Skip to main content

Installation

Quick Start

curl -fsSL <download-url> -o install.sh
chmod +x install.sh
./install.sh
docker compose up -d

Replace <download-url> with the URL provided by your vendor.


What the Installer Creates

Running install.sh scaffolds all the files and directories RAG-DocBot needs:

Path / NameTypePurpose
.envFileAll runtime configuration (tokens, secrets, settings)
docker-compose.ymlFileService definitions
license.keyFileLicense validation
docs/DirectoryDrop documents here for indexing
branding/DirectoryCustom logos and branding assets
models/DirectoryPlace your GGUF model file here
postgres_dataDocker volumeAll application data
redis_dataDocker volumeLive job state
qdrant_storageDocker volumeVector index data

All application data lives in Docker named volumes — data survives container recreation and updates. Database migrations run automatically on every startup, so no manual schema management is needed.


Services

docker compose up -d starts the following services:

ServiceDescription
backendFastAPI application — the main API server
uiRAG-DocBot frontend
inferencellama-cpp-python inference server (serves the GGUF model)
qdrantVector database for the document index
postgresRelational database for application state
redisLive job state
pgadminPostgreSQL admin UI (port 5050 — for dev/admin use)

After Installation

  1. Place your GGUF model file in the models/ directory. See Placing a Model.
  2. Open the app in your browser. See Accessing the App.
  3. Log in with the default admin credentials and change the password immediately. See Changing Password.