自然语言处理从入门到应用——LangChain：链（Chains）-[通用功能：LLMChain、RouterChain和SequentialChain]

von Neumann2023-08-22 9:46

分类目录：《自然语言处理从入门到应用》总目录

LLMChain

LLMChain是查询LLM对象最流行的方式之一。它使用提供的输入键值（如果有的话，还包括内存键值）格式化提示模板，将格式化的字符串传递给LLM，并返回LLM的输出。下面我们展示了LLMChain类的附加功能：

csharp 复制代码 
from langchain import PromptTemplate, OpenAI, LLMChain

prompt_template = "What is a good name for a company that makes {product}?"

llm = OpenAI(temperature=0)
llm_chain = LLMChain(
    llm=llm,
    prompt=PromptTemplate.from_template(prompt_template)
)
llm_chain("colorful socks")

输出：

复制代码 
{'product': 'colorful socks', 'text': '\n\nSocktastic!'}
LLM链条的额外运行方式

除了所有Chain对象共享的__call__和run方法之外，LLMChain还提供了几种调用链条逻辑的方式：

  • apply：允许我们对一组输入运行链：
csharp 复制代码 
input_list = [
    {"product": "socks"},
    {"product": "computer"},
    {"product": "shoes"}
]

llm_chain.apply(input_list)
[{'text': '\n\nSocktastic!'},
 {'text': '\n\nTechCore Solutions.'},
 {'text': '\n\nFootwear Factory.'}]
  • generate：与apply类似，但返回一个LLMResult而不是字符串。LLMResult通常包含有用的生成信息，例如令牌使用情况和完成原因。
csharp 复制代码 
llm_chain.generate(input_list)

输出：

复制代码 
LLMResult(generations=[[Generation(text='\n\nSocktastic!', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\n\nTechCore Solutions.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\n\nFootwear Factory.', generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'prompt_tokens': 36, 'total_tokens': 55, 'completion_tokens': 19}, 'model_name': 'text-davinci-003'})
  • predict：与run方法类似，只是输入键被指定为关键字参数，而不是Python字典。
csharp 复制代码 
# Single input example
llm_chain.predict(product="colorful socks")

输出：

复制代码 
'\n\nSocktastic!'

输入：

复制代码 
# Multiple inputs example

template = """Tell me a {adjective} joke about {subject}."""
prompt = PromptTemplate(template=template, input_variables=["adjective", "subject"])
llm_chain = LLMChain(prompt=prompt, llm=OpenAI(temperature=0))

llm_chain.predict(adjective="sad", subject="ducks")

输出：

复制代码 
'\n\nQ: What did the duck say when his friend died?\nA: Quack, quack, goodbye.'
解析输出结果

默认情况下，即使底层的prompt对象具有输出解析器，LLMChain也不会解析输出结果。如果你想在LLM输出上应用输出解析器，可以使用predict_and_parse代替predict，以及apply_and_parse代替apply。

仅使用predict方法：

csharp 复制代码 
from langchain.output_parsers import CommaSeparatedListOutputParser

output_parser = CommaSeparatedListOutputParser()
template = """List all the colors in a rainbow"""
prompt = PromptTemplate(template=template, input_variables=[], output_parser=output_parser)
llm_chain = LLMChain(prompt=prompt, llm=llm)

llm_chain.predict()

输出：

复制代码 
'\n\nRed, orange, yellow, green, blue, indigo, violet'

使用predict_and_parser方法：

csharp 复制代码 
llm_chain.predict_and_parse()

输出：

复制代码 
['Red', 'orange', 'yellow', 'green', 'blue', 'indigo', 'violet']
从字符串模板初始化

我们还可以直接使用字符串模板构建一个LLMChain。

csharp 复制代码 
template = """Tell me a {adjective} joke about {subject}."""
llm_chain = LLMChain.from_string(llm=llm, template=template)
llm_chain.predict(adjective="sad", subject="ducks")

输出：

复制代码 
'\n\nQ: What did the duck say when his friend died?\nA: Quack, quack, goodbye.'

RouterChain

本节演示了如何使用RouterChain创建一个根据给定输入动态选择下一个链条的链条。RouterChain通常由两个组件组成：

  • 路由链本身（负责选择下一个要调用的链条）
  • 目标链条，即路由链可以路由到的链条

本节中，我们将重点介绍不同类型的路由链。我们将展示这些路由链在MultiPromptChain中的应用，创建一个问题回答链条，根据给定的问题选择最相关的提示，然后使用该提示回答问题。

csharp 复制代码 
from langchain.chains.router import MultiPromptChain
from langchain.llms import OpenAI
from langchain.chains import ConversationChain
from langchain.chains.llm import LLMChain
from langchain.prompts import PromptTemplate
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}"""
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
    }
]
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")
LLMRouterChain

LLMRouterChain链条使用一个LLM来确定如何进行路由。

csharp 复制代码 
from langchain.chains.router.llm_router import LLMRouterChain, RouterOutputParser
from langchain.chains.router.multi_prompt_prompt import MULTI_PROMPT_ROUTER_TEMPLATE
destinations = [f"{p['name']}: {p['description']}" for p in prompt_infos]
destinations_str = "\n".join(destinations)
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("What is black body radiation?"))

日志输出：

复制代码 
> Entering new MultiPromptChain chain...
physics: {'input': 'What is black body radiation?'}
> Finished chain.

