JavaScript / Node.js

Use the official OpenAI SDK with Conduit.im — just change two lines of configuration.

Installation

Conduit.im is fully compatible with the official OpenAI Node.js SDK. Install it with your preferred package manager:

npm install openai

Configuration

Point the SDK at the Conduit.im API by setting the baseURL and using your Conduit.im API key:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CONDUIT_API_KEY,
  baseURL: "https://api.conduit.im/v1",
});

Note: If you have existing code that uses the OpenAI SDK, these two properties (apiKey and baseURL) are the only changes needed to switch to Conduit.im.

Chat Completions

Send a chat completion request just like you would with the OpenAI API:

const response = await client.chat.completions.create({
  model: "gpt-4",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is the capital of France?" },
  ],
});

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

Streaming

The SDK has built-in support for streaming. Set stream: true and iterate over the response:

const stream = await client.chat.completions.create({
  model: "gpt-4",
  messages: [{ role: "user", content: "Write a short poem about APIs." }],
  stream: true,
});

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

console.log(); // trailing newline

Error Handling

The SDK throws typed errors that you can catch and handle individually:

import OpenAI from "openai";

try {
  const response = await client.chat.completions.create({
    model: "gpt-4",
    messages: [{ role: "user", content: "Hello!" }],
  });
  console.log(response.choices[0].message.content);
} catch (error) {
  if (error instanceof OpenAI.APIError) {
    console.error("API error:", error.status, error.message);

    if (error.status === 401) {
      console.error("Invalid API key. Check your CONDUIT_API_KEY.");
    } else if (error.status === 429) {
      console.error("Rate limited. Retry after a short delay.");
    } else if (error.status === 402) {
      console.error("Insufficient balance. Add funds to your account.");
    }
  } else {
    throw error;
  }
}

Using Fetch Directly

If you prefer not to use the SDK, you can call the API directly with fetch:

const response = await fetch("https://api.conduit.im/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.CONDUIT_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "gpt-4",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

TypeScript Support

The OpenAI SDK ships with full TypeScript type definitions out of the box. All request parameters and response objects are fully typed:

import OpenAI from "openai";
import type { ChatCompletionMessageParam } from "openai/resources";

const messages: ChatCompletionMessageParam[] = [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Hello!" },
];

const response = await client.chat.completions.create({
  model: "gpt-4",
  messages,
});