LangChain

LangChain is your Swiss Army knife for building AI-powered apps. It’s packed with features for working with language models, creating agents, managing vector stores, and implementing retrieval augmented generation (RAG). But here’s the catch - it doesn’t handle UI stuff or streaming data to the client out of the box. That’s where we come in!

Quick Example: Completion

// api/completion/route.ts
import { ChatOpenAI } from '@langchain/openai';
import { LangChainAdapter } from 'ai';

export const maxDuration = 60;

export async function POST(req: Request) {
  const { prompt } = await req.json();

  const model = new ChatOpenAI({
    model: 'gpt-3.5-turbo-0125',
    temperature: 0,
  });

  const stream = await model.stream(prompt);

  return LangChainAdapter.toDataStreamResponse(stream);
}

For the frontend, you’ll want to hook this up to your UI using our handy useCompletion hook.