
    "What is the best name to describe \
    a company that makes {product}?"
)

from langchain.chains.sequential import SimpleSequentialChain

llm = ChatOpenAI(temperature=0.9)

# 提示模板 1 ：这个提示将接受产品并返回最佳名称来描述该公司
first_prompt = ChatPromptTemplate.from_template(
    "What is the best name to describe \
    a company that makes {product}?"
)

# Chain 1
chain_one = LLMChain(llm=llm, prompt=first_prompt)

# 提示模板 2 ：接受公司名称，然后输出该公司的长为20个单词的描述
second_prompt = ChatPromptTemplate.from_template(
    "Write a 20 words description for the following \
    company:{company_name}"
)
# chain 2
chain_two = LLMChain(llm=llm, prompt=second_prompt)

overall_simple_chain = SimpleSequentialChain(chains=[chain_one, chain_two], verbose=True)

from langchain.chains.sequential import SequentialChain
from langchain_community.chat_models import ChatOpenAI    #导入OpenAI模型
from langchain.prompts import ChatPromptTemplate   #导入聊天提示模板
from langchain.chains.llm import LLMChain    #导入LLM链。

llm = ChatOpenAI(temperature=0.9)

#子链1

# prompt模板 1: 翻译成英语（把下面的review翻译成英语）
first_prompt = ChatPromptTemplate.from_template(
    "Translate the following review to english:"
    "\n\n{Review}"
)
# chain 1: 输入：Review 输出： 英文的 Review
chain_one = LLMChain(llm=llm, prompt=first_prompt, output_key="English_Review")

#子链2

# prompt模板 2: 用一句话总结下面的 review
second_prompt = ChatPromptTemplate.from_template(
    "Can you summarize the following review in 1 sentence:"
    "\n\n{English_Review}"
)
# chain 2: 输入：英文的Review   输出：总结
chain_two = LLMChain(llm=llm, prompt=second_prompt, output_key="summary")

#子链3

# prompt模板 3: 下面review使用的什么语言
third_prompt = ChatPromptTemplate.from_template(
    "What language is the following review:\n\n{Review}"
)
# chain 3: 输入：Review  输出：语言
chain_three = LLMChain(llm=llm, prompt=third_prompt, output_key="language")

#子链4

# prompt模板 4: 使用特定的语言对下面的总结写一个后续回复
fourth_prompt = ChatPromptTemplate.from_template(
    "Write a follow up response to the following "
    "summary in the specified language:"
    "\n\nSummary: {summary}\n\nLanguage: {language}"
)
# chain 4: 输入： 总结, 语言    输出： 后续回复
chain_four = LLMChain(llm=llm, prompt=fourth_prompt, output_key="followup_message")

#输入：review    
#输出：英文review，总结，后续回复 
overall_chain = SequentialChain(
    chains=[chain_one, chain_two, chain_three, chain_four],
    input_variables=["Review"],
    output_variables=["English_Review", "summary","followup_message"],
    verbose=True
)

from langchain.chains.router import MultiPromptChain  #导入多提示链
from langchain.chains.router.llm_router import LLMRouterChain,RouterOutputParser
from langchain.prompts import PromptTemplate

llm = ChatOpenAI(model='gpt-4o', temperature=0)

#第一个提示适合回答物理问题
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}"""


#第二个提示适合回答数学问题
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}"""


#第三个适合回答历史问题
history_template = """You are a very good historian. \
You have an excellent knowledge of and understanding of people,\
events and contexts from a range of historical periods. \
You have the ability to think, reflect, debate, discuss and \
evaluate the past. You have a respect for historical evidence\
and the ability to make use of it to support your explanations \
and judgements.

Here is a question:
{input}"""


#第四个适合回答计算机问题
computerscience_template = """ You are a successful computer scientist.\
You have a passion for creativity, collaboration,\
forward-thinking, confidence, strong problem-solving capabilities,\
understanding of theories and algorithms, and excellent communication \
skills. You are great at answering coding questions. \
You are so good because you know how to solve a problem by \
describing the solution in imperative steps \
that a machine can easily interpret and you know how to \
choose a solution that has a good balance between \
time complexity and space complexity. 

Here is a question:
{input}"""

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
    },
    {
        "name": "History", 
        "description": "Good for answering history questions", 
        "prompt_template": history_template
    },
    {
        "name": "computer science", 
        "description": "Good for answering computer science questions", 
        "prompt_template": computerscience_template
    }
]

destination_chains = {}
for p_info in prompt_infos:
    name = p_info["name"]
    prompt_template = p_info["prompt_template"]
    prompt = ChatPromptTemplate.from_template(template=prompt_template)
    chain = LLMChain(llm=llm, prompt=prompt)
    destination_chains[name] = chain  
    
destinations = [f"{p['name']}: {p['description']}" for p in prompt_infos]
destinations_str = "\n".join(destinations)

default_prompt = ChatPromptTemplate.from_template("{input}")
default_chain = LLMChain(llm=llm, prompt=default_prompt)

MULTI_PROMPT_ROUTER_TEMPLATE = """Given a raw text input to a \
language model select the model prompt best suited for the input. \
You will be given the names of the available prompts and a \
description of what the prompt is best suited for. \
You may also revise the original input if you think that revising\
it will ultimately lead to a better response from the language model.

