Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/patrickhulce/hulkchat

Last synced: 10 days ago
JSON representation

Host: GitHub
URL: https://github.com/patrickhulce/hulkchat
Owner: patrickhulce
License: other
Created: 2023-07-14T21:19:37.000Z (over 1 year ago)
Default Branch: main
Last Pushed: 2023-09-12T02:03:33.000Z (about 1 year ago)
Last Synced: 2024-10-19T00:49:55.269Z (25 days ago)
Language: TypeScript
Homepage: https://hulkchat.vercel.app
Size: 356 KB
Stars: 0
Watchers: 2
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        

  
HulkChat






  An open-source AI chatbot app built with Next.js, the Vercel AI SDK, OpenAI, Anthropic, and Vercel KV.





  Features ·

  Model Providers ·

  Running locally ·






## Features

- [Next.js](https://nextjs.org) App Router

- React Server Components (RSCs), Suspense, and Server Actions

- [Vercel AI SDK](https://sdk.vercel.ai/docs) for streaming chat UI

- Support for OpenAI (default) and Anthropic

- Edge runtime-ready

- Chat History, rate limiting, and session storage with [Vercel KV](https://vercel.com/storage/kv)

- [NextAuth.js](https://github.com/nextauthjs/next-auth) for authentication

## Model Providers

This template ships with OpenAI `gpt-3.5-turbo` as the default. However, thanks to the [Vercel AI SDK](https://sdk.vercel.ai/docs), you can switch LLM providers to [Anthropic](https://anthropic.com), [Hugging Face](https://huggingface.co), or using [LangChain](https://js.langchain.com) with just a few lines of code.

## Running locally

1. Install Vercel CLI: `npm i -g vercel`

2. Link local instance with the Vercel project accounts (creates `.vercel` directory): `vercel link`

3. Download the environment variables: `vercel env pull`

### First Terminal

```bash

pnpm install

pnpm dev

```

### Second Terminal

```bash

npx inngest-cli@latest dev

```

The app should now be running on [localhost:3000](http://localhost:3000/).