FAQ Bot with ChromaDB and moderate-censor

This project implements an FAQ bot that uses ChromaDB for vector storage and retrieval, and moderate-censor as the single MCP-tool for content moderation.

Features

Vector-based FAQ retrieval using OpenAI embeddings and ChromaDB.
User input moderation with moderate-censor.
Simple HTTP API (/ask) to query the bot.

Prerequisites

Node.js v18+ (or any LTS version)
npm
OpenAI API key (set in .env)
ChromaDB server running locally (default path: chromadb)

Setup

Clone the repository

git clone <repo-url>
cd <repo-directory>

Install dependencies
```
npm install
```

Create a .env file

OPENAI_API_KEY=your_openai_api_key
PORT=3000

Prepare FAQ data

Create a faq.json file in the project root with the following format:

[
  {
    "question": "What is ChromaDB?",
    "answer": "ChromaDB is a vector database for storing and retrieving embeddings."
  },
  {
    "question": "How do I use the bot?",
    "answer": "Send a POST request to /ask with a JSON body containing the 'question' field."
  }
]

Ingest FAQ data
```
npm run ingest
```
This will read faq.json, generate embeddings, and store them in ChromaDB.
Start the bot
```
npm start
```
The server will listen on the port specified in .env (default 3000).

Usage

Send a POST request to /ask:

curl -X POST http://localhost:3000/ask \
     -H "Content-Type: application/json" \
     -d '{"question":"What is ChromaDB?"}'

Response:

{
  "answer": "ChromaDB is a vector database for storing and retrieving embeddings."
}

If the question contains disallowed content, the bot will respond with a 403 status and reasons.

Project Structure

├── package.json
├── src
│   ├── index.js          # HTTP server and bot logic
│   ├── ingest.js         # FAQ ingestion script
│   └── middleware.js     # Moderation middleware
├── faq.json              # FAQ data file
└── README.md

Notes

The bot uses the text-embedding-ada-002 model for embeddings.
Only one MCP-tool (moderate-censor) is used as required.
Ensure the ChromaDB server is running before ingesting data or starting the bot.

License

MIT License

2.4 KiB Raw Blame History