Șabloane de prompturi

Developing LLM Applications with LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Șabloane de prompturi

Rețete pentru definirea prompturilor pentru LLM-uri
Pot conține: instrucțiuni, exemple și context suplimentar

Un șablon de prompt cu substituenți pentru variabile de intrare.

Șabloane de prompturi

from langchain_core.prompts import PromptTemplate


template = "Expain this concept simply and concisely: {concept}"

prompt_template = PromptTemplate.from_template(
    template=template
)


prompt = prompt_template.invoke({"concept": "Prompting LLMs"})
print(prompt)

text='Expain this concept simply and concisely: Prompting LLMs'

llm = HuggingFacePipeline.from_model_id(
    model_id="meta-llama/Llama-3.3-70B-Instruct",
    task="text-generation"
)

llm_chain = prompt_template | llm


concept = "Prompting LLMs"
print(llm_chain.invoke({"concept": concept}))

Prompting LLMs (Large Language Models) refers to the process of giving a model a
specific input or question to generate a response.

LangChain Expression Language (LCEL): operatorul | (pipe)
Lanț: conectează apeluri către diferite componente

Modele de chat

Roluri de chat: system, human, ai

from langchain_core.prompts import ChatPromptTemplate


template = ChatPromptTemplate.from_messages(
    [
        ("system", "You are a calculator that responds with math."),
        ("human", "Answer this math question: What is two plus two?"),
        ("ai", "2+2=4"),
        ("human", "Answer this math question: {math}")
    ]
)

Integrarea ChatPromptTemplate

llm = ChatOpenAI(model="gpt-4o-mini", api_key='<OPENAI_API_TOKEN>')


llm_chain = template | llm

math='What is five times five?'


response = llm_chain.invoke({"math": math})
print(response.content)

5x5=25

Să exersăm!

Developing LLM Applications with LangChain