有没有专做自驾游的网站,大庆市网站建设公司,有什么平台可以接加工单,北京大学两学一做网站分类目录#xff1a;《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#xff08;如果有的话#xff0c;还包括内存键值#xff09;格式化提示模板#xff0c;将格式化的字符串传递给LLM#xff0c;并返回LLM…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
from langchain import PromptTemplate, OpenAI, LLMChainprompt_template What is a good name for a company that makes {product}?llm OpenAI(temperature0)
llm_chain LLMChain(llmllm,promptPromptTemplate.from_template(prompt_template)
)
llm_chain(colorful socks)输出
{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
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。
llm_chain.generate(input_list)输出
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。
# Single input example
llm_chain.predict(productcolorful socks)输出
\n\nSocktastic!输入
# Multiple inputs exampletemplate Tell me a {adjective} joke about {subject}.
prompt PromptTemplate(templatetemplate, input_variables[adjective, subject])
llm_chain LLMChain(promptprompt, llmOpenAI(temperature0))llm_chain.predict(adjectivesad, subjectducks)输出
\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
from langchain.output_parsers import CommaSeparatedListOutputParseroutput_parser CommaSeparatedListOutputParser()
template List all the colors in a rainbow
prompt PromptTemplate(templatetemplate, input_variables[], output_parseroutput_parser)
llm_chain LLMChain(promptprompt, llmllm)llm_chain.predict()输出
\n\nRed, orange, yellow, green, blue, indigo, violet使用predict_and_parser方法
llm_chain.predict_and_parse()输出
[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。
template Tell me a {adjective} joke about {subject}.
llm_chain LLMChain.from_string(llmllm, templatetemplate)
llm_chain.predict(adjectivesad, subjectducks)输出
\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。
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 dont know the answer to a question you admit that you dont 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(templateprompt_template, input_variables[input])chain LLMChain(llmllm, promptprompt)destination_chains[name] chain
default_chain ConversationChain(llmllm, output_keytext)LLMRouterChain
LLMRouterChain链条使用一个LLM来确定如何进行路由。
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(destinationsdestinations_str
)
router_prompt PromptTemplate(templaterouter_template,input_variables[input],output_parserRouterOutputParser(),
)
router_chain LLMRouterChain.from_llm(llm, router_prompt)
chain MultiPromptChain(router_chainrouter_chain, destination_chainsdestination_chains, default_chaindefault_chain, verboseTrue)
print(chain.run(What is black body radiation?))日志输出 Entering new MultiPromptChain chain...
physics: {input: What is black body radiation?}Finished chain.输出
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 bodys atoms and molecules, and it is emitted at all wavelengths. The spectrum of radiation emitted is described by Plancks law and is known as the black body spectrum.输入
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 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
The answer is 43. One plus 43 is 44 which is divisible by 3.输入
print(chain.run(What is the name of the type of cloud that rins))日志输出 Entering new MultiPromptChain chain...
None: {input: What is the name of the type of cloud that rains?}Finished chain.输出
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。
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_chainrouter_chain, destination_chainsdestination_chains, default_chaindefault_chain, verboseTrue)
print(chain.run(What is black body radiation?))日志输出 Entering new MultiPromptChain chain...
physics: {input: What is black body radiation?}Finished chain.输出
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
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 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
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/
