上饶网站建设,扬中网站设计公司,北京网站建设外包公司哪家好,基于html5的电商网站开发分类目录#xff1a;《自然语言处理从入门到应用》总目录 本文将介绍如何创建自己的自定义MRKL Agent。MRKL Agent由三个部分组成#xff1a;
工具#xff1a;代理可用的工具。LLMChain#xff1a;生成以一定方式解析的文本#xff0c;以确定要采取哪个动作。代理类本身《自然语言处理从入门到应用》总目录 本文将介绍如何创建自己的自定义MRKL Agent。MRKL Agent由三个部分组成
工具代理可用的工具。LLMChain生成以一定方式解析的文本以确定要采取哪个动作。代理类本身解析LLMChain的输出以确定要采取哪个动作。
自定义LLMChainCustom LLMChain
本部分将介绍如何通过创建自定义LLMChain来创建自定义MRKL代理。创建自定义代理的第一种方法是使用现有的代理类但使用自定义LLMCain。这也是创建自定义代理的最简单方法。强烈建议使用ZeroShotAgent 因为目前这是最通用的一个。
创建自定义LLMCain的大部分工作都归结为提示符。因为我们使用的是一个现有的代理类来解析输出所以提示符中要生成该格式的文本是非常重要的。此外我们目前需要一个agent_scratchpad输入变量来记录以前的操作和观察结果这几乎总是提示符的最后一部分。但是除了这些说明之外我们还可以根据需要自定义提示。为了确保提示符包含适当的指令我们将在该类上使用helper方法。ZeroShotAgent的helper方法接受以下参数
tools座席将有权访问的工具列表用于设置提示的格式。prefix要放在工具列表前面的字符串。suffix放在工具列表后面的字符串。input_variables最后提示所期望的输入变量列表。
在下面的示例中我们将给予我们的代理访问Google搜索我们将定制它我们将让它回答为盗版。
from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
from langchain import OpenAI, SerpAPIWrapper, LLMChainsearch SerpAPIWrapper()
tools [Tool(name Search,funcsearch.run,descriptionuseful for when you need to answer questions about current events)
]prefix Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:
suffix Begin! Remember to speak as a pirate when giving your final answer. Use lots of ArgsQuestion: {input}
{agent_scratchpad}prompt ZeroShotAgent.create_prompt(tools, prefixprefix, suffixsuffix, input_variables[input, agent_scratchpad]
)如果感到好奇我们现在可以看看最终的提示模板看看它看起来像当它的所有放在一起
print(prompt.template)输出
Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:Search: useful for when you need to answer questions about current eventsUse the following format:Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [Search]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input questionBegin! Remember to speak as a pirate when giving your final answer. Use lots of ArgsQuestion: {input}
{agent_scratchpad}需要注意的是我们能够为代理提供自定义的提示模板即不限于由create_prompt函数生成的提示假设它满足代理的要求。例如对于ZeroShotAgent我们需要确保它应该有一个以Action:开头的字符串和一个以Action Input:开头的字符串并且两者都应该用换行符分隔。
llm_chain LLMChain(llmOpenAI(temperature0), promptprompt)tool_names [tool.name for tool in tools]
agent ZeroShotAgent(llm_chainllm_chain, allowed_toolstool_names)agent_executor AgentExecutor.from_agent_and_tools(agentagent, toolstools, verboseTrue)agent_executor.run(How many people live in canada as of 2023?)输出 Entering new AgentExecutor chain...
Thought: I need to find out the population of Canada
Action: Search
Action Input: Population of Canada 2023
Observation: The current population of Canada is 38,661,927 as of Sunday, April 16, 2023, based on Worldometer elaboration of the latest United Nations data.
Thought: I now know the final answer
Final Answer: Arrr, Canada be havin 38,661,927 people livin there as of 2023! Finished chain.Arrr, Canada be havin 38,661,927 people livin there as of 2023!多路输入 (Multiple Inputs
代理还可以处理需要多个输入的提示
prefix Answer the following questions as best you can. You have access to the following tools:
suffix When answering, you MUST speak in the following language: {language}.Question: {input}
{agent_scratchpad}prompt ZeroShotAgent.create_prompt(tools, prefixprefix, suffixsuffix, input_variables[input, language, agent_scratchpad]
)llm_chain LLMChain(llmOpenAI(temperature0), promptprompt)agent ZeroShotAgent(llm_chainllm_chain, toolstools)agent_executor AgentExecutor.from_agent_and_tools(agentagent, toolstools, verboseTrue)agent_executor.run(inputHow many people live in canada as of 2023?, languageitalian)输出 Entering new AgentExecutor chain...
Thought: I should look for recent population estimates.
Action: Search
Action Input: Canada population 2023
Observation: 39,566,248
Thought: I should double check this number.
Action: Search
Action Input: Canada population estimates 2023
Observation: Canadas population was estimated at 39,566,248 on January 1, 2023, after a record population growth of 1,050,110 people from January 1, 2022, to January 1, 2023.
Thought: I now know the final answer.
Final Answer: La popolazione del Canada è stata stimata a 39.566.248 il 1° gennaio 2023, dopo un record di crescita demografica di 1.050.110 persone dal 1° gennaio 2022 al 1° gennaio 2023. Finished chain.La popolazione del Canada è stata stimata a 39.566.248 il 1° gennaio 2023, dopo un record di crescita demografica di 1.050.110 persone dal 1° gennaio 2022 al 1° gennaio 2023.参考文献 [1] LangChain ️ 中文网跟着LangChain一起学LLM/GPT开发https://www.langchain.com.cn/ [2] 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/
