Few-shot prompting

Developing LLM Applications with LangChain

Jonathan Bennion

AI Engineer & LangChain Contributor

Limitations of standard prompt templates

PromptTemplate + ChatPromptTemplate
✅ Handling small numbers of examples
❌ Don't scale for many examples
FewShotPromptTemplate

examples = [
    {
        "question": "..."
        "answer": "..."
    },
    ...
]

Building an example set

examples = [
    {
        "question": "Does Henry Campbell have any pets?",
        "answer": "Henry Campbell has a dog called Pluto."
    },
    ...
]

# Convert pandas DataFrame to list of dicts
examples = df.to_dict(orient="records")

Formatting the examples

from langchain_core.prompts import FewShotPromptTemplate, PromptTemplate


example_prompt = PromptTemplate.from_template("Question: {question}\n{answer}")

prompt = example_prompt.invoke({"question": "What is the capital of Italy?"
                                "answer": "Rome"})
print(prompt.text)

Question: What is the capital of Italy?
Rome

FewShotPromptTemplate

prompt_template = FewShotPromptTemplate(

    examples=examples,

    example_prompt=example_prompt,

    suffix="Question: {input}",

    input_variables=["input"]

)

examples: the list of dicts
example_prompt: formatted template
suffix: suffix to add to the input
input_variables

Invoking the few-shot prompt template

prompt = prompt_template.invoke({"input": "What is the name of Henry Campbell's dog?"})

print(prompt.text)

Question: Does Henry Campbell have any pets?
Henry Campbell has a dog called Pluto.
...

Question: What is the name of Henry Campbell's dog?

Integration with a chain

llm = ChatOpenAI(model="gpt-4o-mini", api_key="...")


llm_chain = prompt_template | llm
response = llm_chain.invoke({"input": "What is the name of Henry Campbell's dog?"})

print(response.content)

The name of Henry Campbell's dog is Pluto.

Let's practice!

Developing LLM Applications with LangChain