Integrations

Node.js SDK

Connect to DEVUP AI using the official devupai npm package. Built for Node.js, Bun, and Deno with TypeScript definitions, streaming completions, embeddings, and error handling.

Prerequisites

A DEVUP AI account with a valid API key (Dashboard → API Keys).
Node.js 18.0.0 or later (or a modern runtime such as Bun or Deno).

Installation

Install the official client package from npm:

npm install devupai

Create a client

Instantiate the client by passing your API key, or let the SDK read it automatically from the DEVUP_API_KEY environment variable:

import DevupAI from "devupai";

const apiKey = process.env.DEVUP_API_KEY;
if (!apiKey) throw new Error("Set the DEVUP_API_KEY environment variable.");

const client = new DevupAI({
  apiKey,
});

Chat completions

Create non-streaming completions using client.chat.completions.create:

import DevupAI from "devupai";

const apiKey = process.env.DEVUP_API_KEY;
if (!apiKey) throw new Error("Set the DEVUP_API_KEY environment variable.");

const client = new DevupAI({
  apiKey,
});

const response = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-V4-Pro",
  messages: [{ role: "user", content: "Say hello in one word." }],
});

console.log(response.choices[0]?.message?.content);

Streaming

Stream tokens as they are generated.

import DevupAI from "devupai";

const apiKey = process.env.DEVUP_API_KEY;
if (!apiKey) throw new Error("Set the DEVUP_API_KEY environment variable.");

const client = new DevupAI({ apiKey });

const stream = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-V4-Pro",
  messages: [{ role: "user", content: "Count from 1 to 5." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices?.[0]?.delta?.content ?? "");
}
process.stdout.write("\n");

Embeddings

Generate dense vector representations for semantic search or retrieval with client.embeddings.create:

import DevupAI from "devupai";

const apiKey = process.env.DEVUP_API_KEY;
if (!apiKey) throw new Error("Set the DEVUP_API_KEY environment variable.");

const client = new DevupAI({
  apiKey,
});

const response = await client.embeddings.create({
  model: "BAAI/bge-m3",
  input: ["First document for search", "Second document for retrieval"],
});

console.log("Vectors:", response.data.length);
console.log("Dimensions:", response.data[0]?.embedding?.length);

Configuration

Configure client-level defaults such as base URLs and custom headers, or supply per-request timeouts and headers:

import DevupAI from "devupai";

const apiKey = process.env.DEVUP_API_KEY;
if (!apiKey) throw new Error("Set the DEVUP_API_KEY environment variable.");

const client = new DevupAI({
  apiKey,
  baseURL: "https://api.devupai.com/v1",
  headers: {
    "X-Application-Name": "docs-example",
  },
});

const response = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-V4-Pro",
  messages: [{ role: "user", content: "Say hello in one word." }],
  timeout: 30000,
  headers: {
    "X-Request-Source": "nodejs-guide",
  },
});

console.log(response.choices[0]?.message?.content);

Error handling

Catch DevupAPIError to inspect HTTP status codes, error codes, and request identifiers:

import DevupAI, { DevupAPIError } from "devupai";

const apiKey = process.env.DEVUP_API_KEY;
if (!apiKey) throw new Error("Set the DEVUP_API_KEY environment variable.");

const client = new DevupAI({
  apiKey,
});

try {
  await client.chat.completions.create({
    model: "deepseek-ai/DeepSeek-V4-Pro",
    messages: [{ role: "user", content: "Hi" }],
  });
} catch (error) {
  if (error instanceof DevupAPIError) {
    console.log(error.name + " " + error.status);
  } else {
    throw error;
  }
}

For error classifications and status codes, see the Error handling guide.

Webhooks

The SDK includes built-in webhook signature verification utilities (client.webhooks.verifySignature and client.webhooks.constructEvent). For webhook configuration, secret management, and payload structures, see the Webhooks documentation.

n8n

Open WebUI