<< FORMATTING >>
Return a markdown code snippet with a JSON object formatted to look like:
```json
{{{{
    "destination": string \ name of the prompt to use or "DEFAULT"
    "next_inputs": string \ a potentially modified version of the original input
}}}}
```

REMEMBER: "destination" MUST be one of the candidate prompt \
names specified below OR it can be "DEFAULT" if the input is not\
well suited for any of the candidate prompts.
REMEMBER: "next_inputs" can just be the original input \
if you don't think any modifications are needed.

<< CANDIDATE PROMPTS >>
{destinations}

<< INPUT >>
{{input}}

<< OUTPUT (remember to include the ```json)>>

eg:
<< INPUT >>
"What is black body radiation?"
<< OUTPUT >>
```json
{{{{
    "destination": string \ name of the prompt to use or "DEFAULT"
    "next_inputs": string \ a potentially modified version of the original input
}}}}
```

"""

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)

#多提示链
chain = MultiPromptChain(router_chain=router_chain,    #l路由链路
                         destination_chains=destination_chains,   #目标链路
                         default_chain=default_chain,      #默认链路
                         verbose=True   
                        )

# 中文
#第一个提示适合回答物理问题
physics_template = """你是一个非常聪明的物理专家。 \
你擅长用一种简洁并且易于理解的方式去回答问题。\
当你不知道问题的答案时，你承认\
你不知道.

这是一个问题:
{input}"""


#第二个提示适合回答数学问题
math_template = """你是一个非常优秀的数学家。 \
你擅长回答数学问题。 \
你之所以如此优秀， \
是因为你能够将棘手的问题分解为组成部分，\
回答组成部分，然后将它们组合在一起，回答更广泛的问题。

这是一个问题：
{input}"""


#第三个适合回答历史问题
history_template = """你是以为非常优秀的历史学家。 \
你对一系列历史时期的人物、事件和背景有着极好的学识和理解\
你有能力思考、反思、辩证、讨论和评估过去。\
你尊重历史证据，并有能力利用它来支持你的解释和判断。

这是一个问题:
{input}"""


#第四个适合回答计算机问题
computerscience_template = """ 你是一个成功的计算机科学专家。\
你有创造力、协作精神、\
前瞻性思维、自信、解决问题的能力、\
对理论和算法的理解以及出色的沟通技巧。\
你非常擅长回答编程问题。\
你之所以如此优秀，是因为你知道  \
如何通过以机器可以轻松解释的命令式步骤描述解决方案来解决问题，\
并且你知道如何选择在时间复杂性和空间复杂性之间取得良好平衡的解决方案。

这还是一个输入：
{input}"""

# 中文
prompt_infos = [
    {
        "名字": "物理学", 
        "描述": "擅长回答关于物理学的问题", 
        "提示模板": physics_template
    },
    {
        "名字": "数学", 
        "描述": "擅长回答数学问题", 
        "提示模板": math_template
    },
    {
        "名字": "历史", 
        "描述": "擅长回答历史问题", 
        "提示模板": history_template
    },
    {
        "名字": "计算机科学", 
        "描述": "擅长回答计算机科学问题", 
        "提示模板": computerscience_template
    }
]

# 中文
destination_chains = {}
for p_info in prompt_infos:
    name = p_info["名字"]
    prompt_template = p_info["提示模板"]
    prompt = ChatPromptTemplate.from_template(template=prompt_template)
    chain = LLMChain(llm=llm, prompt=prompt)
    destination_chains[name] = chain  
    
destinations = [f"{p['名字']}: {p['描述']}" for p in prompt_infos]
destinations_str = "\n".join(destinations)

default_prompt = ChatPromptTemplate.from_template("{input}")
default_chain = LLMChain(llm=llm, prompt=default_prompt)

# 中文

# 多提示路由模板
MULTI_PROMPT_ROUTER_TEMPLATE = """给语言模型一个原始文本输入，\
让其选择最适合输入的模型提示。\
系统将为您提供可用提示的名称以及最适合改提示的描述。\
如果你认为修改原始输入最终会导致语言模型做出更好的响应，\
你也可以修改原始输入。


<< 格式 >>
返回一个带有JSON对象的markdown代码片段，该JSON对象的格式如下：
```json
{{{{
    "destination": 字符串 \ 使用的提示名字或者使用 "DEFAULT"
    "next_inputs": 字符串 \ 原始输入的改进版本
}}}}
```


记住：“destination”必须是下面指定的候选提示名称之一，\
或者如果输入不太适合任何候选提示，\
则可以是 “DEFAULT” 。
记住：如果您认为不需要任何修改，\
则 “next_inputs” 可以只是原始输入。

<< 候选提示 >>
{destinations}

<< 输入 >>
{{input}}

<< 输出 (记得要包含 ```json)>>

样例:
<< 输入 >>
"什么是黑体辐射?"
<< 输出 >>
```json
{{{{
    "destination": 字符串 \ 使用的提示名字或者使用 "DEFAULT"
    "next_inputs": 字符串 \ 原始输入的改进版本
}}}}
```

"""

# 中文
# 创建路由链

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)

#多提示链
chain = MultiPromptChain(router_chain=router_chain,    #l路由链路
                         destination_chains=destination_chains,   #目标链路
                         default_chain=default_chain,      #默认链路
                         verbose=True   
                        )