開源AI聊天機器人堆疊（代理、記憶體、前端）一鍵部署

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

Uh oh!

There was an error while loading. Please reload this page.

Delta-Darkly/AI-Chatbot

Folders and files

Latest commit

History

Repository files navigation

🤖 AI Chatbot with Dank AI Agent + Weaviate Memory

A production-ready, full-stack template demonstrating how to build an AI chatbot with persistent memory using Dank AI agents and Weaviate vector database. Optimized for quick local development (one command) and seamless deployment to production.

📋 Table of Contents

What is This?

This repository is a complete, production-ready template for building AI chatbots with:

Perfect for:

What is Dank AI?

Dank AI is a framework that lets you build AI agents using JavaScript. Instead of complex Python setups or extensive infrastructure, you can:

Key Benefits:

Think of it as "Vercel for AI agents" - you write JavaScript, push to GitHub, and deploy with a single click.

Architecture Overview

Request Flow

Quick Start

Prerequisites

Before you begin, ensure you have:

First-Time Setup

Fork the repository

Option A: Fork from Dank Cloud (Recommended)

Option B: Fork directly from GitHub

Clone your forked repository

Why fork? Forking creates your own copy that you can modify and deploy to your own Dank Cloud project. If you clone the original repo directly, you won't be able to push changes or deploy to your own project.

Set up the agent environment

Edit .env and add your API key:

Note for deployment: If you plan to deploy to Dank Cloud, ensure the agent ID in dank.config.js is unique. Generate a new UUIDv4 if needed (see Deployment section for details).

Run everything with one command

This will:

Open your browser

Stop everything

What You Should See

Project Structure

How It Works

Component Breakdown

The Dank AI agent handles:

Key Files:

Weaviate provides:

Runs:

The React frontend provides:

Proxies:

Data Flow Example

Using as a Template

This project is designed to be forked and customized for your own use cases.

For Agent Development

Copy the agent directory (ai-chatbot-weaviate/) to start your own agent:

What to reuse:

For Frontend Integration

Copy the service files to integrate with your own frontend:

agentService.ts: Drop into your project to call the agent

weaviateService.ts: Drop into your project to manage conversations

Proxy patterns: Copy the proxy setup to avoid CORS issues

What to reuse:

Environment Configuration

Agent Environment (ai-chatbot-weaviate/.env)

Frontend Environment (chatbot-frontend/.env)

Environment Toggle Behavior

💡 Tip: You can mix and match! Test frontend against production agent/Weaviate by setting AGENT_ENV=prod or WEAVIATE_ENV=prod in the frontend .env while keeping the other local.

Deployment

⚠️ Important: Before deploying, ensure your agent ID in ai-chatbot-weaviate/dank.config.js is unique. Deployment will fail if you use an existing agent ID. Generate a new UUIDv4 using uuid.v4() (you can run node -e "console.log(require('uuid').v4())" in the ai-chatbot-weaviate directory).

Agent + Weaviate (Dank Cloud)

Push to GitHub

Create Project on Dank Cloud

Configure and Deploy Project

Create API Key for Weaviate

Enable Weaviate Service

Add Environment Variables

Rebuild and Deploy

Optional: Secure Agent Endpoint

Test Your Agent (Bonus)

Without API key:

With API key (if configured):

Frontend (Vercel)

Push to GitHub (if not already done)

Connect to Vercel

Set Environment Variables

Deploy

🎉 Done! Your chatbot is now live in production.

Troubleshooting

Common Issues

Error: Cannot connect to Docker daemon

Solution:

Error: Port 5173 (or 3000, 8080) is already in use

Solution:

Error: Agent returns 500 or timeout

Check:

Error: Cannot connect to Weaviate

Solution:

Error: CORS policy: No 'Access-Control-Allow-Origin' header

Solution:

Error: 404 Not Found when calling /api/agent/prompt

Solution:

Getting Help

Learn More

Detailed Documentation

Key Concepts

Next Steps

Built with ❤️ using Dank AI and Weaviate

About

Resources

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

Packages

  0

Languages

Footer

Footer navigation