# 導(dǎo)入LLM包裝器
from langchain import OpenAI, ConversationChain
from langchain.agents import initialize_agent
from langchain.agents import load_tools
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate

LLM：從語言模型中輸出預(yù)測結(jié)果，和直接使用OpenAI的接口一樣，輸入什么就返回什么。

llm = OpenAI(model_name="text-davinci-003", temperature=0.9) // 這些都是OpenAI的參數(shù)
text = "What would be a good company name for a company that makes colorful socks?"
print(llm(text)) 
// 以上就是打印調(diào)用OpenAI接口的返回值，相當(dāng)于接口的封裝，實現(xiàn)的代碼可以看看github.com/hwchase17/langchain/llms/openai.py的OpenAIChat

以上代碼運行結(jié)果：

Cozy Colours Socks.

Prompt Templates：管理LLMs的Prompts，就像我們需要管理變量或者模板一樣。

prompt = PromptTemplate(
    input_variables=["product"],
    template="What is a good name for a company that makes {product}?",
)
// 以上是兩個參數(shù)，一個輸入變量，一個模板字符串，實現(xiàn)的代碼可以看看github.com/hwchase17/langchain/prompts
// PromptTemplate實際是基于StringPromptTemplate，可以支持字符串類型的模板，也可以支持文件類型的模板

以上代碼運行結(jié)果：

What is a good name for a company that makes colorful socks?

Chains：將LLMs和prompts結(jié)合起來，前面提到提供了OpenAI的封裝和你需要問的字符串模板，就可以執(zhí)行獲得返回了。

from langchain.chains import LLMChain
chain = LLMChain(llm=llm, prompt=prompt) // 通過LLM的llm變量，Prompt Templates的prompt生成LLMChain
chain.run("colorful socks") // 實際這里就變成了實際問題：What is a good name for a company that makes colorful socks？

Agents：基于用戶輸入動態(tài)地調(diào)用chains，LangChani可以將問題拆分為幾個步驟，然后每個步驟可以根據(jù)提供個Agents做相關(guān)的事情。

# 導(dǎo)入一些tools，比如llm-math
# llm-math是langchain里面的能做數(shù)學(xué)計算的模塊
tools = load_tools(["llm-math"], llm=llm)
# 初始化tools，models 和使用的agent
agent = initialize_agent(
    tools, llm, agent="zero-shot-react-description", verbose=True)
text = "12 raised to the 3 power and result raised to 2 power?"
print("input text: ", text)
agent.run(text)

通過如上的代碼，運行結(jié)果（拆分為兩個部分）：

> Entering new AgentExecutor chain...
 I need to use the calculator for this
Action: Calculator
Action Input: 12^3
Observation: Answer: 1728
Thought: I need to then raise the previous result to the second power
Action: Calculator
Action Input: 1728^2
Observation: Answer: 2985984
Thought: I now know the final answer
Final Answer: 2985984
> Finished chain.

Memory：就是提供對話的上下文存儲，可以使用Langchain的ConversationChain，在LLM交互中記錄交互的歷史狀態(tài)，并基于歷史狀態(tài)修正模型預(yù)測。

# ConversationChain用法
llm = OpenAI(temperature=0)
# 將verbose設(shè)置為True，以便我們可以看到提示
conversation = ConversationChain(llm=llm, verbose=True)
print("input text: conversation")
conversation.predict(input="Hi there!")
conversation.predict(
  input="I'm doing well! Just having a conversation with an AI.")

通過多輪運行以后，就會出現(xiàn)：

Prompt after formatting:
The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.
Current conversation:
Human: Hi there!
AI: Hi there! It's nice to meet you. How can I help you today?
Human: I'm doing well! Just having a conversation with an AI.
AI: That's great! It's always nice to have a conversation with someone new. What would you like to talk about?

具體代碼

如下：

# 導(dǎo)入LLM包裝器
from langchain import OpenAI, ConversationChain
from langchain.agents import initialize_agent
from langchain.agents import load_tools
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
# 初始化包裝器，temperature越高結(jié)果越隨機
llm = OpenAI(temperature=0.9)
# 進行調(diào)用
text = "What would be a good company name for a company that makes colorful socks?"
print("input text: ", text)
print(llm(text))
prompt = PromptTemplate(
  input_variables=["product"],
  template="What is a good name for a company that makes {product}?",
)
print("input text: product")
print(prompt.format(product="colorful socks"))
chain = LLMChain(llm=llm, prompt=prompt)
chain.run("colorful socks")
# 導(dǎo)入一些tools，比如llm-math
# llm-math是langchain里面的能做數(shù)學(xué)計算的模塊
tools = load_tools(["llm-math"], llm=llm)
# 初始化tools，models 和使用的agent
agent = initialize_agent(tools,
                         llm,
                         agent="zero-shot-react-description",
                         verbose=True)
text = "12 raised to the 3 power and result raised to 2 power?"
print("input text: ", text)
agent.run(text)
# ConversationChain用法
llm = OpenAI(temperature=0)
# 將verbose設(shè)置為True，以便我們可以看到提示
conversation = ConversationChain(llm=llm, verbose=True)
print("input text: conversation")
conversation.predict(input="Hi there!")
conversation.predict(
  input="I'm doing well! Just having a conversation with an AI.")

參考資料

note.com/npaka/n/n15…

http://www.dbjr.com.cn/article/279343.htm

github.com/hwchase17/l…

以上就是LangChain簡化ChatGPT工程復(fù)雜度使用詳解的詳細(xì)內(nèi)容，更多關(guān)于LangChain簡化ChatGPT的資料請關(guān)注腳本之家其它相關(guān)文章！

您可能感興趣的文章: