Developing the Application

Cloning the Repository

Clone the GitHub repository to start development. You can edit the code using your preferred editor and use the application in a local environment with Node.js.

GitHub Repository Check out the TutoriaLLM GitHub repository.

Setting Environment Variables

Below are examples of environment variables. Set them in /apps/frontend/.env and /apps/backend/.env.

/apps/frontend/.env

VITE_BACKEND_URL=http://localhost:3001

/apps/backend/.env

OPENAI_API_KEY="sk-xxxxxx"
OPENAI_API_ENDPOINT="https://your-openai-api-endpoint"
BETTER_AUTH_URL="http://localhost:3001"
BETTER_AUTH_SECRET=dummyDummyDummy


CORS_ORIGIN="http://localhost:3000"
POSTGRES_USER=postgres
POSTGRES_PASSWORD=postgres
DB_PORT=5432
POSTGRES_DB="tutoriallm_db"
DB_HOST="db.tutoriallm.local"

DOMAIN="localhost"
EMAIL="[email protected]"

DEFAULT_USER_PASSWORD="admin"
DEFAULT_USER_NAME="admin"

S3_USER="s3_root"
S3_PASSWORD="s3_password"
S3_ACCESS_KEY_ID="s3_access_key_id"
S3_SECRET_ACCESS_KEY="s3_secret_access_key"

When using the documentation development server (apps/docs), set the environment variables in /apps/docs/.env.

/apps/docs/.env

OPENAPI_DOCS_URL=http://localhost:3001

Connecting to the Database

TutoriaLLM requires a connection to PostgreSQL with vector capabilities. Here’s how to use Docker compose with pgvector.

/docker-compose.pg.yml

services:
  db:
    container_name: tutoriallm_db
    image: pgvector/pgvector:pg14
    ports:
      - "5432:5432"
    env_file:
      - ./apps/backend/.env
    environment:
      - POSTGRES_USER
      - POSTGRES_PASSWORD
      - POSTGRES_DB
      - PGDATA=/var/lib/postgresql/data/pgdata
      - TZ=UTC
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U $POSTGRES_USER -d $POSTGRES_DB"]
      interval: 5s
      timeout: 60s
      retries: 5
      start_period: 5s
    volumes:
      - db_data_db:/var/lib/postgresql/data
volumes:
  db_data_db:

About Docker

For information about Docker, refer to Docker.

Starting the Server

(Recommended) Starting with Docker

Use Docker compose to start the frontend and backend. Use the docker-compose.yml and docker-compose.dev.override.yml files in the TutoriaLLM repository.

Start the server

docker compose -f docker-compose.yml -f docker-compose.dev.override.yml up --build # Build and start
docker compose -f docker-compose.yml -f docker-compose.dev.override.yml up # Start

If you need to start the documentation development server, use pnpm.

Starting with pnpm

You can start the frontend and backend individually using pnpm.

Start the database:

Start the database

docker compose up

Start the frontend, backend, and documentation (if needed) with the following commands:

Start the development server

# Frontend
cd apps/frontend
pnpm i && pnpm dev

# Backend
cd apps/backend
pnpm i && pnpm dev

# Documentation
cd apps/docs
pnpm i && pnpm dev

Note

By default, TutoriaLLM uses port 3000 for the frontend and port 3001 as the API entry point.

Sharing Type Definitions

This repository uses pnpm workspace to share type definitions between the frontend and backend. Type definitions are defined in the backend and can be used in the frontend.

Build the type definitions

# Generate type definitions in the backend
cd apps/backend
pnpm run build

Testing

Run tests with the following command in the root directory:

Test

pnpm test

Developing Extensions

Extensions are located in /packages/extensions by default. Place your extensions in this directory when creating them. The values exported in index.ts are used by the frontend and backend.

After defining an extension, build it with the following command:

Build the extension

# Build the extension
pnpm run build

After building, restart the frontend and backend.