我为什么放弃了 LangChain？( 二 ) _人工智能

response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=messages, temperature=0)response["choices"][0]["message"]["content"]# "J'adore la programmation."
使用的代码量与仅使用官方库的代码量大致相同，估计合并了更多对象类，但代码优势并不明显。
提示模板的示例揭示了工作原理的核心：
from langchain.prompts.chat import (ChatPromptTemplate,SystemMessagePromptTemplate,HumanMessagePromptTemplate,)template = "You are a helpful assistant that translates {input_language} to {output_language}."system_message_prompt = SystemMessagePromptTemplate.from_template(template)human_template = "{text}"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])chat_prompt.format_messages(input_language="English", output_language="French", text="I love programming.")
吹嘘的提示工程只是 f-，一个存在于每个安装中的功能，但是有额外的步骤。为什么我们需要使用这些来做同样的事情呢？
我们真正想做的是知道如何创建 Agent，它结合了我们迫切想要的 ReAct 工作流。幸运的是，有一个演示，它利用了和另一个数学计算工具，展示了如何区分和使用两种不同的工具：
from langchain.agents import load_toolsfrom langchain.agents import initialize_agentfrom langchain.agents import AgentTypefrom langchain.chat_models import ChatOpenAIfrom langchain.llms import OpenAI# First, let's load the language model we're going to use to control the agent.chat = ChatOpenAI(temperature=0)# Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in.llm = OpenAI(temperature=0)tools = load_tools(["serpapi", "llm-math"], llm=llm)# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.agent = initialize_agent(tools, chat, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)# Now let's test it out!agent.run("Who is Olivia Wilde's boyfriend? What is his current age raised to the 0.23 power?")
各个工具如何工作？. 到底是什么？agent.run () 的结果输出（仅在 =True 时出现）更有帮助。
> Entering new AgentExecutor chain...Thought: I need to use a search engine to find Olivia Wilde's boyfriend and a calculator to raise his age to the 0.23 power.Action:{"action": "Search","action_input": "Olivia Wilde boyfriend"}Observation: Sudeikis and Wilde's relationship ended in November 2020. Wilde was publicly served with court documents regarding child custody while she was presenting Don't Worry Darling at CinemaCon 2022. In January 2021, Wilde began dating singer Harry Styles after meeting during the filming of Don't Worry Darling.Thought:I need to use a search engine to find Harry Styles' current age.Action:{"action": "Search","action_input": "Harry Styles age"}Observation: 29 yearsThought:Now I need to calculate 29 raised to the 0.23 power.Action:{"action": "Calculator","action_input": "29^0.23"}Observation: Answer: 2.169459462491557Thought:I now know the final answer.Final Answer: 2.169459462491557> Finished chain.'2.169459462491557'
文档中没有明确说明，但是在每个思想 / 行动 / 观察中都使用了自己的 API 调用，所以链条比你想象的要慢。另外，为什么每个动作都是一个 dict？答案在后面，而且非常愚蠢。