Prompt-sjablonen

LLM-toepassingen ontwikkelen met LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Prompt-sjablonen

Recepten om prompts voor LLM’s te definiëren
Kunnen bevatten: instructies, voorbeelden en extra context

Een promptsjabloon met placeholders voor invoervariabelen.

Prompt-sjablonen

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): | (pipe)-operator
Chain: koppel aanroepen van verschillende componenten

Chatmodellen

Chatrollen: 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}")
    ]
)

ChatPromptTemplate integreren

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

Laten we oefenen!

LLM-toepassingen ontwikkelen met LangChain