A better prompt engineering library built for JS. Langchain.js feels like a python team writing JS

Levan Kvirkvelia — Tue, 30 May 2023 17:51:48 +0000

As JS (Mostly TS) devs, we feel like AI or LLM tooling in JS kinda sucks rn, that said most production applications inevitably end up being in JS, so a friend and I started hacking on a new JS native library for making it easier to write prompts.

The idea of the library is to give a much more ergonomic syntax for writing complex prompts, the repo itself goes much more in detail

https://github.com/LevanKvirkvelia/salute

import { gpt3, gen, assistant, system, user } from "salute";

const agent = gpt3(
  ({ params })=>[
    system`You are a helpful and terse assistant.`,
    user`
      I want a response to the following question: 
      ${params.query}
      Don't answer the question yet.
      Name 3 world-class experts (past or present) who would be great at answering this?
    `,
    assistant`${gen("expertNames")}`,
    user`
      Great, now please answer the question as if these experts had collaborated in writing a joint anonymous answer.
    `,
    assistant`${gen("answer")}`,
    user`Are you sure you gave a good answer? Write the answer again and fix it if necessary.`,
    assistant`${gen("fixedAnswer")}`,
  ]
);

const result = await agent(
  { query: `How can I be more productive?` },
  { render: true }
);

console.log(result);

DEV Community: Levan Kvirkvelia

A better prompt engineering library built for JS. Langchain.js feels like a python team writing JS