This repository provides a template for building a chat application using OpenAI's Assistant API, targeting developers who want to create personalized AI assistants capable of interacting with files and potentially visual content. It offers a customizable chat experience with OpenAI's advanced models, simplifying the integration of AI into applications.

How It Works

The application leverages OpenAI's Assistant API to manage conversational threads and AI interactions. A central ChatManager class, implemented using a singleton pattern, orchestrates state management, file uploads, and API calls. The architecture separates concerns into distinct modules for API interactions, assistant management, and chat functionalities, with a React-based frontend for user interaction.

Quick Start & Requirements

• Install: npm install
• Prerequisites: Node.js, OpenAI API key.
• Deployment: Vercel is recommended, requiring OpenAI API key and optionally an Assistant ID during deployment.
• Docs: https://github.com/admineral/OpenAI-Assistant-API-Chat

Highlighted Details

• Utilizes OpenAI's gpt-4-1106-preview model with a 128k context window.
• Supports file uploads for the assistant to analyze.
• Includes GPT-4 Vision integration for image analysis (described as "improved version soon").
• Future features planned include Function Calls and Code Interpretation.

Maintenance & Community

The project is marked as "Code Refactor 90% done" with a dedicated Code_refactor branch. Contributions are encouraged via issues and pull requests.

Licensing & Compatibility

The repository does not explicitly state a license in the provided README.

Limitations & Caveats

The application is described as being in a "beta phase" and "Work in Progress," with potential for "hiccups or unexpected behavior." Function Calls and Code Interpretation features are listed as "Coming Soon."