llm-exe
Invoke llm-exe as a AWS lambda function. Deploy using CDK. View on Github

Appearance

llm-exe

A package that provides simplified base components to make building and maintaining LLM-powered applications easier.

Documentation
See Examples
Github
llm-exe

Modular

Write functions powered by LLM's with easy to use building blocks.

Few Dependencies

Pure Javascript and Typescript. Allows you to pass and infer types.

Use {{variables}}

Supercharge your prompts by using handlebars expressions and functions.

Control

Not very opinionated. You have control on how you use it.

Chat or Text Prompts

Support for text-based and chat-based prompts.

Function Calling

Allow LLM's to call functions (or call other LLM executors).

Prompt Templates

Build reusable prompt template parts.

Test Coverage

100% test coverage

Quick Example ​

ts
import * as llmExe from "llm-exe";

/**
 * Define a yes/no llm-powered function
 */
export async function YesOrNoBot<I extends string>(input: I) {
  const llm = llmExe.useLlm("openai.gpt-4o-mini");

  const instruction = `You are not an assistant, I need you to reply with only 
  'yes' or 'no' as an answer to the question below. Do not explain yourself 
  or ask questions. Answer with only yes or no.`;

  const prompt = llmExe
    .createChatPrompt(instruction)
    .addUserMessage(input)
    .addUserMessage(`yes or no:`);

  const parser = llmExe.createParser("stringExtract", { enum: ["yes", "no"] });
  return llmExe.createLlmExecutor({ llm, prompt, parser }).execute({ input });
}
ts
const isTheSkyBlue = await YesOrNoBot(`Can the sky be blue?`)
// yes

const isGrassRed = await YesOrNoBot(`Is grass usually red?`)
// no

Want to use a different model? ​

All you need to do is change this one line to use any of the supported models. Make sure you have configured API keys.

ts
import * as llmExe from "llm-exe";

/**
 * Define a yes/no llm-powered function
 */
export async function YesOrNoBot<I extends string>(input: I) {
  const llm = llmExe.useLlm("openai.gpt-4o-mini"); 
  // const llm = llmExe.useLlm("openai.gpt-4o"); // or
  // const llm = llmExe.useLlm("google.gemini-2.0-flash"); // or
  // const llm = llmExe.useLlm("xai.grok-2"); // or
  // const llm = llmExe.useLlm("anthropic.claude-3-7-sonnet"); // or
  // const llm = llmExe.useLlm("deepseek.chat"); // or
  // const llm = llmExe.useLlm("anthropic.claude-3-opus"); // or
  // const llm = llmExe.useLlm("google.gemini-1.5-pro"); // or
  // ..and many more!


  const instruction = `You are not an assistant, I need you to reply with only 
  'yes' or 'no' as an answer to the question below. Do not explain yourself 
  or ask questions. Answer with only yes or no.`;

  const prompt = llmExe
    .createChatPrompt(instruction)
    .addUserMessage(input)
    .addUserMessage(`yes or no:`);

  const parser = llmExe.createParser("stringExtract", { enum: ["yes", "no"] });
  return llmExe.createLlmExecutor({ llm, prompt, parser }).execute({ input });
}