OpenAI Assistant SDK

⚠️ UNDER DEVELOPMENT: This package is currently in active development and not ready for production use.

This package provides an easy-to-use interface for interacting with OpenAI's API to manage assistants, threads, messages, and runs.

Features

• Create, retrieve, update, and delete Assistants.
• Manage threads to handle conversations.
• Send and manage messages within threads.
• Initiate and control runs for processing interactions.

Installation

You can add this package to your project by including it in your JavaScript environment. Ensure you have axios installed:

npm install axios

Usage

Here is a basic example of how to use the OpenAIAssistant class to interact with OpenAI's API.

import OpenAIAssistant from './OpenAIAssistant.js';

const apiKey = 'your-openai-api-key';
const assistant = new OpenAIAssistant(apiKey);

async function createAndManageAssistant() {
    const assistantData = {
        model: 'gpt-4o',
        instructions: 'You are a helpful assistant.',
        name: 'My Assistant'
    };

    // Create a new assistant
    const newAssistant = await assistant.createAssistant(assistantData);
    console.log('Assistant Created:', newAssistant);

    // Retrieve an assistant
    const fetchedAssistant = await assistant.retrieveAssistant(newAssistant.id);
    console.log('Assistant Details:', fetchedAssistant);
}

createAndManageAssistant();

Methods

The SDK includes several methods for interacting with the OpenAI API:

• createAssistant(data)
• listAssistants()
• retrieveAssistant(assistantId)
• updateAssistant(assistantId, data)
• deleteAssistant(assistantId)
• createThread(data)
• retrieveThread(threadId)
• updateThread(threadId, data)
• deleteThread(threadId)
• createMessage(threadId, data)
• retrieveMessage(threadId, messageId)
• listMessages(threadId)
• updateMessage(threadId, messageId, data)
• deleteMessage(threadId, messageId)
• createRun(threadId, data)
• retrieveRun(threadId, runId)
• listRuns(threadId)
• cancelRun(threadId, runId)

Configuration

Ensure your API key is securely stored and not hardcoded in your production applications.

For detailed API documentation and more examples, visit OpenAI API Documentation.

License

This project is licensed under the MIT License - See the LICENSE.md file for details..