输出：

复制代码 
Black body radiation is the term used to describe the electromagnetic radiation emitted by a "black body"---an object that absorbs all radiation incident upon it. A black body is an idealized physical body that absorbs all incident electromagnetic radiation, regardless of frequency or angle of incidence. It does not reflect, emit or transmit energy. This type of radiation is the result of the thermal motion of the body's atoms and molecules, and it is emitted at all wavelengths. The spectrum of radiation emitted is described by Planck's law and is known as the black body spectrum.

输入：

复制代码 
print(chain.run("What is the first prime number greater than 40 such that one plus the prime number is divisible by 3"))

输出：

复制代码 
> Entering new MultiPromptChain chain...
math: {'input': 'What is the first prime number greater than 40 such that one plus the prime number is divisible by 3'}
> Finished chain.

输出：

复制代码 
The answer is 43. One plus 43 is 44 which is divisible by 3.

输入：

复制代码 
print(chain.run("What is the name of the type of cloud that rins"))

日志输出：

复制代码 
> Entering new MultiPromptChain chain...
None: {'input': 'What is the name of the type of cloud that rains?'}
> Finished chain.

输出：

复制代码 
The type of cloud that rains is called a cumulonimbus cloud. It is a tall and dense cloud that is often accompanied by thunder and lightning.
EmbeddingRouterChain

EmbeddingRouterChain使用嵌入和相似性来在目标链条之间进行路由。

csharp 复制代码 
from langchain.chains.router.embedding_router import EmbeddingRouterChain
from langchain.embeddings import CohereEmbeddings
from langchain.vectorstores import Chroma
names_and_descriptions = [
    ("physics", ["for questions about physics"]),
    ("math", ["for questions about math"]),
]
router_chain = EmbeddingRouterChain.from_names_and_descriptions(
    names_and_descriptions, Chroma, CohereEmbeddings(), routing_keys=["input"]
)
chain = MultiPromptChain(router_chain=router_chain, destination_chains=destination_chains, default_chain=default_chain, verbose=True)
print(chain.run("What is black body radiation?"))

日志输出：

复制代码 
> Entering new MultiPromptChain chain...
physics: {'input': 'What is black body radiation?'}
> Finished chain.

输出：

复制代码 
Black body radiation is the emission of energy from an idealized physical body (known as a black body) that is in thermal equilibrium with its environment. It is emitted in a characteristic pattern of frequencies known as a black-body spectrum, which depends only on the temperature of the body. The study of black body radiation is an important part of astrophysics and atmospheric physics, as the thermal radiation emitted by stars and planets can often be approximated as black body radiation.

输入：

复制代码 
print(chain.run("What is the first prime number greater than 40 such that one plus the prime number is divisible by 3"))

日志输出：

复制代码 
> Entering new MultiPromptChain chain...
math: {'input': 'What is the first prime number greater than 40 such that one plus the prime number is divisible by 3'}
> Finished chain.

输出：

复制代码 
Answer: The first prime number greater than 40 such that one plus the prime number is divisible by 3 is 43.

参考文献：

1\] LangChain官方网站：https://www.langchain.com/ \[2\] LangChain 🦜️🔗 中文网，跟着LangChain一起学LLM/GPT开发：https://www.langchain.com.cn/ \[3\] LangChain中文网 - LangChain 是一个用于开发由语言模型驱动的应用程序的框架：http://www.cnlangchain.com/

相关推荐
且慢.5895 分钟前
Python_day47
python·深度学习·计算机视觉
大写-凌祁22 分钟前
论文阅读：HySCDG生成式数据处理流程
论文阅读·人工智能·笔记·python·机器学习
柯南二号33 分钟前
深入理解 Agent 与 LLM 的区别：从智能体到语言模型
人工智能·机器学习·llm·agent
珂朵莉MM34 分钟前
2021 RoboCom 世界机器人开发者大赛-高职组（初赛）解题报告 | 珂学家
java·开发语言·人工智能·算法·职场和发展·机器人
爱喝喜茶爱吃烤冷面的小黑黑1 小时前
小黑一层层削苹果皮式大模型应用探索：langchain中智能体思考和执行工具的demo
python·langchain·代理模式
IT_陈寒1 小时前
Element Plus 2.10.0 重磅发布！新增Splitter组件
前端·人工智能·后端
jndingxin1 小时前
OpenCV CUDA模块图像处理------创建一个模板匹配（Template Matching）对象函数createTemplateMatching()
图像处理·人工智能·opencv
&永恒的星河&1 小时前
基于TarNet、CFRNet与DragonNet的深度因果推断模型全解析
深度学习·因果推断·cfrnet·tarnet·dragonnet
盛寒1 小时前
N元语言模型 —— 一文讲懂！！！
人工智能·语言模型·自然语言处理
weixin_177297220691 小时前
家政小程序开发——AI+IoT技术融合，打造“智慧家政”新物种
人工智能·物联网
热门推荐
01海康Visionmaster-常见问题排查方法-启动阶段02KGG转MP3工具|非KGM文件|解密音频03YOLOv8入门 | 重要性能衡量指标、训练结果评价及分析及影响mAP的因素【发论文关注的指标】04Coze扣子平台完整体验和实践（附国内和国际版对比）05从零安装 LLaMA-Factory 微调 Qwen 大模型成功及所有的坑06【SpeedAI科研小助手】2分钟极速解决知网维普重复率、AIGC率过高，一键全文降！文件格式不变，公式都保留的！07CCF CSP 认证考试历年真题满分题解（所有前四题）08DeepSeek各版本说明与优缺点分析09VMware虚拟机安装Win7专业版保姆级教程（附镜像包）10【无人机】无人机通信模块，无人机图数传模块的介绍，数传，图传，图传数传一体电台，