Multiple AI models always same syntax

Welcome to Middlebop, integrate with multiple AI models using one single syntax. Our library serves as a unified interface, allowing you to communicate with multiple AI models and seemlessly switch between them in real time without rewriting your code.

Before you begin

Make sure you have a Middlebop account and have created an API key that you will use with the api and clients.

:warning: Always store your Middlebop API key safely! Never share it and we recommend to always call it from your backend!

You can create and handle your API keys at https://middlebop.com

npm install @middlebop/client # or yarn add @middlebop/client or bun add @middlebop/client

Chat completion example

import { sendChat } from "middlebop";

const middlebopApiKey = "mb-yourSuperSecretApiKey";

const messages: MiddlebopChatMessage[] = [
  {
    role: "user",
    content: {
      type: "text",
      text: "Hello, who are you?",
    },
  },
];

const response = await sendChat({
  messages,
  model: "gpt-4",
  middlebopApiKey,
});

console.log(response.data);
// OUTPUT:
// {
//   "responseMessages": [
//     {
//       "role": "assistant",
//       "content": {
//         "type": "text",
//         "text": "Hello! I'm AI developed by OpenAI. How can I help you today?"
//       }
//     }
//   ]
// }

Streaming chat response example

Input is the same as when creating a non streaming chat response. When calling the streaming chat function you pass a callback handler that recieves every chunk. You can also pass in an error handler.

import {
  MiddlebopChatMessage,
  startChatStream,
} from "middlebop";

const middlebopApiKey = "mb-yourSuperSecretApiKey";

const messages: MiddlebopChatMessage[] = [
  {
    role: "system",
    content: {
      type: "text",
      text: "You are a helpful assistant called beep-boop",
    },
  },
  {
    role: "user",
    content: {
      type: "text",
      text: "Hello, who are you?",
    },
  },
];

const onStreamResponse = (chunk: MiddlebopChatCompletionStreamChunk) => {
  console.log(chunk);
};

const onStreamError = (error: unknown) => {
  console.error(error);
};

startChatStream(
  {
    messages,
    model: "gemini-pro",
    middlebopApiKey,
  },
  onStreamResponse,
  onStreamError
);

// CHUNK OUTPUT EXAMPLE
// {
//   "type": "chunk",
//   "model": "gemini-pro",
//   "messages": [
//     {
//       "role": "assistant",
//       "content": {
//         "type": "text",
//         "text": "Hello"
//       }
//     }
//   ]
// }

More documentation can be found at https://docs.middlebop.com