TypeScript prompt compression guide

API-based integration

// compress.ts
const SUPERCOMPRESS_API_KEY = process.env.SUPERCOMPRESS_API_KEY;

export async function compress(context: string, query: string) {
  const res = await fetch("https://supercompress.dev/api/v1/compress", {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "X-API-Key": SUPERCOMPRESS_API_KEY,
    },
    body: JSON.stringify({ context, query }),
  });
  const data = await res.json();
  return data.compressed_text;
}

Vercel AI SDK integration

import { StreamingTextResponse } from "ai";
import { openai } from "@ai-sdk/openai";
import { compress } from "./compress";

export async function POST(req: Request) {
  const { messages } = await req.json();
  const latestQuery = messages[messages.length - 1].content;
  const history = messages.slice(0, -1)
    .map((m: any) => `${m.role}: ${m.content}`).join("\n");

  const compressed = await compress(history, latestQuery);

  const response = await openai.chat.completions.create({
    model: "gpt-4o",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: compressed + "\n\n" + latestQuery },
    ],
    stream: true,
  });

  return new StreamingTextResponse(response);
}

Frequently asked questions

Is there a native npm package?

Not yet. Use the REST API for now. A native npm wrapper is on the roadmap.

Does the API support streaming?

Compression returns the compressed text synchronously. Use it before your streaming LLM call.