Skip to main content

Prompt templates

info

Conceptual Guide

A fundemental part of working with language models is taking some input and formatting it in some way using a template. Doing this is simple using LangChain. Here is a simple example: 

import "github.com/tmc/langchaingo/prompts"

func main() {
    prompt := prompts.NewPromptTemplate(
        "What is a good name for a company that makes {{.product}}?",
        []string{"product"}, 
    )

    result, err := prompt.Format(map[string]any{
        "product": "colorful socks",
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(result)
}
What is a good name for a company that makes colorful socks?

A prompt template can take any number of inputs as shown belown.

prompt := prompts.NewPromptTemplate(
    "Tell me a {{.adjective}} joke about {{.content}}.",
    []string{"adjective", "content"}, 
)

result, err := prompt.Format(map[string]any{
    "adjective": "funny",
    "content": "chickens", 
})
if err != nil {
    log.Fatal(err)
}

fmt.Println(result)
Tell me a funny joke about chickens.

Creating prompt templates for chat messages​

Chat Models take a list of chat messages as input - this list is commonly referred to as a prompt. These chat messages differ from a raw string (which you would pass into a LLM model), in that every message is associated with a role.

For example, in OpenAI Chat Completion API, a chat message can be associated with the AI, human or system role. The model is supposed to follow instruction from system chat message more closely.

You are encouraged to use these chat related prompt templates instead of PromptTemplate when querying chat models to fully exploit the potential of underlying chat model.

import "github.com/tmc/langchaingo/prompts"

func main() {
   prompt := prompts.NewChatPromptTemplate([]MessageFormatter{
        NewSystemMessagePromptTemplate(
            "You are a translation engine that can only translate text and cannot interpret it.",
            nil,
        ),
        NewHumanMessagePromptTemplate(
            `translate this text from {{.inputLang}} to {{.outputLang}}:\n{{.input}}`,
            []string{"inputLang", "outputLang", "input"},
        ),
    })

    result, err := prompt.Format(map[string]any{
        "inputLang": "English",
        "outputLang": "Chinese",
        "input": "I love programming",
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(result)
}
[{You are a translation engine that can only translate text and cannot interpret it.} {translate this text from English to Chinese:\nI love programming}]

Dig deeper​