Flowise prompt compression

Custom Flowise node

// Custom Function Node in Flowise
const fetch = require("node-fetch");

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

Frequently asked questions

Where in the Flowise flow should I add compression?

Between the document retrieval node and the LLM chat node. This compresses the retrieved context before generation.

Does it work with Flowise's chat memory?

Yes. Compress the conversation history stored in Flowise's memory node before each LLM call.