Docs on HappyRock

Hermes Web Chat MVP in Action: Building Your Own AI Web Chat System from Scratch (Full Version)

Thu, 09 Jul 2026 00:23:18 +0800

Chapter 1 Why Build Hermes Web Chat

Chapter 2 Overall Architecture Design

Chapter 3 Project Directory

Chapter 4 Frontend Page Development

Chapter 5 FastAPI Backend

Chapter 6 DeepSeek Integration

Chapter 7 API Design

Chapter 8 OpenResty Proxy Configuration

Chapter 9 HTTPS Deployment

Chapter 10 Systemd Deployment

Chapter 11 Common Troubleshooting

Chapter 12 Performance Optimization

Chapter 13 Next Upgrade Directions

Appendix A Full Source Code

Appendix B Complete nginx Configuration

Appendix C Complete systemd Configuration

Chapter 1 Why Build Hermes Web Chat

Previously, our Hermes Agent could already:

Enterprise WeChat AI Auto-Reply System Troubleshooting Record (Docker + FastAPI + Redis)

Thu, 02 Jul 2026 04:23:18 +0800

This troubleshooting journey covered a typical “enterprise‑level AI message‑processing pipeline” — from Webhook → Redis queue → Worker → AI → Enterprise WeChat sending. Almost every layer of the chain presented a pitfall.

The entire set of issues can be summarised in one sentence:

It wasn’t that the system wasn’t running, but rather that the combination of “multi‑layer structure + configuration + indentation + imports + startup methods” broke the entire chain.

Complete Implementation Plan for Enterprise WeChat AI Auto-Reply System (Runable Version)

Thu, 02 Jul 2026 01:23:18 +0800

Below is a complete, production-ready implementation plan for an “Enterprise WeChat AI Bot (DeepSeek + Redis + Worker Architecture)” that integrates all the pitfalls I have already encountered (callback, queue, worker, IP whitelist, send failures, etc.) into a standardized step‑by‑step guide.

I. Overall Architecture Design

This is a typical “event‑driven + queue‑decoupled + AI‑processing” architecture:

Enterprise WeChat User
      │
      ▼
Enterprise WeChat Server
      │
      ▼
Nginx / OpenResty (Reverse Proxy + HTTPS)
      │
      ▼
FastAPI (Callback Reception / Decryption / Enqueue)
      │
      ▼
Redis Queue (wecom_queue)
      │
      ▼
Worker (Task Consumer)
      │
      ├── Calls DeepSeek (AI Generation)
      ▼
Enterprise WeChat Message Send API
      │
      ▼
User Receives Reply

II. Environment Setup

1. Install Base Dependencies

apt update
apt install -y docker docker-compose

2. Create Project Directory

mkdir -p /opt/ai/wecom-bot
cd /opt/ai/wecom-bot

3. Basic Docker Compose Services

services:
  wecom-bot:
    build: .
    container_name: wecom-bot
    ports:
      - "8000:8000"
    depends_on:
      - redis

  worker:
    build: .
    container_name: wecom-worker
    command: python -m app.worker
    depends_on:
      - redis

  redis:
    image: redis:7-alpine
    container_name: ai-redis

III. FastAPI Callback Service (Core Entry)

File: `app/main.py`

Core responsibilities:

WeCom + DeepSeek: A Practical Record of Building a Usable AI Agent from 0 to 1

Wed, 01 Jul 2026 08:23:18 +0800

When doing AI automation within an enterprise, many people get stuck on the most basic problem:

“The WeCom callback works fine, but it just doesn’t reply.”

This article is a complete record of the practical process: from integrating the WeCom callback, to driving AI replies with DeepSeek, and finally getting a usable AI Agent up and running.

This is not a concept, but a system that actually runs in production.

Use Let’s Encrypt to Apply for a Free HTTPS Certificate for Your Website (Complete Tutorial)

Thu, 25 Jun 2026 22:42:54 +0800

📌 This article explains how to configure a free HTTPS certificate for your domain on a Linux (Ubuntu / Debian / CentOS) server, with automatic renewal.

Suitable for:

Nginx / OpenResty
PHP websites (e.g., forums, Flarum)
Static sites (Hugo / Vue SPA)
API services

1. Prerequisites

1️⃣ Must have

A properly resolved domain name (A record pointing to your server IP)
Server ports 80 / 443 accessible
root or sudo privileges

2️⃣ Verify domain resolution

ping forum.happyrock.cloud

Or:

Complete Tutorial: Docker Desktop + n8n + Qdrant + Embedding Auto-Ingestion Pipeline

Fri, 19 Jun 2026 16:19:24 +0800

🚀 Complete Tutorial: Docker Desktop + n8n + Qdrant + Embedding Auto-Ingestion Pipeline

A fully local AI knowledge base system you can run right away: Webhook → Embedding → n8n processing → Qdrant vector database → searchable knowledge base Including all the pitfalls I personally encountered (Webhook parsing, vector format, HTTP JSON errors, payload structure, etc.) — this is the “bug-proof” edition.

🧱 1. Overall Architecture

User Request (Webhook)
        ↓
n8n Workflow
        ↓
Embedding Model (Ollama / OpenAI)
        ↓
Set Node (standardize structure)
        ↓
HTTP Request (write to Qdrant)
        ↓
Qdrant Vector DB
        ↓
Subsequent retrieval / RAG

🐳 2. Launch Qdrant + n8n with Docker Desktop

1️⃣ docker-compose.yml

version: "3.9"

services:
  qdrant:
    image: qdrant/qdrant
    ports:
      - "6333:6333"
    volumes:
      - ./qdrant_data:/qdrant/storage

  n8n:
    image: n8nio/n8n
    ports:
      - "5678:5678"
    environment:
      - N8N_HOST=localhost
      - N8N_PORT=5678
      - N8N_PROTOCOL=http
      - NODE_ENV=production
    volumes:
      - ./n8n_data:/home/node/.n8n

Start up:

Building an AI News Automation System from Scratch: A Hands-On Tutorial for Deploying n8n + DeepSeek + Hugo on Ubuntu

Sun, 07 Jun 2026 00:23:18 +0800

Author: HappyRock

Target Audience: Developers, Indie Developers, Technical Managers, AI Enthusiasts

Tech Stack: Ubuntu + Docker + n8n + DeepSeek + Hugo

Preface

In the past few years, we’ve been used to:

Open RSS
↓
Browse News
↓
Filter Hot Topics
↓
Summarize
↓
Write WeChat Article
↓
Publish Blog Post

The whole process often takes 1–2 hours.

But in the era of AI Agents, these tasks can already be handed over to AI.