langchain

What is langchain?

The langchain npm package is designed to facilitate the development of applications that leverage language models. It provides tools for chaining together different language model operations, managing prompts, and integrating with various data sources.

What are langchain's main functionalities?

Prompt Management

This feature allows you to create and manage prompts easily. You can define templates and format them with dynamic data.

const { PromptTemplate } = require('langchain');

const template = new PromptTemplate('Translate the following text to French: {text}');
const prompt = template.format({ text: 'Hello, how are you?' });
console.log(prompt); // Output: Translate the following text to French: Hello, how are you?

Chaining Operations

This feature allows you to chain together multiple operations, where the output of one step becomes the input to the next.

const { Chain } = require('langchain');

const chain = new Chain();
chain.addStep(async (input) => `Step 1: ${input}`);
chain.addStep(async (input) => `Step 2: ${input}`);

chain.run('Initial Input').then(console.log); // Output: Step 2: Step 1: Initial Input

Integration with Data Sources

This feature allows you to integrate with various data sources, making it easy to fetch and use data within your language model operations.

const { DataSource } = require('langchain');

const dataSource = new DataSource('https://api.example.com/data');
dataSource.fetch().then(data => console.log(data));

Other packages similar to langchain

openai

The openai npm package provides a simple interface to interact with OpenAI's GPT-3 and other models. While it focuses on direct interaction with OpenAI's API, langchain offers more advanced features like prompt management and chaining operations.

node-nlp

The node-nlp package is a natural language processing library for Node.js. It provides tools for entity extraction, sentiment analysis, and more. While it offers a broad range of NLP functionalities, langchain is more specialized in chaining language model operations and managing prompts.

compromise

Compromise is a lightweight NLP library for Node.js. It focuses on text processing and manipulation. Compared to langchain, compromise is more about text analysis and less about chaining language model operations or managing prompts.

README

🦜️🔗 LangChain.js

⚡ Building applications with LLMs through composability ⚡

Looking for the Python version? Check out LangChain.

To help you ship LangChain apps to production faster, check out LangSmith. LangSmith is a unified developer platform for building, testing, and monitoring LLM applications. Fill out this form to get off the waitlist or speak with our sales team

Quick Install

yarn add langchain

import { OpenAI } from "langchain/llms/openai";

Supported Environments

LangChain is written in TypeScript and can be used in:

• Node.js (ESM and CommonJS) - 18.x, 19.x, 20.x
• Cloudflare Workers
• Vercel / Next.js (Browser, Serverless and Edge functions)
• Supabase Edge Functions
• Browser
• Deno

🤔 What is this?

Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.

This library is aimed at assisting in the development of those types of applications.

📖 Full Documentation

For full documentation of prompts, chains, agents and more, please see here.

Relationship with Python LangChain

This is built to integrate as seamlessly as possible with the LangChain Python package. Specifically, this means all objects (prompts, LLMs, chains, etc) are designed in a way where they can be serialized and shared between languages.

The LangChainHub is a central place for the serialized versions of these prompts, chains, and agents.

💁 Contributing

As an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.

Check out our contributing guidelines for instructions on how to contribute.